agentleFS
MicrosoftKnown publishermicrosoft/verona/.agents/skills/review/SKILL.md

review

Skill3.7k starsChanged 3 months agoMITView on GitHub

Run a principle-based code review on the current branch. Use when the user asks for a review, or at mandatory review checkpoints (after planning, after implementation before PR).

193 other projects use a version of this.

Trending

Quiet this year.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the microsoft/verona repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about microsoft/verona

The biggest 5 of 18 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 18

Talked about on GitHub and Hacker News (18 times).

On GitHub · 12

7 more on GitHub

On Hacker News · 6

1 more on Hacker News

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

11 rules. 0 are common, 7 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read ~/.claude/CLAUDE.md for global principles and workflow rules.

    line 14
  2. Very specific:

    Read CLAUDE.md (project root) for Verona-specific conventions.

    line 15
  3. Very specific:

    Read all documentation in vc/docs/ that is relevant to the changed files.

    line 16
  4. Distinctive:

    Read every changed file in full (not just the diff).

    line 26
  5. Distinctive:

    If the build fails or tests fail, report those as findings.

    line 38
  6. Distinctive:

    Test coverage gaps — are new code paths tested?

    line 48
  7. Distinctive:

    If violated: the specific file, line, and what needs to change

    line 56
  8. Very specific:

    Test conventions: self-contained, no use "_builtin", bitmask exit codes

    line 80
  9. Distinctive:

    No explicit type annotations when inference suffices

    line 84
  10. Distinctive:

    Verify every factual claim by reading the actual code.

    line 90
  11. Distinctive:

    If no issues are found, state "Clean review — no findings."

    line 100

“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

Principle Review

You are a fresh-context code reviewer for the Verona compiler (verona-bc). Your job is to deliver a two-part review: general correctness + principle-by-principle evaluation.

Setup

  1. Read ~/.claude/CLAUDE.md for global principles and workflow rules.
  2. Read CLAUDE.md (project root) for Verona-specific conventions.
  3. Read all documentation in vc/docs/ that is relevant to the changed files.

Identify changes

Determine the base branch. If $ARGUMENTS provides one, use it. Otherwise default to main.

git diff --name-only $(git merge-base HEAD $0) HEAD

Read every changed file in full (not just the diff). Also read supporting files needed for verification — if a changed file calls a function, read the function's definition.

Build and test

cd build && ninja install 2>&1 | tail -20
cd build && ctest --output-on-failure -j$(nproc) 2>&1 | tail -40

If the build fails or tests fail, report those as findings.

Part 1: General Correctness Review

Check for:

  • Logic errors, off-by-one, null/empty checks
  • Resource leaks, use-after-move
  • Missing error handling
  • Dead code or unreachable paths
  • Incomplete implementations (TODOs, stubs)
  • Test coverage gaps — are new code paths tested?
  • Documentation accuracy — do comments match the code?

Part 2: Principle-by-Principle Review

Go through each principle from ~/.claude/CLAUDE.md systematically. For each one that is relevant to the changes, state:

  • The principle name
  • Whether the code complies or violates
  • If violated: the specific file, line, and what needs to change

Key principles to check (non-exhaustive):

C++ Style:

  • C++20 features used appropriately
  • snake_case functions/variables, PascalCase types/tokens
  • Allman braces
  • No goto
  • #pragma once, correct include ordering

Trieste Patterns:

  • Named WF accessors (n / ChildToken) over positional indexing
  • clone() shared nodes before multi-insertion
  • Node n = Token for construction (not auto n = Token)
  • Error nodes via err() helper
  • WF declarations match actual output

Architecture:

  • Small composable passes (not monolithic)
  • Layered dependencies respected

Testing & Robustness:

  • Liberal use of assert()
  • Test conventions: self-contained, no use "_builtin", bitmask exit codes
  • Golden file format: exit_code.txt has no trailing newline

Verona Style:

  • No explicit type annotations when inference suffices
  • (obj.field)(args) for apply on field access
  • Type(args) constructor sugar

Factual Accuracy Requirement

Verify every factual claim by reading the actual code. Do NOT summarize from memory or inference. If you're unsure about something, read the file again.

Deliverable

Report findings as a numbered list. For each finding:

  1. Severity: must-fix, should-fix, or nit
  2. File and line reference
  3. What's wrong and what the fix should be
  4. Which principle applies (for Part 2 findings)

If no issues are found, state "Clean review — no findings."

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.