agentleFS
lithammerlithammer/ai/skills/self-review/SKILL.md

self-review

Skill0 starsChanged 52 days agoMITView on GitHub

Use this skill automatically when you feel your code is ready for human review, and whenever writing or reviewing code comments. Ready means the code works and achieves a stated goal, verified by your own tests and/or, if you deem it necessary, human testing.

51 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 10 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

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 5 projects that use this

  • +6 more from lingzhi227

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 3

    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:

    One word per concept, one concept per word: Keep a vocabulary. If sync names "pulling remote changes," it cannot also name "flushing edits …

    line 23
  2. Distinctive:

    Combine overlapping concepts: If two types, functions, or constants overlap significantly, merge them.

    line 43
  3. Distinctive:

    Derivability: If a value can be computed from values already in scope, don't pass or store it separately.

    line 45
  4. Distinctive:

    If a name or comment needs the conversation to be understood, rewrite it against the codebase's own vocabulary.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 42 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

Review changes in the current branch, or in the scope the user specifies. Apply these criteria without changing behavior. Only touch code in that scope, and run the relevant existing checks after changes.

Word choice in code and comments

Variable names, function names, and comments are all prose. Apply Orwell's rules ("Politics and the English Language") to each:

Never use a long word where a short one will do.

If it is possible to cut a word out, always cut it out.

Never use the passive where you can use the active.

Never use a foreign phrase, a scientific word, or a jargon word if you can think of an everyday English equivalent.

Latinate vocabulary (reconcile, coalesce, normalize, reconciliation) sounds technical and abstract; Anglo-Saxon words (prune, run, watch, stop, drop, walk) are short and physical. Prefer the Saxon word.

Names

  1. One word per concept, one concept per word. Keep a vocabulary. If sync names "pulling remote changes," it cannot also name "flushing edits to disk;" rename one of them.
  2. Cut words the context already carries. A module named workspaceWatcher does not need startNativeWorkspaceWatcher; watchWorkspace says the same thing.
  3. A compound name is usually a hedge:
  • ❌ lastObservedDiskContent is a specification to defend
  • ✅ baseline is a readable description

Comments

State, in plain English, the constraint the code cannot show: why the non-obvious exists.

  • ✅ If code is complex and the implementation is non-obvious, add a comment.
  • ✅ If a function contains complex behaviors or side effects, add a doc comment.
  • 🗑️ If a comment narrates change history from the conversation, delete it.
  • 🗑️ If a comment restates code whose behavior is self-evident, delete it.

Code structure

  1. Inverted pyramid. Within a file, lead with the exported or significant functions and push helpers below them. Don't bury the lead.
  2. Related concepts over monoliths. Break a large file into modules that each own one concept.
  3. Combine overlapping concepts. If two types, functions, or constants overlap significantly, merge them. The fewer distinct concepts a reader must hold in their head, the better.
  4. Use shared code. Common utilities (ex. file path parsing) may exist in the codebase already. Check for library or utility functions before inlining.
  5. Derivability. If a value can be computed from values already in scope, don't pass or store it separately. Removing derivable state often simplifies signatures, types, and control flow in one move. Example: an isDirty parameter that is always editorContent !== baseline can be dropped.

Overfitting

Code must stand on its own. If a change only makes sense to someone who watched it happen (this conversation, this PR), it is overfitted. Write for the reader who arrives with no history.

  • If a name or comment needs the conversation to be understood, rewrite it against the codebase's own vocabulary.
  • No backwards compatibility with unshipped code. Supporting an old signature, alias, or data shape that only existed earlier in the same branch is compatibility with something that was never deployed. Delete the old path and update its callers.

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.