refactor
Audit an existing project against its standards and apply selected improvements while preserving behavior.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-11
- Stars
- ★ 1.6k
- Forks
- 474
01 前言 Front Matter
- name
- refactor
- effort
- xhigh
- description
- Audit an existing project against its standards and apply selected improvements while preserving behavior.
- argument-hint
- [focus]
- user-invocable
- true
- disallowed-tools
- Write Edit NotebookEdit
- disable-model-invocation
- true
02 资源文件 1
- 参考文档agents/openai.yaml186 B
03 SKILL.md 正文
Refactor
Bring an existing project closer to its standards without changing user-visible behavior. This is the repository-convergence exception in the development loop. It can inspect the whole target but can change only an approved tranche.
$ARGUMENTS is a free-text focus, such as database queries, src/orders, or a planned feature.
With a focus, audit that area and its required dependencies. Without one, audit the whole project.
The audit is always read-only. The user chooses what to change afterwards.
The audit changes nothing in the target. The frontmatter withholds write tools during the audit, but the rule holds even when the harness exposes them.
1. Audit
Apply the loop's Standards gate and the engineering contract. Record the source paths you selected.
Use focused owners where their signal exists:
align-docsin inspection-only mode for repository context and documentation;staff-reviewfor code quality inside the scope.
Then inspect what these owners do not cover. Check the data model, query access paths, batching, indexes, repeated work, held resources, retries, recomputation, and behavior with multiple owners.
Exclude generated code and dependencies. Record inspected surfaces and gaps. Confirm disputed library behavior in official documentation for the installed version.
Every finding includes evidence, location, severity, expected result, impact, effort, change risk, dependencies, confidence, and required proof.
2. Rank
Do not invent a score. Put security and data-loss risks before normal impact-to-effort ordering. Severity measures defect risk. Impact over effort orders the roadmap.
Use repository history to weight code that changes often.
Group findings with one root cause into one item.
Label each item strong, worth exploring, or speculative. Mark estimated values as estimates.
Diagnose only. Do not design the fix yet.
3. Choose
Present the roadmap, then ask the user to select tranches. Selecting none ends the work with the audit. A tranche covers one area, has compatible dependencies, and shares one verification and rollback strategy.
A pure audit writes nothing.
Save the roadmap under docs/plans/ only after the user selects work or explicitly asks to save it.
4. Converge
Run a full cycle for each tranche:
- Use
brainstormingandcreate-testto settle invariants, thresholds, failure cases, and rollback. - Capture a characterization proof that passes on unchanged code and after the refactor.
- Write the plan and chronicle, then present the plan for approval before code changes.
- Implement in small slices and run the nearest check after each slice.
Finish with cumulative verification, independent review, and a recalculated roadmap. If a tranche fails proof or review, stop and report it.
Keep business changes as separate tasks. Do not widen a tranche during implementation. Record a new finding in the roadmap. Never commit.
5. Resume
The saved roadmap and any incomplete tranche plan are the persistent state. A later run resumes them instead of repeating the audit.
04 同仓库更多 Skills
migrate-to-e2e
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.
e2e
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
create-verification-skill
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.
deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.