全部 Agent Skills
41,263 个结果
- Plan ReviewcountzeroSecond-pass review of a plan before presenting it to the user. Use when about to present a non-trivial plan in plan mode, or a multi-step implementation outline in normal/build mode (TodoWrite with 3+ non-trivial items, or a response describing edits to 2+ files). Skip for trivial / one-line changes or when the user asked for "minimal" / "quick" / "just do X" / "smallest fix".
- Plan Rls AuditkenjiPlan-only Supabase/Postgres RLS and access-control audit. Use when "is my Supabase secure", "anyone can read my data", "lock down my tables", "service_role key", or "security advisor". Route gates → audit-auth-flows.
- Playwright Browser DragX-School-AcademyTo drag and drop between elements on a web page, perform a drag interaction from a source to a target.
- Playwright Browser Fill FormX-School-AcademyTo fill multiple form fields at once, set values for inputs, checkboxes, and selects in a single call.
- Pr Code ReviewcountzeroMulti-pass PR code review. Use when reviewing pull request code changes for defects and design issues. Performs 3 review passes with escalating focus, deduplicates findings, and produces a severity-filtered summary with deep links to the relevant code on GitHub. This skill is read-only and advisory; it never writes comments, reviews, or any data to GitHub.
- Preview JsonveelengaRender and preview JSON files in browser with syntax highlighting, collapsible tree view, and search
- Project Field ManagementyebotComprehensive guide to GitHub Projects field types, configuration, and management strategies. Use when setting up fields, troubleshooting field issues, or optimizing field structures.
- Protocol Browser Anti Stallkenjiplaywright-cli guardrail: headed, named -s= sessions, one real action at a time, max 4 attempts, then a BLOCKER. Read before browser work, or when "the browser is stuck", "playwright hangs", or agents share a browser.
- Publish Github Skills ExerciseAri LiVigni ContinuousG33kPrepare a GitHub Skills exercise for publication, contribution, or rollout. Use this when the user asks for release readiness, final checklist, README/marketplace copy, PR description, validation evidence, launch notes, or publishing guidance for a GitHub Skills-style exercise.
- Qbr PrepZoomInfoAssemble a QBR prep pack for a business review — value moments, usage and adoption themes, risks, and open items, with a deal and relationship snapshot. Combines account_research for the account picture with conversation_intelligence over recent calls (scoped to individual engagements) for what the customer actually said.
- QuickIfeOlulesiSmall, clear changes done fast but still proven — a copy or styling fix, a contained bug, a config value; three files or fewer. Use when the user asks for a quick fix or the change is obviously small. If it grows past that, the gate switches back to the full build process.
- Recommend ContactsZoomInfoGet AI-powered contact recommendations at a target company based on your ZoomInfo interaction history. Provide a company name or domain and optionally a use case.
- Renewal PrepZoomInfoPrepare for a renewal by assembling pre-renewal context — value delivered and value moments, risk handles, and stakeholder state — from recent conversations and account_research. Identify the account by ZoomInfo company ID (preferred) or name/domain (triggers a lookup).
- Repo Scoutnaman10parikhScout popular GitHub repos for patterns, frameworks, and harnesses relevant to Energy. Ingest learnings automatically.
- RepomagpieVarshaviaReads and records the user's own notes on dependencies and tools with RepoMagpie's MCP tools or its repomagpie CLI. Use before adding or installing any package (npm, pnpm, yarn, bun, pip, uv, cargo), when the user asks what they have or know for a task ("what do I have for browser testing?"), when choosing libraries or tools for a project, and when the user gives an opinion on a tool worth…
- ResearchkenjiResearch current practice with Context7, Firecrawl, and official docs before a non-trivial change: gap analysis and a file-mapped plan, no implementation. Use when "look up current docs" or before anything unfamiliar.
- Review Github Skills ExerciseAri LiVigni ContinuousG33kReview GitHub Skills exercises for learner experience, validation correctness, workflow safety, accessibility, and publish readiness. Use this whenever the user asks to audit, review, improve, QA, or validate a GitHub Skills-style exercise repository or draft.
- Risk Management0xhubedRisk management rules learned from competition outcomes. Use when sizing positions or setting stop-losses.
- Sales Page Copywritingyashaiguy-devGenerate battle-tested sales page copy through hostile validation, output only polished final copy
- Score AccountsZoomInfoScore and rank a list of accounts (mixed ZoomInfo company IDs, names, or domains) by ICP fit + buying intent + recent triggers. Returns per-account composite score (0–100), tier (A/B/C), explainable component breakdown (fit / intent / trigger / engagement), a specific "why now" sentence per account, and the working weight set as a saveable search filter set.
- Score LeadsZoomInfoScore and prioritize leads or cold contacts (mixed ZoomInfo person IDs, emails, or name+company rows). Returns Hot / Warm / Cold tier per lead with a response-time SLA tuned to the use case (live inbound routing, MQL triage, event follow-up, PQL triage, content follow-up, SDR queue ordering), per-axis breakdown (person fit · account fit · source signal · trigger), a "why now" reasoning snippet…
- Self Improvenaman10parikhAnalyze past session logs to find repeated patterns, forgotten rules, and backtracking moments. Auto-update CLAUDE.md, skills, and rules to address gaps. "Correct once, never again."
- Send EmailwangyendtSend emails via SMTP with support for HTML formatting, file attachments, and email templates. Use when users ask to: (1) Send an email, (2) Email someone, (3) Send a notification, (4) Use email templates, or (5) Send files via email.
- Sequential ThinkingduongdevStructured problem-solving through iterative reasoning with revision and branching capabilities for complex problems. Use when tackling multi-step problems with uncertain scope, design planning, architecture decisions, or systematic decomposition. Auto-activates when user asks about breaking down epics, designing systems, assessing complexity, or performing root-cause analysis.