Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
perf-theory-tester
Use when running controlled perf experiments to validate hypotheses.
agent-sh/agentsys 720
-
enhance-plugins
Use when analyzing plugin structures, MCP tools, and plugin security patterns.
agent-sh/agentsys 720
-
enhance-orchestrator
Use when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces unified report.
agent-sh/agentsys 720
-
debate
Structured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 'stress test idea', 'devil advocate'.
agent-sh/agentsys 720
-
web-auth
Authenticate to websites with human-in-the-loop browser handoff. Use when user needs to log into a website, complete 2FA, or solve CAPTCHAs for agent access.
agent-sh/agentsys 720
-
enhance-claude-memory
Use when improving CLAUDE.md or AGENTS.md project memory files.
agent-sh/agentsys 720
-
validate-delivery
Use when user asks to "validate delivery", "check readiness", or "verify completion". Runs tests, build, and requirement checks with pass/fail instructions.
agent-sh/agentsys 720
-
drift-analysis
Use when the user asks about plan drift, reality check, comparing docs to code, project state analysis, roadmap alignment, implementation gaps, or needs guidance on identifying discrepancies between documented plans and actual implementation state.
agent-sh/agentsys 720
-
enhance-cross-file
Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.
agent-sh/agentsys 720
-
enhance-prompts
Use when improving general prompts for structure, examples, and constraints.
agent-sh/agentsys 720
-
perf-baseline-manager
Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.
agent-sh/agentsys 720
-
sync-docs
Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes.
agent-sh/agentsys 720
-
perf-benchmarker
Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.
agent-sh/agentsys 720
-
enhance-docs
Use when improving documentation structure, accuracy, and RAG readiness.
agent-sh/agentsys 720
-
maintain-cross-platform
Use when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for maintaining AgentSys's 3-platform architecture.
agent-sh/agentsys 720
-
claude-code-skill
Manage persistent coding sessions across Claude Code, Codex, Gemini, and Cursor engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, or switching models/tools at runtime. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent".
Enderfga/openclaw-claude-code 314
-
openai-whisper
Local speech-to-text with the Whisper CLI (no API key).
letta-ai/lettabot 308
-
himalaya
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
letta-ai/lettabot 308
-
bear-notes
Create, search, and manage Bear notes via grizzly CLI.
letta-ai/lettabot 308
-
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
letta-ai/lettabot 308
-
nano-banana-pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
letta-ai/lettabot 308
-
ordercli
Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).
letta-ai/lettabot 308
-
camsnap
Capture frames or clips from RTSP/ONVIF cameras.
letta-ai/lettabot 308
-
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
letta-ai/lettabot 308