All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 279,374
- 11,641
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse ai & agents skills
Showing 1–24 of 279,374 skills
- Verify GateRun Fishhawk's `scripts/test verify` gate (lint, schema-sync, gate harnesses, tests, patch coverage) safely and read its result. Use before pushing or opening a PR, when asked to "run verify", "run the gate", "run the tests", or to check a change passes CI locally. Covers the per-repo verify lock, host-load and toolchain preflights, scoped runs, and what each failure means.Votes: 0GitHub stars: 9
- Spec ChangeChange a Fishhawk canonical schema or API contract end to end — `docs/spec/*.schema.json` (workflow, plan, operator overlay), the embedded mirrors, the generated site reference, version advertising, and `docs/api/v0.openapi.yaml`. Use when adding/changing a field in the workflow spec or plan schema, standing up a new workflow major, or changing the REST API surface.Votes: 0GitHub stars: 9
- Explain DiffExplain a code change, diff, branch, commit, or PR as a rich, self-contained page: background, intuition with concrete examples, a walkthrough in execution order, what could break, and a quiz that cannot be gamed by picking the longest answer. Use when the user asks to explain, walk through, teach, or help them understand a change, diff, branch, or PR. Output is HTML by default, Markdown with --md (cheapest), and --chat moves the quiz into conversation as free-response questions.Votes: 0GitHub stars: 6
- R LifecycleGuidance for managing R package lifecycle according to tidyverse principles using the lifecycle package. Use when: (1) Setting up lifecycle infrastructure in a package, (2) Deprecating functions or arguments, (3) Renaming functions or arguments, (4) Superseding functions, (5) Marking functions as experimental, (6) Understanding lifecycle stages (stable, experimental, deprecated, superseded), or (7) Writing deprecation helpers for complex scenarios.Votes: 0GitHub stars: 529
- Patronus Api SetupConnect the hosted Patronus API, explain account sign-in and open the account dashboard. Use for initial setup, authentication problems or usage questions.Votes: 0GitHub stars: 2
- Review CodeReview a diff, branch or pull request for correctness, security, data compatibility, tests and maintainability, with a verdict and concrete findings. Use when the user asks for a code review or a review of a pull request.Votes: 0GitHub stars: 2
- Production Readiness ReviewReview a whole project for production readiness across functionality, security, configuration, tests, operations and documentation, apply safe fixes, and give a Ready, Almost ready, Not ready or Insufficient evidence verdict. Use when the user asks whether a project is ready to ship or wants a pre-launch review.Votes: 0GitHub stars: 2
- Prepare ReleasePrepare a release: decide the version, check readiness, update the version and changelog, write release notes, verify artifacts and list the commands to tag and publish. Use when the user asks to release, cut a version or write release notes.Votes: 0GitHub stars: 2
- Improve PromptRewrite a prompt so it works reliably across AI models, with clear structure, scope, output format and handling of missing information. Use when the user asks to improve, fix or rewrite a prompt.Votes: 0GitHub stars: 2
- Implement FeatureImplement a feature with a plan, small verified changes that follow the project's conventions, tests and documentation. Use when the user asks to build, add or implement functionality.Votes: 0GitHub stars: 2
- Describe ChangesWrite commit messages and pull request descriptions that explain what changed and why, matching the repository's conventions. Use when the user asks for a commit message or a pull request description.Votes: 0GitHub stars: 2
- Cli And Scripts AuditAudit command-line tools, shell and PowerShell scripts, installers, setup scripts and dotfiles for safety, robustness, portability, testing and distribution, and fix the safe parts. Use when the user asks to review a CLI, a shell or PowerShell script, an installer or a setup tool.Votes: 0GitHub stars: 2
- Architecture ReviewAssess architecture and codebase health: boundaries, consistency, runtime qualities, evolvability, hotspots and technical debt, with ranked risks and a prioritized plan. Use when the user asks whether the architecture fits, how healthy the codebase is, or which technical debt to pay first.Votes: 0GitHub stars: 2
- Accessibility AuditAudit a user interface against every WCAG 2.2 A and AA criterion with evidence, fix safe barriers, and produce a manual test plan. Use when the user asks about accessibility, WCAG, screen readers, keyboard use or contrast.Votes: 0GitHub stars: 2
- Thermo Nuclear Code Quality ReviewRun an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.Votes: 0GitHub stars: 13
- TodoThe user often stops mid-session to ask where things stand. A review of about 150 such prompts in the Claude Code and Codex histories (2026-02 to 2026-10) found these patterns:Votes: 0GitHub stars: 2
- Loom CC language expertise (C11/C17/C23) for memory-safe, portable, production-quality systems code.Votes: 0GitHub stars: 61
- Alera AutomationsCreate, edit, inspect, pause, and run scheduled Alera agent automations through the CLI, and report the lifecycle of an automation run. Use for recurring or one-time agent work in an Alera runtime.Votes: 0GitHub stars: 37
- RemindersUse when the user wants to be reminded of something at a time, or wants something offered to them on a recurring basis -- "recuérdame mañana a las 4", "avísame el viernes", "cada viernes a las 5 cargar el timesheet", "rutinariamente", "remind me to", "every morning". Also when a due reminder or routine shows at session start or in the prompt counter and has to be acted on. NOT for work to do once now in this session.Votes: 0GitHub stars: 4
- DispatchUse when the orchestrator is about to dispatch a specialist turn that writes to a repository, runs alongside other turns, or carries acceptance the specialist must meetVotes: 0GitHub stars: 4
- RetroReview a coding session and propose environment changes that prevent repeated agent mistakes.Votes: 0GitHub stars: 123
- Implement SpecImplement a complete spec from its ticket graph, using isolated workers and one integration branch.Votes: 0GitHub stars: 123
- Diagnosing BugsBuild a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock the fix with a regression test.Votes: 0GitHub stars: 123
- Graftty ImageUse when the user asks to see, show, display, preview, or render an image, screenshot, diagram, chart, or photo inline in the terminal pane, or when a finished image should be shown in place on the Mac. Also use before reaching for imgcat, kitten icat, chafa, or hand-written Kitty graphics escapes.Votes: 0GitHub stars: 5