agentleFS
charliee1wcharliee1w/consolidation-memory/.claude/skills/review/SKILL.md

review

Skill8 starsChanged 9 months agoMITView on GitHub

Deep code review of recent changes or a specific area

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, daily-arxiv 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.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +5 more from Lambenthan
  • +3 more from dzhng

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    If $ARGUMENTS is empty, review all uncommitted changes:

    line 14
  2. Very specific:

    If $ARGUMENTS is a file or glob pattern, review those files.

    line 20
  3. Very specific:

    If $ARGUMENTS looks like a commit range (e.g., v0.9.0..HEAD), review that range:

    line 22
  4. Distinctive:

    Do existing tests still make sense?

    line 56
  5. Distinctive:

    No dead code or commented-out blocks

    line 62

“Common” is measured: kept by at least 6 in 10 of the 156 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

Code Review for consolidation-memory

Review $ARGUMENTS (or uncommitted changes if empty).

Scope

If $ARGUMENTS is empty, review all uncommitted changes:

git diff
git diff --cached

If $ARGUMENTS is a file or glob pattern, review those files.

If $ARGUMENTS looks like a commit range (e.g., v0.9.0..HEAD), review that range:

git diff <range>

Review Checklist

For each changed file, evaluate:

Correctness

  • Logic errors, off-by-one, race conditions
  • Edge cases: empty inputs, None values, large inputs
  • Error handling: correct exceptions, no swallowed errors
  • Thread safety: shared state protected by locks?

Architecture

  • Does this fit the existing patterns? (Config singleton, atomic writes, structured records)
  • Are new dependencies justified?
  • Is the consolidation engine's threading model respected?

Security

  • Prompt injection vectors in LLM-facing strings
  • Path traversal in file operations
  • SQL injection (should use parameterized queries)
  • Input validation and size limits

Performance

  • FAISS operations: batch vs single-item?
  • SQLite: indexes used? N+1 queries?
  • Embedding calls: batched?
  • Memory: unbounded collections?

Testing

  • Are new code paths covered?
  • Do existing tests still make sense?
  • Are mocks patching the right module paths? (common issue after refactors)

Code Quality

  • Type hints present and correct
  • ruff-clean (line length 100, Python 3.10+ target)
  • No dead code or commented-out blocks
  • Docstrings where behavior is non-obvious

Output Format

Organize findings by severity:

CRITICAL — bugs, data loss risks, security issues HIGH — incorrect behavior, race conditions, missing error handling MEDIUM — performance issues, missing tests, architectural concerns LOW — style, naming, minor improvements GOOD — patterns worth noting as positive examples

Include file paths and line numbers. Quote the problematic code.

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.