agentleFS
jukanntennjukanntenn/harness-deepseek-harness/.agents/skills/reviewing/SKILL.md

reviewing

Skill2 starsChanged 41 days agoMITView on GitHub

Use when reviewing a pull request in this repository — orients the reviewer to this codebase's standards (AGENTS.md conventions, RFCs, quality gates) and the review-specific checks that code alone can't show

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    New prose receives semantic review: Use editing-prose to critically review every added or changed Markdown passage, docstring, comment, …

    line 20
  2. Distinctive:

    Required evidence exists: Verify the author ran the relevant local checks for the diff and that CI covers the exhaustive matrix.

    line 22
  3. Distinctive:

    Configuration and public choices: ask what current-consumer evidence or prior art supports each default, public operation set, format, or …

    line 29
  4. Distinctive:

    Enforcement: follow every denial path to the operation that executes it.

    line 30
  5. Distinctive:

    Negative controls: verify that a deliberately invalid case fails through the real gate or runner for the intended rule.

    line 34
  6. Very specific:

    Implemented RFCs match shipped reality: when a PR implements a proposed RFC, move it to implemented/ and rewrite it as present-tense …

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Reviewing a PR

This skill is guidance, not a complete checklist. Verify and fetch the PR's live base and exact head, then run uv run hdsh scope --base <verified-base-ref> --head <verified-head-ref> before reading the diff and enough surrounding code to understand the design. The report identifies paths and dirty layers but does not replace semantic review. Re-establish the base and rerun it after a retarget or merge. Prioritize correctness, lifecycle, security, and broken required behavior over style; a short review with one substantiated blocker is better than a list of nits.

Sources of truth

  • AGENTS.md: standing repository rules.
  • docs/AGENTS.md: documentation placement and prose discipline.
  • editing-prose: required coverage and editorial judgment for comments, docs, diagnostics, and CLI strings.
  • RFCs (.agents/rfcs/): design rationale and decisions. Treat disagreement with an RFC as a design discussion, not an automatic veto.
  • For bilingual changes, read translation-rules.md and terminology.md; the extended translation skill is outside automatic review and runs only on explicit user invocation.

Blocking requirements

  1. New prose receives semantic review. Use editing-prose to critically review every added or changed Markdown passage, docstring, comment, diagnostic, and visible string. Verify required coverage, accuracy, placement, and editorial quality against the owning code or behavior; automated checks do not establish those properties.
  2. Docs match the code. Config, defaults, errors, CLI output, exit codes, and public behavior update the owning README and docstrings in the same diff. Comments state non-obvious contracts; flag implementation narration, test walkthroughs, review history, and duplicated rationale for deletion or a link to their one home.
  3. Required evidence exists. Verify the author ran the relevant local checks for the diff and that CI covers the exhaustive matrix; review the semantic gaps neither can detect.

Manual checks

  • Intent and interface contracts: trace both sides of every changed interface. Confirm the implementation matches the PR and any RFC, including errors, cancellation, ownership, and disposal.
  • Lifecycle and concurrency: for async setup, subprocesses, locks, filesystem state, or teardown, check races before publication, cancellation during waits, independent error reporting, ownership before reentry, complete cleanup, and quiescent disposal.
  • Scope, ownership, and necessity: map each abstraction, state machine, option, and defensive copy to its current contract and production consumer. Challenge unrelated features and speculative generality, then test the PR against the root rules.
  • Configuration and public choices: ask what current-consumer evidence or prior art supports each default, public operation set, format, or imported external concept. Require an explicit choice or deferral when that evidence is absent.
  • Enforcement: follow every denial path to the operation that executes it; exercise direct and alternate callers that can bypass argument parsing, validation, wrappers, or configuration.
  • Borrowed and derived state: determine whether each retained value is borrowed or owned, then trace every cache or derived view to its authoritative source and documented refresh point.
  • Real entry path: tests exercise the shipped console entry points (hdsh-scope, the gates) through their main() or a real subprocess where relevant. A hand-imported helper does not catch argument-parsing or exit-code regressions.
  • Test strength: assertions fail on the intended regression and verify external state, logs, events, or disposal rather than restating the implementation or trusting an agent's report. Coverage is necessary but not evidence that the scenario is correct.
  • Negative controls: verify that a deliberately invalid case fails through the real gate or runner for the intended rule.
  • Implemented RFCs match shipped reality: when a PR implements a proposed RFC, move it to implemented/ and rewrite it as present-tense shipped state in the same diff, then verify paths, names, and mechanisms against the implementation.
  • Bilingual changes: compare meaning and terminology on both sides; a green pairing hash does not prove translation quality.

Reporting findings

State the defect, location, impact, and evidence. Place a localized defect inline on the tightest relevant diff range; use a PR-level comment for cross-cutting architecture, scope, or review-wide synthesis. Separate blockers from suggestions and omit issues already enforced by a green gate. Use the existing GitHub review thread for replies. When receiving review, verify each claim and fix or rebut it on technical grounds without performative agreement.

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.