Loading...
Loading...
Found 110 Skills
Attack a code change and report what survives. Dispatches independent reviewers in parallel, each with a single job and no access to the implementer's reasoning: one hunts correctness bugs blind to the issue, one hunts requirement gaps against the issue text, one runs outside the process entirely. Optionally re-attacks its own findings, then synthesizes what is left. Returns findings and changes nothing — no tooling, no autofix, no edits. On request it publishes to the author, gated on demonstrated evidence. Every phase is configurable.
Handle a pull request from whichever side you are on. On someone else's branch it attacks the diff through changes-review, then publishes a real review with per-line comments and a verdict. On your own it works the threads people and bots left — decides its standing in each, verifies the claim before answering, runs the project's checks, then replies and resolves. Changes no code unless asked.
Write Rust tests to verify correctness of Rust code.
Validate that implementation matches specs, design, and tasks. Trigger: When the orchestrator launches you to verify a completed (or partially completed) change.
Implement a GitHub issue end-to-end using TDD, following the Agent Brief contract. Use when user wants the agent to pick up a ticket, write code to fulfill its acceptance criteria, commit, push, and close the issue.
Prove a claim of done, fixed, or passing by running the commands and reading the output before making it. Use before claiming work is complete, fixed, or tested, and before committing or opening a PR.
Implement an agreed task incrementally and verify the result.
Use when you have a written implementation plan to execute with review checkpoints
Use before claiming work is done, fixed, or passing — requires running verification commands and confirming output before any success claim. Prevents false completion claims, unverified assertions, and "should work" statements.
Creates or updates TODO_LIST.md by reading all .md files in the project using sub-agents, then verifies which TODOs are already done by checking the actual code. Use when the user wants to build a comprehensive TODO list from existing documentation, verify TODO status against code, or says "build TODO list".
CRITICAL: Use for agent-spec CLI tool workflow. Triggers on: agent-spec, contract, lifecycle, guard, verify, explain, stamp, checkpoint, spec verification, task contract, spec quality, lint spec, run log, "how to verify", "how to use agent-spec", "spec failed", "guard failed", contract review, contract acceptance, PR review, code review workflow, 合约, 验证, 生命周期, 守卫, 规格检查, 质量门禁, 合约审查, "验证失败", "怎么用 agent-spec", "spec 不通过", "工作流"
Use when completing tasks, implementing major features, or before merging to verify work meets requirements