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.
12,636 skills from 362 repositories · updated 24 minutes ago
1,023 skills
- shopify-email-flowsnexscope-ai/eCommerce-SkillsEmail automation flows — welcome series, abandoned cart, post-purchase, win-back, browse abandonmentProductivityNo warnings★ 1.2K↓ —
- shopify-cart-abandonmentnexscope-ai/eCommerce-SkillsCart abandonment recovery — email sequences, SMS, retargeting, exit intent, checkout friction auditProductivityNo warnings★ 1.2K↓ —
- mem-automationComposioHQ/awesome-claude-skillsAutomate Mem tasks via Rube MCP (Composio). Always search tools first for current schemas.ProductivityNo warnings★ 77.6K↓ —Also in 1 other repo
- ably-automationComposioHQ/awesome-claude-skillsAutomate Ably tasks via Rube MCP (Composio). Always search tools first for current schemas.ProductivityNo warnings★ 77.6K↓ —Also in 1 other repo
- npm-automationComposioHQ/awesome-claude-skillsAutomate NPM tasks via Rube MCP (Composio). Always search tools first for current schemas.ProductivityNo warnings★ 77.6K↓ —Also in 1 other repo
- babysita5c-ai/babysitterOrchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)ProductivityNo warnings★ 1.9K↓ —
- ask-experta5c-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↓ —
- babysita5c-ai/babysitterExecute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called explicitly. (babysit, babysitter, with a process, orchestrate, orchestrate a run, workflow, loop until, etc.)ProductivityNo warnings★ 1.9K↓ —
- audit-traila5c-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↓ —
- github-synca5c-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↓ —
- atlas-graph-querya5c-ai/babysitterReference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)ProductivityNo warnings★ 1.9K↓ —
- smart-routinga5c-ai/babysitterComplexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.ProductivityNo warnings★ 1.9K↓ —
- vector-memorya5c-ai/babysitterHNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.ProductivityNo warnings★ 1.9K↓ —
- pending-questionsa5c-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↓ —
- session-memorya5c-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↓ —
- epic-generationa5c-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↓ —
- state-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↓ —
- quick-flowa5c-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↓ —
- progress-trackinga5c-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↓ —
- context-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↓ —
- task-decompositiona5c-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↓ —
- context-engineeringa5c-ai/babysitterContext window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.ProductivityNo warnings★ 1.9K↓ —
- agent-dispatcha5c-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↓ —
- feature-intakea5c-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↓ —
atlas-graph-query
a5c-ai/babysitter
ProductivityUpdated Sep 16, 2026
From the author
Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)
Install
npx skills add a5c-ai/babysitter --skill atlas-graph-query -a claude-code
Installs to .claude/skills/atlas-graph-query/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 86
Security100
Provenance79
Maintenance85
Licence100
Adoption52
Files (1)
- SKILL.md