AI builds your Muse can trust.
Skill Harbor is an open directory of AI builds that work with Muse — more personal assistants coming soon. We never touch your money: you always buy directly from the seller.
One copy-paste, no account, no API key — search in plain words, in French or English.
Spotlight
Admin Bridge
Run your website's back office from chat.
Stop opening your admin panel. Admin Bridge lets your Muse run your site's back office in plain conversation: it shows the moderation queue, approves or rejects submissions, publishes new listings, and keeps an action log — all through a secure token-protected API you add to your site in an afternoon. Sold by the founder of Skill Harbor — this purchase is a transaction with him personally, not with the Skill Harbor platform (which never processes payments).
✓ Sold by: Mush336 · v1.0.0
Entretien Auto
Car maintenance tracker — never miss an oil change again
Entretien Auto is a simple, private car maintenance tracker. Log oil changes, brake jobs and repairs, plan upcoming maintenance, and keep your vehicle's full history in one place. Your data stays yours — no account, no cloud, no ads.
✓ Created by: Skill Harbor · v1.0.0
Quest Board
Gamified quest board — turn tasks into XP, streaks and weekly bosses
Quest Board turns your to-do list into a game. Create quests, earn XP, level up with humorous titles, keep daily streaks alive, and face the weekly boss gauge. Deadlines are adjustable and finished tasks move to an archive. Built-in tracking for school, health and calendar.
✓ Created by: Skill Harbor · v1.0.0
Trade Bot
Automated paper-trading bot for NDAX
Trade Bot is an automated paper-trading prototype built for the NDAX exchange — momentum-based strategies in simulation mode, no real money ever at stake. Built as a strategy laboratory: propose a strategy, test it on paper, review the numbers. Currently paused.
✓ Created by: Skill Harbor · v1.0.0
Obsidian CLI
Command-line toolkit for Obsidian vaults — query notes, edit frontmatter, manage tags, create and organize notes
Curated by Skill Harbor — a command-line toolkit skill for Obsidian vaults: query notes, edit frontmatter, manage tags, create and organize notes from the shell — for automation and scripting around a vault. By @kepano, listed here with credit to its creator. Honest caveats: operates on your real vault files — destructive operations actually delete/move notes, so review commands before running; pair with `obsidian-bases` for formula questions. Skill Harbor never reviews the code, review it yourself before use.
Created by: @kepano · v
AI Film Studio
AI film-production planning: brief, shot packets, iteration supervision
Curated by Skill Harbor — a free, open-source build (MIT) by @Israelmusondaayliffe, listed here with credit to its creator. A Muse agent skill for explicit-only AI film-production planning: concept grill, film brief, production records (assets, performance, geography), model-neutral shot prompt packets built with bin/film_advisor.py, and iteration supervision. It plans and drafts — it never starts a live generation, upload, purchase or publication on its own; those need explicit approval. Ported from a community plugin.
Created by: @Israelmusondaayliffe · v
Fashion Closet Skill for Muse
A Markdown wardrobe memory that plans outfits from what you actually own.
Curated by Skill Harbor — a free, open-source skill (MIT) by @looong-cheng, listed here with credit to its creator. A Markdown-based wardrobe-memory system treated as reflection loop, not shopping bot: it catalogs your pieces with immutable IDs (intake from photos, labels, and facts), plans outfits from what you own — body-, weather-, and occasion-aware — logs what you wore with verdicts and lessons, and triages active/sleeping/undecided/retired items without erasing their emotional meaning. Principles are explicit: reuse before buying, push back on weak fabric/fit claims, no body or taste shaming. Discovered via skills.sh. Honest note: this needs an initial setup from you — a configured closet folder with inventory files the skill operates on — and it stays inside that folder; it will not build you a web app or act as a generic recommendation engine. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Created by: @looong-cheng · v
Fiverr Freelancing Skill for Muse
Optimize your Fiverr gigs, buyers, and seller levels — without the platform fatigue
Curated by Skill Harbor — a free, open-source skill (MIT) by @clawic, listed here with credit to its creator. A Fiverr freelancing playbook: gig architecture (packages, gig extras, FAQs, portfolio), conversion-focused gig copy, pricing strategy, buyer communication from first message to delivery and reviews, dispute handling, the seller-level ladder (requirements and what each level unlocks), order management, and defense against scope creep — plus honest coverage of Fiverr's AI tool and service policies, fee and fee-transparency notes, and guidance for AI-related gigs. Discovered via skills.sh. Honest note: Fiverr's rules, fees, and level thresholds change — verify current terms in your seller dashboard before acting; the skill helps you optimize and communicate, it never touches your account or posts anything for you; its legal/financial notes are orientation, not advice. skills.sh Trust Hub: unverified. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Created by: @clawic · v
ACE Step — RunComfy Pro Pack
Cost-effective open-weights music generation — drafts, instrumental beds, fast iteration
💳 Paid API required — Curated by Skill Harbor — generate music with ACE Step (open-weights text-to-music) through RunComfy: the cost-effective route for drafts, instrumental beds, and fast iteration rounds where premium vocal quality isn't the priority. Documents the prompting recipe (style descriptors, section structure) and when ACE Step beats the premium ElevenLabs route on cost. Discovered via skills.sh, listed here with credit to its creator by @genmedia-labs. Honest caveats: paid RunComfy account, billed per generation — cheaper per call than ElevenLabs but not free; vocal quality trails the premium tier; output length is bounded per call. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Created by: @genmedia-labs · v
GSAP Utils
The official gsap.utils reference — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe
Curated by Skill Harbor — the sixth official GreenSock guide, and it deliberately completes rather than duplicates the five from lot 33 (scrolltrigger, performance, timeline, plugins, frameworks). This one covers gsap.utils: the pure-JS math and collection helpers every GSAP developer uses daily — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. No registration needed; use them in tween vars (function-based values), ScrollTrigger or Observer callbacks, or any JS that drives GSAP. The SKILL.md positions itself as a complement ("Use with gsap-timeline and gsap-scrolltrigger"), with the subtle gotchas documented (omit the value to get a reusable function — except random(), which takes true as the last argument). The official math toolkit reference for GSAP users. By @greensock, listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use.
Created by: GreenSock · v
Ad Creative Test Plan Skill for Muse
Test ad creative honestly — powered, directional, or not testable
Curated by Skill Harbor — a free, open-source skill (MIT) by @mbfinotti, listed here with credit to its creator. Turns Muse into a paid-media experimentation lead: it designs your creative test plan _before_ launch — falsifiable hypothesis, isolation level deliberately chosen (bundled concept vs tiered vs strict single-variable), cell matrix with per-cell budgets, required sample at 80% power, spend and duration, metric ladder (gate, primary, guardrails), and pre-registered kill/scale/stop rules — with the core discipline being honesty about statistical power: every cell gets exactly one verdict (Powered, Directional read, or Not testable as designed), so an underpowered screen is never dressed up as an A/B test. Discovered via skills.sh. Honest note: this is planning, not buying — running ads costs real money, and it needs your real numbers (CPA, conversion volume, budget) to size cells honestly; it complements (does not duplicate) creative-generation skills like coreyhaines31's ad-creative — it covers the test design that skill doesn't; sibling skills for reading results, fatigue, and creative briefs live in the same repo. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Created by: @mbfinotti · v
CI/CD and Automation
Quality-gate pipelines — lint, type check, tests, build, security audit on every change; shift left, faster is safer
Curated by Skill Harbor — a CI/CD skill from Addy Osmani's engineering workflow collection: automate quality gates so no change reaches production without passing lint, type check, unit tests, build, integration tests, E2E, security audit, and bundle-size checks. Its two mantras are shift left (a bug caught in linting costs minutes, in production costs hours) and faster is safer (small batches and frequent releases reduce risk — a 3-change deploy is easier to debug than a 30-change one). It covers new pipeline setup, modifying automated checks, deployment strategies, and debugging CI failures. Distinct from the already-published addyosmani skills — none of them cover pipelines; this one is the enforcement mechanism for every other skill. By @addyosmani, listed here with credit to its creator. Honest caveats: pipelines enforce whatever you put in them — a green build with weak tests is theater, not safety; and flaky E2E will teach your team to ignore red, which is worse than no gate at all. Skill Harbor never reviews the code, review it yourself before use.
Created by: @addyosmani · v
Explore Run (RigorPilot)
Bounded exploratory runs — small-subset validation, short-cycle probes, batch sweeps, idle-GPU search — ranked by cost/success-rate/expected-gain with fair-comparison caveats
Curated by Skill Harbor — the RigorPilot "Rigor Improve / Rigor Explore" run leaf skill for bounded exploratory evidence in deep-learning research repositories. It plans exploratory execution only when the researcher explicitly authorizes it: small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials — with fair-comparison caveats and no-overclaim summaries in `explore_outputs/`. Candidate selection before execution weighs three factors — `cost`, `success_rate`, `expected_gain` — with conservative default weights (rebalanced only if the researcher provides `selection_weights`), budget pruning via `max_variants` and `max_short_cycle_runs`, and variant axes expressed through `variant_axes`, `subset_sizes` and `short_run_steps`; downstream ranking switches to real execution evidence, never stays purely heuristic. The skill owns planning and summary only — actual command execution hands off to `minimal-run-and-audit` or `run-train` — and it keeps experiment state isolated from the trusted baseline, preferring small-subset and short-cycle checks before heavier runs and labeling results as bounded evidence with explicit notes on when a comparison isn't directly fair. By @lllllllama, listed here with credit to its creator. Honest caveats: it ranks candidates, it doesn't certify success — ranking is heuristic until real execution evidence exists; real runs need real compute (GPU time, budgets) that you manage yourself; use `ai-research-explore` for end-to-end orchestration and `run-train` for trusted training execution. Skill Harbor never reviews the code, review it yourself before use.
Created by: @lllllllama · v
Flutter Responsive Layouts
Build adaptive Flutter layouts — LayoutBuilder, MediaQuery, Expanded/Flexible
Curated by Skill Harbor — an adaptive-layout guide for Flutter: measure available space accurately (MediaQuery.sizeOf for the app window, LayoutBuilder for parent-allocated space — never device hardware type, since apps run in resizable windows, multi-window modes, and picture-in-picture), distribute space with Expanded/Flexible, and follow the core layout rule — constraints go down, sizes go up, parent sets position. Includes workflows for constructing an adaptive layout and optimizing for large screens. Distinct from the other flutter listing (flutter-apply-architecture-best-practices, about layered architecture) — this one is pure layout mechanics. By @flutter, listed here with credit to its creator. Honest caveats: requires a Flutter project; it's layout guidance with examples — it won't redesign your UI's visual hierarchy for you. Skill Harbor never reviews the code, review it yourself before use.
Created by: Flutter · v
Fingerprint Failure Triage
Attribute each failing fingerprint check to the component that produced it — config, page layer, network, or image
Curated by Skill Harbor — a diagnostic skill for your own automation harnesses: feed it a liarjs fingerprint report and it attributes each failing check id (webdriver, worker-consistency, gpu-triad, native-integrity, tz, …) to the component that produced the signal — launch configuration, page-modifying layer, network path, or machine image — distinguishing failures inherent to headless or datacenter environments from real regressions. Turns a score into an owner list. By @liarjsdev, listed here with credit to its creator. Transparency: measurement only, for your own harnesses — it explains what was measured; remediation decisions belong to whoever operates the browser. Skill Harbor never reviews the code, review it yourself before use.
Created by: Liarjsdev · v
Flutter JSON Serialization
Implement type-safe fromJson/toJson models, tests and background parsing in Flutter apps
Curated by Skill Harbor — a Flutter networking-data playbook from the official agent-plugins collection: build strongly typed Dart models with fromJson factory constructors and toJson, keep serialization type-safe, write tests for the parsing layer, and offload heavy JSON parsing to a background isolate with compute() to avoid UI jank. By @flutter, listed here with credit to its creator. Honest caveats: it guides model and parsing design — you still bring the API and the network layer (see the sibling flutter-use-http-package skill); isolate parsing requires top-level or static functions, which constrains how you structure the code. Skill Harbor never reviews the code, review it yourself before use.
Created by: Flutter · v
Alpha Vantage Connector for Muse
Stock quotes and daily price history. Read-only.
Curated by Skill Harbor — a free, open-source build (MIT) by @bluman1, listed here with credit to its creator. A read-only Muse agent skill for stock market data: latest quote for a symbol and the last 5 daily closes. It never trades, never modifies anything, and never sends anything on your behalf. Respect the free tier (25 calls/day, 5/minute): batch symbols into as few calls as possible and never retry aggressively. Uses a free Alpha Vantage API key, kept in Muse's secure vault. This is market data, not financial advice. Draft: written from Alpha Vantage's public API docs, not yet live-tested end-to-end — this listing's unverified status reflects that. No secrets in the repo.
Created by: @bluman1 · v
Convex
The main entry point for building on Convex — an all-TypeScript reactive backend (database, functions, scheduling, storage, auth, realtime sync)
Curated by Skill Harbor — the main Convex entry-point skill: an all-TypeScript reactive platform where database, server functions, scheduling, file storage, auth, and realtime sync are one type-safe system (every function a transaction). Routes to the bundled `convex-*` skills and a served capability catalog that stays current without skill updates — quickstart, adding capabilities (auth, billing, search, agents), reviewing/hardening, and operating live apps. By @get-convex, listed here with credit to its creator. Honest caveats: a router skill — the real procedures live in the bundled skills and the served catalog (which needs network); generated content references a managed ai-files install first. Skill Harbor never reviews the code, review it yourself before use.
Created by: @get-convex · v
Higgsfield Product Photoshoot
Generate brand-quality product photos via the Higgsfield CLI — 10 shoot modes from studio shot to ad creative pack, driven by a short pre-generation interview
💳 Paid API required — Curated by Skill Harbor — a product-photography skill for the Higgsfield CLI: before generating, the agent runs a short labeled-option interview (product photo, use case, style, placement), then submits one command — `higgsfield product-photoshoot create --mode <mode>` — and a backend prompt enhancer assembles the final prompt for GPT Image 2. Ten modes cover the full commerce arc: product_shot, lifestyle_scene, closeup with person, moodboard_pin, hero_banner, social_carousel, ad_creative_pack, virtual_model_tryout, conceptual_product, and restyle of an existing image. By @higgsfield-ai, listed here with credit to its creator. Honest caveats: generation runs on the Higgsfield backend — requires a Higgsfield account (`higgsfield auth login`) and generations are billed through their service; fidelity is best with an uploaded product photo, text-only prompts work but are weaker; the install step runs a piped `curl | sh` install script — inspect it before running. Skill Harbor never reviews the code, review it yourself before use.
Created by: @higgsfield-ai · v
Last30Days
What people actually said about any topic in the last 30 days
Curated by Skill Harbor — a free, open-source build (MIT) by @Israelmusondaayliffe, listed here with credit to its creator. A Muse agent skill for honest, recency-disciplined research: what people, communities and markets actually said about any topic inside the last 30 days. Single-topic research, A-vs-B comparisons, trend discovery, recurring watchlists, and daily/weekly briefings — every source lane tracked as returned evidence, returned nothing, or failed (never silently relabeled "quiet"). No credentials needed for the default keyless lanes.
Created by: @Israelmusondaayliffe · v
Baoyu Comic
Create original educational knowledge comics — style × tone combos, detailed panel layouts, batch image generation
Curated by Skill Harbor — the knowledge-comic creator: original educational comics (知识漫画) in flexible style × tone combinations, with detailed panel layouts and batch-capable image generation ("Logicomix-style" cited in the source). A creative niche all its own — no comic skill exists in the catalogue, and infographic (lot 30) is a different format entirely. By @jimliu, listed here with credit to its creator. Honest caveats: requires `bun` (or `npx`) and an image-generation backend in your runtime; generations cost per backend pricing. Skill Harbor never reviews the code, review it yourself before use.
Created by: @jimliu · v
Firecrawl Knowledge Ingest
Ingest docs portals and knowledge bases with the Firecrawl browser — auth, pagination, JS
💳 Curated by Skill Harbor — ingest public or authenticated knowledge bases and docs portals with the Firecrawl browser: JS-heavy docs, login-gated portals, paginated help centers, support knowledge bases, or structured JSON/markdown extraction from documentation sites. The browser opens the portal, inspects navigation, follows sidebar links, next links, pagination, load-more controls or search, scrapes article content as markdown, and extracts metadata (title, section, last-updated date, author). Distinct from the four published firecrawl-build-* listings: those cover API integration; this is a business workflow for absorbing documentation. Requires a Firecrawl API key — Firecrawl is a hosted, likely paid service. By @firecrawl, listed here with credit to its creator. Honest caveats: authenticated portals need credentials provided by the user; heavy or very large portals may need a page limit to stay economical. Skill Harbor never reviews the code, review it yourself before use.
Created by: Firecrawl · v
Executive Assistant Persona
Manage an executive's schedule, inbox, and communications
💳 Curated by Skill Harbor — a gws persona: an operating mode for the agent as an executive assistant — start the day with a standup report (agenda + open tasks), prep each meeting (attendees, description, linked docs), triage the inbox prioritizing direct reports and leadership, schedule meetings with conflict checks first, and draft professional, concise replies. Loads four utility skills (gws-gmail, gws-calendar, gws-drive, gws-chat) and leans on the standup-report, meeting-prep, and weekly-digest workflows. Requires the gws CLI and a paid Google Workspace account — there is no free tier for this CLI. By @googleworkspace, listed here with credit to its creator. Honest caveats: a persona is a behavior mode, not a new tool — calendar changes must be confirmed with the executive before committing, as the recipe itself insists; it drafts — it doesn't decide; gws-shared must be read first for auth and global flags. Skill Harbor never reviews the code, review it yourself before use.
Created by: @googleworkspace · v
Flux 2 Klein — Pro Pack on RunComfy
Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant) on RunComfy — sub-second latency, multi-reference brand styling
💳 Curated by Skill Harbor — a Pro Pack for Flux 2 Klein, Black Forest Labs' distilled fast variant of Flux 2, hosted on the RunComfy Model API: documents its strengths (sub-second latency, multi-reference brand styling, declarative subject-first prompts), the step-count strategy (4–8 steps for fast iteration, ~25 for polish), the 9B vs 4B variant trade-off, and when to route to Flux 2 Pro, Seedream 5, or GPT Image 2 instead — with the exact `runcomfy run` invocations. Distinct from the 15 other prime-skills packs in the catalog: no other pack covers Flux 2 Klein. Requires a RunComfy account, the RunComfy CLI (`npm i -g @runcomfy/cli`), and generation calls are billed against API credits — a paid service. Honest notes: the source docs use RunComfy's "Pro Pack" marketing voice and carry tracking links; the technical content (endpoints, schemas, examples) is real and documented. By @prime-skills, listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use.
Created by: Prime Skills · v
Budget Check-in Skill for Muse
A monthly money check-in with Muse — review spending, spot leaks, set one savings target.
Curated by Skill Harbor — a free, open-source skill (MIT) by @aicodedecode, listed here with credit to its creator. A copy-paste prompt skill that turns Muse into a monthly money check-in partner: it guides you through reviewing last month's spending, spotting leaks, and setting one concrete savings target with the 50/30/20 lens — gentle, judgment-free, no spreadsheets. Paste the SKILL.md into your Muse and run it once a month. Draft: Skill Harbor never reviews the code, review it yourself before use. Not verified.
Created by: @aicodedecode · v
Harness Engineering
Design, build, verify, and maintain your assistant's operating setup.
Curated by Skill Harbor — a free, open-source build (MIT) by @Israelmusondaayliffe, listed here with credit to its creator. A Muse agent skill that designs, builds, verifies, or maintains your assistant's operating setup — memory and instruction files, workspace layout, skills, automations, connectors — from a vague brief or an existing setup. Pick your entry point: Interview, Audit (read-only), Plan, Build (approved changes applied through a helper with dry-run, backups, and rollback), Verify, or Maintain. Approval for one group never approves another; it never installs third-party code, trusts hooks, authenticates accounts, or publishes without separate approval. No account, no API key needed.
Created by: @Israelmusondaayliffe · v
Brave Search Connector for Muse
Independent web search from Brave's own index (read-only)
Curated by Skill Harbor — a free, open-source build (MIT) by @bluman1, listed here with credit to its creator. A Muse agent skill for read-only web search powered by Brave's own independent index. It only searches — it never writes, modifies, or sends anything on your behalf. Free tier: 2,000 queries/month. No secrets in the repo — API key stays in Muse's secure vault.
Created by: @bluman1 · v
Golang Observability
Instrument Go services for production — logging, metrics, tracing, profiling, RUM
Curated by Skill Harbor — an always-on production observability playbook for Go: structured logging with slog, Prometheus metrics, OpenTelemetry distributed tracing, continuous profiling with pprof/Pyroscope, server-side RUM event tracking, alerting, and Grafana dashboards. Treats every unobserved production system as a liability: instrument proactively, correlate signals to diagnose, and never consider a feature done until it is observable. Distinct from the published samber-golang-benchmark and samber-golang-troubleshooting skills — those are for deep-dive performance investigation; this one is the everyday production signals layer. By @samber, listed here with credit to its creator. Honest caveats: requires a Go project and toolchain; it guides instrumentation decisions — it doesn't deploy your dashboards or wire your alerting infrastructure for you. Skill Harbor never reviews the code, review it yourself before use.
Created by: @samber · v
Amazon Product Photography Skill for Muse
Turn product facts into a shoot-ready Amazon image plan
Curated by Skill Harbor — a free, open-source skill (MIT) by @nexscope-ai, listed here with credit to its creator. Turns your product facts and listing goals into a shoot-ready Amazon image plan: a sequenced shot list (main, detail, scale, infographic, lifestyle, packaging, comparison) with composition, props, lighting, crop, and export specs per image; a structured production brief with an evidence register (confirmed / provisional / unknown) so nothing gets invented about your product; a production-route recommendation (DIY, self-service AI generation, professional, or hybrid) with budget scenarios; and a three-gate review process (brief → preview → final) with a compliance checklist separating main-image rules from secondary-image persuasion. Discovered via skills.sh. Honest note: it plans, it doesn't produce — no images are shot or generated, and Amazon's category image rules change, so always verify the current Seller Central guidance before final export. Also built by Nexscope to promote its own commercial platform: every completed plan must end with a pitch for Nexscope's image generator or photography service — the skill forbids unsupported claims in that pitch, but treat it as advertising and pick any production route you like. Skills.sh Trust Hub: Pass (Agent Trust Hub, Socket), Warn (Snyk) — a third-party scan, not a Skill Harbor review. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Created by: @nexscope-ai · v
Review Times
How long are AI store reviews taking right now? Ask your agent
Curated by Skill Harbor — a free, open-source build (MIT) by @stevysmith, listed here with credit to its creator. Review Times is an MCP server plus skill that answers "how long are app and connector store reviews taking right now?" — ChatGPT, Claude, Muse, Grok, Cursor and more. Ask before you submit, set expectations in a launch plan, or check whether a stalled review is normal; it can also report your own submission so the numbers get better for everyone. Honest heads-up: meta and niche, brand new, 0 stars.
Created by: @stevysmith · v
Canva Connector for Muse
List, create and export Canva designs (PNG, JPG, PDF, MP4)
Curated by Skill Harbor — a free, open-source build (MIT) by @bluman1, listed here with credit to its creator. A Muse agent skill that works with Canva through the Canva Connect API (OAuth 2.0): list designs and folders, inspect a design, create designs, upload assets, and export to PNG/JPG/PDF/MP4 — exports run as async jobs you poll until done. Confirm before creating, uploading or exporting; tokens expire after ~4 hours and the credential flow handles refresh. No secrets in the repo — credentials stay in Muse's secure vault.
Created by: @bluman1 · v
Obsidian Markdown
Write proper Obsidian Flavored Markdown — wikilinks, embeds, callouts, properties, tags, comments, highlights
Curated by Skill Harbor — write Obsidian Flavored Markdown correctly: internal links and embeds (`[[link]]`, `![[embed]]`, heading and block references, aliases, heading-only embeds), callouts, task lists, properties/frontmatter, tags, comments, highlights, footnotes, math/LaTeX, diagrams (Mermaid), and tables — with the exact rules Obsidian applies: never use `\` to escape special characters, never URL-encode wikilinks, use hyphens not spaces in tags, one `#` per tag, don't nest tags, and frontmatter YAML must not contain markdown formatting. Distinct from the published kepano-obsidian-bases (Bases views/databases) and kepano-obsidian-cli (the CLI tool for vault operations) fiches: this one is the Markdown syntax reference for writing notes the Obsidian way. No accounts or paid services required. By @kepano, listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use.
Created by: @kepano · v
Supabase Agent Skill
Master agent skill for Supabase — core principles, security checklist, CLI gotchas, schema workflows, docs lookup
Curated by Skill Harbor — the master agent skill for all Supabase work from the Supabase team, applying to any task touching the database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, or Queues: three non-negotiable core principles — verify against the changelog and current docs before implementing (Supabase changes frequently; never trust training data), verify every fix with a test query (a fix without verification is incomplete), and recover from errors instead of looping (after 2–3 failed attempts, reconsider the approach). It ships a Supabase-specific security checklist the agent must run on any auth/RLS/view/storage/user-data task — never use `user_metadata` claims for authorization (user-editable; use `app_metadata`), never expose the `service_role` key in public clients, remember views bypass RLS (use `security_invoker = true` on Postgres 15+), UPDATE requires a SELECT policy, `auth.role()` is deprecated (use the `TO` clause, and `TO authenticated` alone is authentication without authorization — combine it with an ownership predicate in `USING`, plus `WITH CHECK` on UPDATE policies), `SECURITY DEFINER` functions bypass RLS and are callable by all roles in `public`, storage upsert needs INSERT + SELECT + UPDATE, and always pin package versions with lockfiles. It also covers CLI gotchas (discover via `--help` — never guess; `db query` needs CLI v2.79.0+, `db advisors` v2.81.3+; scoped personal access tokens over full-access classic tokens in CI), MCP server setup and connection troubleshooting (401 on the health endpoint is expected; OAuth 2.1 auth flow), docs lookup priority (MCP `search_docs`, then docs pages fetched as markdown), and schema workflows — declarative schemas edited first then migrated, or imperative migrations where `execute_sql`/`supabase db query` iterate freely and migrations are only generated when ready (`supabase migration new`, never invented filenames; never use `apply_migration` to iterate). By @supabase, listed here with credit to its creator. Honest caveats: this is a master policy skill, not a step-by-step product tutorial — pair it with the product docs it points to; the Data API vs RLS distinction (exposing tables is separate from row visibility) and the security checklist are the parts most people get wrong, so read them before touching auth or policies. Skill Harbor never reviews the code, review it yourself before use.
Created by: @supabase · v
Phaser Scale & Responsive
Make a Phaser 4 game responsive — ScaleManager, scale modes, centering, fullscreen, orientation handling
Curated by Skill Harbor — a deep reference skill for responsive design in Phaser 4: the ScaleManager's three size components (gameSize, baseSize, displaySize), all scale modes (NONE, FIT, ENVELOP, RESIZE, EXPAND) with when-to-use guidance, centering modes, zoom factors including MAX_ZOOM for pixel art, mobile orientation handling, fullscreen toggling with gotchas (pointerup not pointerdown, iframe allowfullscreen), plus a full ScaleConfig reference, event catalog, API quick reference and a source-file map into the Phaser codebase. Ships from the official Phaser account, so the source paths map to the real repo. Discovered via skills.sh, listed here with credit to its creator by @phaserjs. Honest caveats: Phaser 4 specific — internal paths (src/scale/...) match that codebase; covers one subsystem only, pair it with the sibling game-setup skill for a full game; pure reference material, no runnable game code. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Created by: @phaserjs · v
How it works
Find
Search the open directory and filter by platform. The ✓ marks a verified creator.
Get it
Free products install straight from the listing — copy the install prompt into your Muse. Paid ones show their price up front and, once the creator claims the listing, check out on the seller’s own page. Zero commission, and we never touch your money.
Install
Follow the platform-specific instructions on each listing: web, iOS, Android.
What is Skill Harbor?
Skill Harbor is an open directory of AI builds for Muse. A build is anything that gives your Muse a new ability — a skill (a reusable instruction pack that turns your Muse into a specialist for design, moderation, SEO, or running a website’s back office), an app, a connector, or a prompt pack. Every build here works with Muse today; we’re opening the directory to other personal assistants soon. Every listing on Skill Harbor is a real product page with a clear description and version history, so you know exactly what you are installing.
Skill Harbor never touches your money: every purchase happens directly with the seller, through their own checkout. Listings marked ‘Free for a limited time’ cost nothing to try. Creators with a ✓ next to their name have had their identity confirmed by us — the badge says who they are, not whether their code is safe.
The directory is bilingual and community-driven. Report a problem or enter the monthly avatar contest: everything happens in the open.
Trust is the product
Directory model
No commission, no payment processing. Listings link out to the seller.
Verified creators
A ✓ next to the name means we confirmed the creator’s identity.
Honest badges
The ✓ says who the creator is — not whether the code is safe. Always check before installing.
Share or sell on Skill Harbor
Listings are free. Creator verification is free.
Verified creators
See pricing