agentleFS
VinkyDevVinkyDev/vibestart/.agents/skills/self-review/SKILL.md

self-review

Skill295 starsChanged 30 days agoMITView on GitHub

Review your own change before you open or update a pull request. Use when a change is ready to commit or push, or after fixing review findings.

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use latex-formatting, novelty-assessment and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lingzhi227Skill

    latex-formatting

    Handle LaTeX formatting, templates, and styling for academic papers. Set up conference templates (ICML, ICLR, NeurIPS, AAAI, ACL), fix formatting issues, manage packages, and ensure venue-specific compliance. Use when the user needs to set up a paper template, fix LaTeX formatting, or prepare for submission.

    Also in 4 projects that use this

  • lingzhi227Skill

    novelty-assessment

    Assess research idea novelty through systematic literature search. Multi-round search-evaluate loops with harsh critic persona. Binary novel/not-novel decision with justification. Use before committing to a research direction.

    Also in 4 projects that use this

  • michaelboedingSkill

    slide-generation

    Use this skill to create presentation slides from structured content. Triggers: "create slides", "generate presentation", "make powerpoint", "create pptx", "build slides", "presentation from content", "slide deck", "slides for" Outputs: PPTX files, Markdown slides, or HTML presentations. Used by: pitch-deck-agent, market-researcher-agent, and other agents needing slides.

    Also in 4 projects that use this

  • juanlurgSkill

    paper-to-code

    Reads a research paper and generates an implementation notebook with equations, code, and a toy example. Use when the user wants to implement a paper, convert a paper to code, or reproduce a paper's algorithm.

    Also in 4 projects that use this

  • OpenAISkill

    idea-generation

    Use when triaging public-equity idea candidates. Do not use for final trade recommendations, pitches, memos, or models.

    Also in 3 projects that use this

  • +6 more from lingzhi227

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Pull request: Write the body with the pr skill.

    line 13

“Common” is measured: kept by at least 6 in 10 of the 44 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Machines read a change before a person does. This skill runs the checks and a fresh-context review, then answers every finding.

  1. Evidence. Run vp run ready and keep its last lines. A change that alters generated output also needs the snapshot and golden diff read: it is what every generated project receives. When the change reaches a template and its services are available, run vp run stacks verify '<pattern>' for one stack that renders it. Done when you hold output that shows the change working, not a claim that it does.
  2. Review in a fresh context. Dispatch the reviewer subagent (.agents/agents/reviewer.md) with the diff range, or the changed paths when nothing is committed, and one paragraph of intent. It loads REVIEW.md itself. Done when it returns its count line.
  3. Answer every finding. Fix each Important one at its root and every instance of its class, or record why it does not apply. A Nit is your call. Done when each finding is marked fixed or answered with a reason.
  4. Converge. Re-run the reviewer on the commits since its last pass only. After three rounds, stop and reconsider the approach rather than patching further. Done when a round reports no Important finding.
  5. Fix the source. When a finding is one a rule could have caught, or one you have seen before, put the fix where the next change meets it: a lint rule or test, a line in REVIEW.md or AGENTS.md, or a case in docs/review-evals/cases.json. Say which in the pull request.
  6. Pull request. Write the body with the pr skill; .github/pull_request_template.md holds its sections. Evidence is the output from step 1. Done when Merge Danger names the door and the blast radius.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.