Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
14,555 skills from 421 repositories · updated 5 hours ago
1,085 skills
- search-knowledgeindranilbanerjee/digital-marketing-proSearch the brand's stored knowledge and memory, ranked with provenance. "what are our brand voice guidelines"ProductivityNo warnings★ 906↓ —
- amplify-workflowawslabs/agent-pluginsBuild and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). Covers auth (Cognito), data (AppSync/DynamoDB including schema modeling, enum types, relationships, authorization rules), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock). Supports React, Next.js, Vue, Angular, React Native, Flutter, Swift, and Android. Always use this skill for Amplify Gen2 topics — even for questions you think you know — it contains validated, version-specific patterns that prevent common mistakes. TRIGGER when: user mentions Amplify Gen2; project has amplify/ directory or amplify_outputs; code imports @aws-amplify packages; user asks about defineBackend, defineAuth, defineData, defineStorage, or npx ampx. SKIP: Amplify Gen1 (amplify CLI v6), standalone SAM/CDK without Amplify (use aws-serverless), direct Bedrock without Amplify AI Kit (use bedrock).ProductivityNo warnings★ 927↓ —
- superselfwshobson/agentsUse when a project keeps its state in Superself (a `<!-- superself:begin` block in AGENTS.md or CLAUDE.md, or `self setup` resolves the directory to a registered project): read `self context` at session start, attach work to a work unit, report with evidence, and record confirmed decisions so the next session picks up where this one left off.ProductivityReview first★ 41.6K↓ —
- engagement-workflowindranilbanerjee/digital-marketing-proRun the 12-Part engagement workflow from intake to growth plan, checkpointed. "start a new engagement"ProductivityNo warnings★ 906↓ —
- content-calendarindranilbanerjee/digital-marketing-proBuild a content calendar: topics by platform and date, pillar and funnel tags. "plan next month's content"ProductivityNo warnings★ 906↓ —
- signal-mineindranilbanerjee/digital-marketing-proMine raw signals (news, threads, sales notes) into content angles. "turn this industry news into ideas"ProductivityNo warnings★ 906↓ —
- sync-memoryindranilbanerjee/digital-marketing-proSync session learnings to persistent memory incrementally, with a report. "save what we learned this session"ProductivityNo warnings★ 906↓ —
- email-sequenceindranilbanerjee/digital-marketing-proDesign an ESP-ready email sequence: subjects, copy, timing, branching, deliverability. "build a welcome sequence"ProductivityNo warnings★ 906↓ —
- save-knowledgeindranilbanerjee/digital-marketing-proSave one piece of brand knowledge to persistent memory with dedup and tags. "store this competitor intel"ProductivityNo warnings★ 906↓ —
- exec-summaryindranilbanerjee/digital-marketing-proWrite an executive summary from tracked marketing results for CEO, CFO or board. "summarize this quarter for the CEO"ProductivityNo warnings★ 906↓ —
- context-engineindranilbanerjee/digital-marketing-proLoad shared marketing context: brand profile, benchmarks, compliance rules, specs. "load my brand context"ProductivityNo warnings★ 906↓ —
- switch-brandindranilbanerjee/digital-marketing-proSwitch the active brand profile for agency work and confirm the new context. "change brand to Acme"ProductivityNo warnings★ 906↓ —
- dispatching-parallel-agentscoco-research/cocoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesProductivityNo warnings★ 961↓ —
- relay-80-100-workflowAgentWorkforce/relayUse when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.ProductivityNo warnings★ 893↓ —
- relay-80-100-workflowAgentWorkforce/relayUse when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.ProductivityNo warnings★ 893↓ —
- process-generatora5c-ai/babysitterGenerate process JS files following Babysitter SDK patterns including task definitions, quality gates, breakpoints, and proper io configuration.ProductivityNo warnings★ 1.9K↓ —
- process-validatora5c-ai/babysitterValidate process JS files for correct SDK patterns, task definitions, syntax, and quality gate implementation.ProductivityNo warnings★ 1.9K↓ —
- formula-authoringa5c-ai/babysitterAuthor TOML-based Formula workflow templates that become Protomolecules and active Molecules in Gas Town's durable workflow system.ProductivityNo warnings★ 1.9K↓ —
- quality-hooksa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationProductivityNo warnings★ 1.9K↓ —
- process-integratora5c-ai/babysitterIntegrate skills and agents into process files by updating task definitions with appropriate skill.name and agent.name references.ProductivityNo warnings★ 1.9K↓ —
- kanban-managementa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationProductivityNo warnings★ 1.9K↓ —
- parallel-orchestrationa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationProductivityNo warnings★ 1.9K↓ —
- cog-onboardinga5c-ai/babysitterPersonalize COG Second Brain workflow through role pack selection and vault initializationProductivityNo warnings★ 1.9K↓ —
- task-decompositiona5c-ai/babysitterConvert technical plans into actionable development tasks with dependency graphs, effort estimates, and parallelization opportunities.ProductivityNo warnings★ 1.9K↓ —