agentleFS
eugnmueller-87eugnmueller-87/claude-blueprint/.claude/skills/pr-review/SKILL.md

pr-review

Skill1 starsChanged 5 months agoMITView on GitHub

Multi-lens review of the current diff — delegates to the code-reviewer, silent-failure-hunter, and security-reviewer agents, applies an 80%-confidence filter, and returns terse findings sorted by severity. Use before committing, before opening a PR, or on any diff that needs a real correctness pass. Trigger phrases "review this PR", "review the diff", "review my changes".

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use clack-cli-patterns, drag-to-reorder 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.
  • openchamberSkill

    clack-cli-patterns

    Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.

    Also in 3 projects that use this

  • openchamberSkill

    drag-to-reorder

    Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.

    Also in 3 projects that use this

  • jtenniswoodSkill

    expert-reset

    Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.

    Also in 3 projects that use this

  • CES-LtdSkill

    oss-pr

    Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.

    Also in 3 projects that use this

  • CES-LtdSkill

    pr-automation

    PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".

    Also in 3 projects that use this

  • +7 more from openchamber

The file

Files
SKILL.md

pr-review

Trigger: "review this PR" / "review the diff" / "review my changes"

Standing rules: ../_conventions.md.

Catch real bugs, not style. Style is handled by the formatter/linter — don't report it. Only ship findings you're at least 80% sure are real; drop the rest. Lead with the single most important fix.

Steps

  1. Get the diff. git diff --name-only (working tree) or the staged diff if invoked mid-ship. If reviewing a GitHub PR, gh pr diff <n>. State what scope you're reviewing in one line.
  2. Delegate the lenses (run the agents on the changed files):
    • code-reviewer — off-by-ones, null derefs, inverted logic, race conditions, complexity.
    • silent-failure-hunter — swallowed exceptions, bare except:, results ignored, None returned on error paths (huge in Python + agent code).
    • security-reviewer — only if the diff touches an API/auth/input boundary or handles credentials.
  3. Python/AI-specific passes (do these yourself on top of the agents):
    • Bare except: or except Exception: pass — swallowed errors.
    • Mutable default arguments (def f(x=[])).
    • Un-awaited coroutines / blocking calls inside async def.
    • LLM calls with no timeout, no retry, or output parsed without a guard for refusals/truncation.
    • Secrets read from anywhere but env vars.
  4. Merge + filter. Collapse duplicate findings across agents. Apply the ≥80% confidence filter. Drop anything pre-existing and outside the changed scope.
  5. Report (terse): one line per finding, most severe first — file:line: <issue> (fix: <hint>). End with one sentence naming the single most important fix. If nothing survives the filter, say the diff is clean — and only because you actually reviewed it.

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.