Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus…
Use when the user wants prose, comments, docs, or a file's text to read like a human engineer wrote it instead of an AI. Strips AI tells (em-dashes, filler openers, chatbot scaffolding) by rewriting, then runs klaussy's deterministic scrubber as a guaranteed backstop. Never touches code.
Use when the user pastes a ticket, design doc, or task description and wants it implemented. Multi-phase flow — understand, investigate (in plan mode), plan, implement, verify. Enforces strict scope rules and writes failing tests first for bug fixes.
Use when the user wants a new git worktree created for a task. Picks a kebab-case branch name with a fix/feat/chore/docs/refactor prefix, runs git worktree add from the configured base branch, and reports the new path.
Use when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.
Use when the user wants a PR description generated for the current branch. Reads commit history, file changes, and CLAUDE.md, then writes a Summary / Changes / Test Plan / Notes block to pr-description.md.
Use when reviewing a staged diff or an about-to-commit/push change for last-mile issues — silent failures, leaked secrets, debug leftovers, blatant correctness landmines, and excessive/narrating comments. Reports findings on the changed lines only; it does not refactor or rewrite code. This is the canonical source for…
Use when the user wants the current change QA'd and PR-ready evidence captured. Classifies the diff and runs the verification that actually fits it — screenshots for UI/frontend changes, endpoint or e2e runs for backend, command output for a CLI, tests for a library — then saves artifacts and writes a QA summary.…
Use when the user wants to restructure code while preserving behavior exactly. Establishes a passing test baseline first, then makes incremental moves that each leave the suite green. Refuses to change behavior and structure in the same step.
Use when the user wants to cut a release — bump the version, update the changelog from conventional commits, and tag. Detects where the version lives, derives the next version from the commits since the last tag, and stages the release locally; it does not push or publish unless explicitly asked.
Use when the user hands you a task definition and wants the ENTIRE development loop run end-to-end — plan, implement, review and fix, QA the change with evidence appropriate to it, open a humanized PR, then poll CI and code review, fixing and resolving until the PR is green and clean. Does everything except merge.…
Use when the user wants a thorough PR or branch review. Triages by diff size — small PRs get a single-pass review, large PRs fan out to parallel sub-agents (correctness, architecture, security, scope, and an Agentic & Evals lens that activates on AI/agent code) with a validation phase that drops false positives.
Use when the user wants to run, start, or launch this project's app — to watch a change work end-to-end, reproduce behavior in the real app, or smoke-test locally. Finds the run command from CLAUDE.md and drives the app; it does not write features or fix bugs.
Use when the user wants a focused security pass over the current change — scanning the branch diff for leaked secrets, injection and SSRF, broken access control, unsafe deserialization, and newly added or vulnerable dependencies. Narrower and deeper than the general review skill: it applies only the security lenses…
Use right before declaring an implementation done — a last-pass review of your OWN uncommitted change against a fixed checklist (reuse, stdlib, comments, dead code, tests, scope). Catches the things that make a diff read as AI-written before a human ever sees it. Reviews the current diff; it does not write new…