agentleFS
Sign inStart free
tokarixtokarix/memory-server/skills/review/SKILL.md

review

Skill1 starsChanged 8 months agoApache-2.0View on GitHub

Use when one agent should hand off work (a plan, code changes, or any memory) for another agent to review through the memory server's review tools.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images 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

  • 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

    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

  • 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

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

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 6

    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. Distinctive:

    Use this skill when work should be handed from one agent to another for structured review through the memory server.

    line 8
  2. Very specific:

    Call review_queue(project) to see all pending reviews, or filter with review_queue(project, category: "plan") or review_queue(project, …

    line 58
  3. Distinctive:

    Prefer findings over vague impressions.

    line 80
  4. Distinctive:

    If the work is acceptable, say why.

    line 82
  5. Distinctive:

    If the work needs changes, explain what is wrong and what should change.

    line 83
  6. Distinctive:

    Use stable reviewer/author tags so later searches are easy:

    line 105
  7. Distinctive:

    If a review supersedes an earlier one, mention that explicitly in the notes.

    line 112

“Common” is measured: kept by at least 6 in 10 of the 157 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

Use this skill when work should be handed from one agent to another for structured review through the memory server. Supports plan reviews, code reviews, and any future review type.

When to use it

  • A plan should be stored durably and reviewed before execution.
  • An agent has completed a feature or fix and wants a second opinion.
  • Cross-agent review is needed before merging or proceeding.
  • A project needs a consistent review workflow instead of ad hoc prompts.

Core workflow

  1. Author stores a memory tagged review-needed and author:<agent>.
  2. Reviewer calls review_queue(project) to find pending items.
  3. Reviewer evaluates the item and calls review_submit(...).
  4. review_submit stores a decision memory and retags the original from review-needed to reviewed.

Request a review

Plan review

Store the plan as a plan memory.

Required tags: review-needed, author:<agent>

Recommended tags: session:<external-session-id>, topic:<short-topic>

The content should include:

  • goal
  • proposed steps
  • risks or open questions
  • verification or test plan

Code review

Store a context memory describing the code to review.

Required tags: code-review, review-needed, author:<agent>

Recommended tags: session:<external-session-id>, topic:<short-topic>

The content should include:

  • git range or commit references (e.g. abc123..def456)
  • description of the changes
  • areas of concern or focus
  • how to verify

Perform a review

  1. Call review_queue(project) to see all pending reviews, or filter with review_queue(project, category: "plan") or review_queue(project, category: "context").
  2. Select the relevant item.
  3. Review it:
    • For plans: bugs, missing tests, risky assumptions, behavioral regressions, rollout or verification gaps.
    • For code: correctness, missing tests, security concerns, API design, performance issues.
  4. Produce a clear verdict:
    • approved
    • changes-requested
    • rejected
  5. Call review_submit(...) with:
    • memory_id
    • reviewer
    • verdict
    • notes

Review style

  • Be concrete.
  • Prefer findings over vague impressions.
  • Tie criticism to execution risk.
  • If the work is acceptable, say why.
  • If the work needs changes, explain what is wrong and what should change.

Suggested note template

  • Finding: concrete issue or risk
  • Impact: why it matters
  • Change: what should be different

Polling for reviews

To watch for incoming review requests, use CronCreate to poll review_queue every 5-10 minutes:

CronCreate(
  schedule: "*/5 * * * *",
  command: "review_queue(project=\"<project>\")"
)

Cross-agent convention

Use stable reviewer/author tags so later searches are easy:

  • author:claude
  • author:codex
  • reviewed-by:claude
  • reviewed-by:codex

If a review supersedes an earlier one, mention that explicitly in the notes.

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.

Check your setup, free