One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-explore/SKILL.md
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-help/SKILL.md
Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/skills/caveman-learn/CLAUDE.md
The consent-gated half of caveman learn. The analyzer (the Go proxy) measures where an agent's tokens go and writes a ranked plan; this skill is what an agent loads to…
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-learn/SKILL.md
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-manage/SKILL.md
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-optimize/SKILL.md
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-review/SKILL.md
Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-setup/SKILL.md
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman/SKILL.md
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
JuliusBrusseeSkillJuliusBrussee/caveman/skills/caveman-stats/SKILL.md
Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/investigate-first/SKILL.md
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/lean-build/SKILL.md
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/migration/SKILL.md
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/safe-refactor/SKILL.md
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/surgical-patch/SKILL.md
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
JuliusBrusseeSkillJuliusBrussee/caveman/skills/verify-and-stop/SKILL.md
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
GoogleSkillgoogle-gemini/gemini-cli/.gemini/skills/agent-tui/SKILL.md
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection. Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior. Also use when: user asks "what is agent-tui", "what does agent-tui do", "demo agent-tui", "show me agent-tui", "how does agent-tui work", or wants to see it in action.
GoogleSkillgoogle-gemini/gemini-cli/.gemini/skills/async-pr-review/SKILL.md
Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.
GoogleSkillgoogle-gemini/gemini-cli/.gemini/skills/behavioral-evals/SKILL.md
Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.
GoogleSkillgoogle-gemini/gemini-cli/.gemini/skills/ci/SKILL.md
This skill enables the agent to efficiently monitor GitHub Actions, triage failures, and bridge remote CI errors to local development. It defaults to automatic replication of failures to streamline the fix cycle. - Automatic Replication: Automatically monitors CI and immediately executes suggested test or lint commands locally upon failure. - Real-time Monitoring: Aggregated status line for all concurrent workflows on the current branch. - Fail-Fast Triage: Immediately stops on the first job failure to provide a structured report. - Test…
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
