All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 305,611
- 12,734
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 2,377–2,400 of 305,611 skills
- Cross ReviewGive an existing proposal an independent second opinion when requested; return one judged recommendation.Votes: 0GitHub stars: 48
- Agent Planning LoopReview unsettled plans with independent scouts when the user requests multi-agent planning or alignment.Votes: 0GitHub stars: 48
- Plans- Plan status: DONE - Session scope: cross-review-skill - Parent plan: none - Child plans: none - Last updated: 2026-08-17 - Current slice: Shipped and verified. - Next action: none - Blocked on: none - Do not touch from this session: unrelated skills, vendor sources, and global installsVotes: 0GitHub stars: 48
- .PlanningCreate a `plan-bakeoff` skill that takes one approved implementation plan and runs multiple independent coding-agent attempts against it in separate git worktrees. Each attempt may use a different harness, provider profile, model, reasoning setting, or runtime wrapper. The main session then compares the attempts, selects a winner, and optionally ports the winning change back through the normal worktree-port flow.Votes: 0GitHub stars: 48
- Zoom OutExplain code with visual diagrams and analogies. Use when explaining how code works, walking through a codebase area, or the user asks "how does this work?" Don't use for modifying code, fixing bugs, or multi-session learning (/teach).Votes: 0GitHub stars: 16
- Wait WhatStop — that last message didn't land. Re-pitch it plainly.Votes: 0GitHub stars: 16
- Visual ReviewTwo visual modes — render a PR diff as an HTML page with each hunk annotated by principle, or check a UI change in a real browser (screenshots, console, network). Use for a visual/HTML diff report, "check the UI", or "screenshot before/after". Don't use for text-only feedback (/code-review), unit tests (/tdd), or full reviews (/review).Votes: 0GitHub stars: 16
- TriageClassify any input — idea, bug, ticket key, `#42`, PR URL, stack trace — size it, and name the command to type; with no args, report where you are.Votes: 0GitHub stars: 16
- To TicketsSlice a spec or a ticket into tracer-bullet tickets with blocking edges, saved to `.specs/tickets/<slug>.md`.Votes: 0GitHub stars: 16
- To SpecTurn the settled conversation into a spec (PRD) at `.specs/specs/<slug>.md`.Votes: 0GitHub stars: 16
- To PrGate, push, and open a GitHub pull request on the repo's PR template, then watch CI.Votes: 0GitHub stars: 16
- To AdrRecord an Architecture Decision Record (ADR) — 1–3 sentences on what was decided and why. Use when user says "create an ADR", "record this decision", or just made an architecturally significant choice. Don't use for forward-looking specs (/to-spec) or repo conventions (CLAUDE.md).Votes: 0GitHub stars: 16
- TeachTeach the user a new skill or concept, within this workspace.Votes: 0GitHub stars: 16
- TddTest-driven development, from unit to end-to-end tests. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration or end-to-end tests (Playwright, Cypress). Don't use to backfill tests on existing code (/refactor) or diagnose an unknown bug (/debug).Votes: 0GitHub stars: 16
- Source DrivenImplement features from official docs for the exact installed dependency versions, not training data. Use when asked to "check the docs", "use official docs", "source-driven", or with unfamiliar APIs/libraries. Don't use for well-known stdlib APIs or project-internal code.Votes: 0GitHub stars: 16
- Safe RepoCheck the repository for sensitive data. Use when asked to "check for sensitive data" or verify no credentials or company data are committed; `--diff [<base>]` scopes to a branch's changes. Don't use for general code review or non-git directories.Votes: 0GitHub stars: 16
- ReviseEdit prose in place — restructure article drafts (reorder sections, tighten arguments) or polish any markdown/text (typos, dashes, filler). Use when asked to "revise", "edit my draft", "improve my article", "fix typos", "fix dashes", "clean up text", or "improve sentences". Don't use for code style or linting (/check).Votes: 0GitHub stars: 16
- ReviewFan out parallel read-only reviewers over a diff and consolidate one severity-ranked verdict.Votes: 0GitHub stars: 16
- RetroRun a retrospective on a coding session and suggest changes to the agent's environment, not the code.Votes: 0GitHub stars: 16
- ResearchInvestigate a question against primary sources and capture cited findings as Markdown. Use when the user wants a topic researched, docs or API facts gathered, or reading delegated to a background agent. Pass the question as the argument. Don't use for implementing against pinned dependency versions (/source-driven) or codebase search.Votes: 0GitHub stars: 16
- RefactorImprove existing code without changing behavior — split large functions, backfill tests, simplify. Use when asked to "refactor", "make robust", "bulletproof", "strengthen", "add missing tests", "split functions", "simplify", "clean up", or "reduce complexity". Don't use for new features (/tdd), security (/harden), or PR review.Votes: 0GitHub stars: 16
- PrototypeBuild a throwaway prototype — a shareable HTML demo for state/logic questions, or several UI variations toggleable from one route. Use when comparing design directions before committing, or the user says "prototype", "mock up", "try a few approaches". Don't use for production code (/build, /tdd).Votes: 0GitHub stars: 16
- Perf AuditAudit frontend bundle size and performance. Use when asked to "audit performance", "analyze bundle", "check bundle size", or find frontend bottlenecks. Don't use for backend performance, database queries, or projects without a frontend build step.Votes: 0GitHub stars: 16
- I18nAudit internationalization coverage and find hardcoded strings. Use when asked to "check i18n", "find hardcoded strings", or verify translation coverage. Don't use for backend code, projects without an i18n library, accessibility (/a11y-audit), or bundle size (/perf-audit).Votes: 0GitHub stars: 16