AGENT SKILLS · MISSION KIT
Useful agent skills ranked by real adoption
Browse verified skills from public repositories. Compare what each skill does, package contents, install activity, and source evidence before adding it to your agent.
- CATALOG SCOPE
- VERIFIED
- skills
- 20,759
- repositories
- 3195
- last synced
- Oct 21, 2026
fellowship-devspeckit-runner
Use when implementing a GitHub issue end-to-end — runs speckit with an independent advisory review before creating one PR.
- installs
- 2
- GitHub stars
- 3
- Updated
- Oct 7
fellowship-devtrash-truck
Investigate and retire unused product, code, operational, or infrastructure surfaces using real usage evidence. Use when a repository needs active pruning, when a specific capability may no longer be necessary, or when a scheduled review should preserve retirement candidates without executing them. Do not use for routine lint cleanup, broad refactoring, or dependency updates.
- installs
- 2
- GitHub stars
- 3
- Updated
- Oct 7
fellowship-devvercel-deploy
Use when deploying an existing Vercel project to production non-interactively.
- installs
- 2
- GitHub stars
- 3
- Updated
- Oct 7
fellowship-devvisual-evidence
Use when capturing Playwright screenshots or GIF recordings for PR evidence — before/after comparisons and feature demos.
- installs
- 2
- GitHub stars
- 3
- Updated
- Oct 7
fellowship-devwrite-report
Use when writing a mission report to the gateway DB from any operator mission.
- installs
- 2
- GitHub stars
- 3
- Updated
- Oct 7
xtonecode-review
PRやコード変更の汎用コードレビューを実施します。コードの品質、セキュリティ、設計を共通基準で評価し、approve/rejectを判断します。「このPRをレビュー」「コードレビューして」「マージ前チェック」などの依頼や、gh pr viewコマンドの実行時に使用してください。
- installs
- 2
- GitHub stars
- 3
- Updated
- Oct 7
customware-aidomain-context
Progressive Domain Crystallization (PDC) — a skill for building and maintaining a living domain knowledge base for any custom business application. Use this skill whenever the user is developing a business application and wants the AI to accumulate understanding of internal terminology, entities, relationships, and business rules over time — especially when that knowledge is not fully defined upfront and grows across sessions. Trigger on any of: "remember how our system works", "learn our domain
- installs
- 2
- GitHub stars
- 2
- Updated
- Sep 30
apidojo-iofinding-podcast-hosts-for-outreach
Finds podcast hosts for PR and guest outreach using apidojo's Twitter scrapers on Apify. Triggers when the user asks to: find podcast hosts to pitch for a guest spot, discover podcasters in a niche for PR outreach, build a podcast outreach list from Twitter, find podcast hosts who cover a specific topic or industry, identify podcasters who interview guests in a business niche, find B2B podcast hosts for thought leadership placement, or compile a list of podcast hosts for a media relations campai
- installs
- 2
- GitHub stars
- 1
- Updated
- May 13
spenserhalegithub-ref
Inspect external GitHub source, documentation, and examples as reference material. Use whenever an agent needs GitHub repository content for research, implementation guidance, debugging, or comparison, even as an intermediate step and without a user asking to clone. Not for issue or PR API operations alone, or editing the active project; use the relevant GitHub or development workflow instead.
- installs
- 2
- GitHub stars
- 1
- Updated
- Oct 7
harryitcgithub-pull-request
Create or update a GitHub pull request the careful way — read-only pre-push checks (clean tree, sync with the base via a dry-run merge, real test evidence for the areas the diff touches, new migrations), a PR description that contains only the sections the diff actually triggers, and a draft shown to the user for approval before any push or gh pr create. Per-repo settings (base branch, test commands, extra checklist lines) come from .agents/pr-config.md when present. PR text defaults to English;
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 7
wkentaroask-exemplar
Consult the accepted standard and strongest supported exemplars for a decision, plan, design, completed artifact, or diff, then return a source-grounded recommendation or evaluation.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentarodaily-recap
Reconstruct today's work sessions as a reviewable summary of completed, ongoing, and blocked work.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentarodispatch-new-session
Launch a task in a new Herdr tab after choosing the agent harness and model.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentarohear-me
Checks voice-dictated requests with a readback and stays active in the current conversation until disabled.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentaropark
Print and copy a one-line reminder and the command for resuming the current coding-agent session.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentaropr-review
Gut-check a pull request — is it meaningful, worth adding, correct, and minimal — and give one recommend- verdict.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentarorecommit
Reshape the commits a branch carries on top of its target branch into a clean, logical sequence without changing the final committed tree. Use when a branch needs presentable history before review or merge, when iterative work left fixups, WIP commits, or interleaved refactors, when another skill needs clean commits, or when the user says "recommit" or asks to tidy the git history.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentarosending-pull-request
Prepare a conventional branch, write or review a pull/merge request title and body, then push and create or update the GitHub PR. Use when work is ready for review or PR/MR copy needs drafting or review.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentarosetup-github-labels
Apply and document the canonical GitHub issue and pull-request label set in a repository.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentarosimplify
- Simplify changed code without changing intended behavior. Use for /simplify, cleanup focused on reuse, unnecessary complexity, efficiency, or abstraction altitude, and report-only simplify reviews inside review-fix.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
wkentaroworkmap
Map the session's work as an idea, its projects, and their tasks, each with a status and a stable ID. Use when the user asks to divide work into projects or tasks, asks where the session stands, or a reply has to show how pieces of work relate.
- installs
- 2
- GitHub stars
- 0
- Updated
- Oct 5
huangchihhungleoclaude-real-video
Watch a video for the user. Use when the user shares a video URL (YouTube etc.) or local video file and wants it summarized, analyzed, or discussed — Claude can't ingest video directly, so this skill extracts scene-aware keyframes + transcript first, then reads those.
- installs
- 2
- GitHub stars
- 2.2K
- Updated
- Oct 1
huangchihhungleoclaude-real-video-for-agents
Install and use crv (claude-real-video) — a tool that lets any AI agent watch videos by extracting scene-aware keyframes, deduplicating them, and transcribing audio. Use when the user shares a video URL or file and wants it analyzed, summarized, or discussed.
- installs
- 2
- GitHub stars
- 2.2K
- Updated
- Oct 1
tinyfish-iouse-tinyfish
Use TinyFish for web search, fetching URLs, reading pages, current information, source-backed answers, research, docs, pricing/product pages, extraction, scraping, and browser automation. Use whenever the user asks to search, find, look up, research, compare, get information from the web, summarize a URL, fetch page content, or automate a website.
- installs
- 2
- GitHub stars
- 2.2K
- Updated
- Oct 1