agentleFS
DenchHQDenchHQ/ironclaw/skills/gstack/review/SKILL.md

review

Skill1.7k starsChanged 7 months agoMITView on GitHub

Pre-landing PR review. Analyzes diff for SQL safety, race conditions, LLM trust boundary violations, conditional side effects, and structural issues. Auto-fixes obvious issues, asks about complex ones. Use when reviewing code before merge, or when asked for "code review".

192 other projects use a version of this.

Trending

Quiet since February.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 1 mentionMar 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 DenchHQ/ironclaw repository that our weekly crawl found: only 1 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about DenchHQ/ironclaw

The biggest 1 of 1 mention linking to the repository that our crawl found. Each line is their own headline.

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

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Check for existing PR: gh pr view --json baseRefName -q .baseRefName

    line 20
  2. Very specific:

    If no PR: gh repo view --json defaultBranchRef -q .defaultBranchRef.name

    line 21
  3. Distinctive:

    Before reviewing code quality, check: did they build what was requested?

    line 35
  4. Distinctive:

    Read commit messages, PR description, and TODOS.md

    line 37
  5. Distinctive:

    If you claim "this is handled elsewhere" → read and cite the handling code

    line 113
  6. Distinctive:

    If you claim "tests cover this" → name the test file and method

    line 114
  7. Distinctive:

    Never say "likely handled" or "probably tested" — verify or flag as unknown

    line 115
  8. Distinctive:

    After review, proceed to ship to create the PR.

    line 134
  9. Distinctive:

    Read the FULL diff before commenting: Don't flag issues already addressed.

    line 140
  10. Distinctive:

    Never commit, push, or create PRs — that's ship's job.

    line 144

“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

Pre-Landing Review — Find What CI Misses

You are a staff engineer. Find the bugs that pass CI but blow up in production. Auto-fix the obvious ones. Flag the rest.

Related skills: plan-eng-review | ship | investigate


Step 0: Detect Base Branch

  1. Check for existing PR: gh pr view --json baseRefName -q .baseRefName
  2. If no PR: gh repo view --json defaultBranchRef -q .defaultBranchRef.name
  3. Fallback: main

Step 1: Check Branch

  1. git branch --show-current — if on base branch, nothing to review.
  2. git fetch origin --quiet && git diff origin/<base> --stat — if no diff, nothing to review.

Step 1.5: Scope Drift Detection

Before reviewing code quality, check: did they build what was requested?

  1. Read commit messages, PR description, and TODOS.md
  2. Compare files changed against stated intent
Scope Check: [CLEAN / DRIFT DETECTED / REQUIREMENTS MISSING]
Intent: <what was requested>
Delivered: <what the diff actually does>

This is informational — does not block the review.


Step 2: Get the Diff

git fetch origin <base> --quiet
git diff origin/<base>

Step 3: Two-Pass Review

Pass 1 (CRITICAL)

CategoryWhat to look for
SQL & Data SafetyRaw SQL injection, missing parameterization, unguarded DELETE/UPDATE
Race ConditionsConcurrent access to shared state, read-modify-write without locks
LLM Trust BoundaryLLM output used in SQL, eval, system commands, or rendered as HTML without sanitization
Enum CompletenessNew enum value added but not handled in all switch/case/if-else chains

Pass 2 (INFORMATIONAL)

CategoryWhat to look for
Conditional Side EffectsSide effects (DB writes, API calls, emails) inside conditional branches that might not execute
Magic NumbersHardcoded values that should be constants
Dead CodeUnreachable code, unused imports, commented-out blocks
Test GapsNew code paths without corresponding tests
PerformanceN+1 queries, missing indexes, unbounded queries, large bundle imports

Step 4: Fix-First Review

Every finding gets action — not just critical ones.

Classify each finding as AUTO-FIX or ASK

  • AUTO-FIX: Mechanical fixes with one correct answer (unused imports, missing await, obvious typos)
  • ASK: Fixes requiring judgment (architecture changes, behavior changes, security decisions)

Apply AUTO-FIX items directly

For each: [AUTO-FIXED] [file:line] Problem → what you did

Batch-ask about ASK items

Present in one question:

I auto-fixed N issues. M need your input:

1. [CRITICAL] file:line — Race condition in status transition
   Fix: Add WHERE clause to UPDATE
   → A) Fix  B) Skip

2. [INFO] file:line — LLM output not validated before DB write
   Fix: Add schema validation
   → A) Fix  B) Skip

Verification of Claims

  • If you claim "this is handled elsewhere" → read and cite the handling code
  • If you claim "tests cover this" → name the test file and method
  • Never say "likely handled" or "probably tested" — verify or flag as unknown

Step 5: Documentation Staleness Check

For each .md file in the repo root — if code changes affect described features but the doc wasn't updated, flag as informational.


Step 6: Output

Pre-Landing Review: N issues (X critical, Y informational)
Auto-fixed: [list]
Needs input: [list]
Scope: [CLEAN / DRIFT / MISSING]

After review, proceed to ship to create the PR.


Important Rules

  • Read the FULL diff before commenting. Don't flag issues already addressed.
  • Fix-first, not read-only. AUTO-FIX items are applied directly.
  • Be terse. One line problem, one line fix.
  • Only flag real problems. Skip anything that's fine.
  • Never commit, push, or create PRs — that's ship's job.

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.