RE

Automates PR review decision-making for ShardingSphere based on root-cause analysis.

Install

mkdir -p .claude/skills/review-pr && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/2234" && unzip -o skill.zip -d .claude/skills/review-pr && rm skill.zip

Installs to .claude/skills/review-pr

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Used to review whether an Apache ShardingSphere PR truly fixes the root cause, assess side effects and regression risks, and determine whether it can be safely merged. If not mergeable, produce committer-tone change request suggestions. Supports targeted comparison across multiple review rounds.
296 chars · catalog descriptionno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • →Evaluate root-cause fixes in database code
  • →Assess regression risks in hot paths
  • →Generate committer-tone feedback
  • →Determine PR merge readiness

How it works

Iteratively applies a formal verification rubric based on public evidence to ensure PRs meet strict project standards.

Inputs & outputs

You give it
Pull request URL or diff
You get back
Merge decision and technical change recommendations

When to use review-pr

  • →Verifying root cause fixes in PRs
  • →Assessing regression risks for database code
  • →Generating actionable change requests
  • →Evaluating ShardingSphere merge readiness

About this skill

Review PR

Purpose and Modes

Judge the latest reviewed scope from root cause, behavior, contracts, tests, and public or user-authorized repository evidence. Select one output mode:

  • Formal Review Mode: return one formal result for a public PR review, authorized local-candidate review, code-readiness judgment, mergeability decision, or CI review.
  • PR Discussion Reply Mode: return a copy-ready committer reply only when the user explicitly requests a review-thread response, author or maintainer objection reply, or challenged-finding reply. Do not add a formal verdict unless requested.

Use Formal Review Mode for every explicit code or PR review and every Formal Review required by the repository completion route. Identify a local candidate and its local-only delta in ### Coverage; do not create a separate local-preflight result format or describe local-only work as the public PR state.

Review Focus

Review focus is independent from output mode.

FocusUse whenCI behavior
Code Correctness ReviewDefault review of code, tests, behavior, scope, or regression riskDo not query, wait for, or report GitHub Actions, checks, workflow runs, or Actions logs
Mergeability ReviewThe user asks whether the PR can be merged, approved, or landedReview code and required CI or checks
CI ReviewThe user asks about checks, Actions, logs, or CI failuresTreat CI evidence as the primary target

Explicit user scope wins. Formal Review of a local candidate uses Code Correctness Review unless the user explicitly requests CI.

In Code Correctness Review, unreviewed CI is not an evidence gap. Runtime facts may still be required from code, official specifications, public reproductions, or local verification. If such a decisive fact is unavailable, identify that fact—not CI—as the incomplete reason.

Canonical Assessment

Resolve one review basis before discovery: the effective candidate, applicable requirements, accepted behavior and project commitments, selected review focus, and admissible evidence. Run the Review Workflow against that basis and produce one mode-independent assessment: confirmed findings consolidated by fix boundary, needs-discussion conditions, incomplete-evidence gaps, and Completion Gate state.

Record each applicable requirement's source, content version, scope and valid exceptions in readable basis source material; a task-only requirement applies only to its authorized task candidate and must not become a universal repository or public-PR rule. Reconstruct those requirements from original user requests and maintained contracts before checking the author's proposed solution, distinguishing author choices and unverified assumptions from confirmed constraints. Do not promote an unverified inference into a requirement for a new interface, SPI, behavior, or test. Preserve later user approvals with their actual provenance instead of treating approval of an implementation choice as proof of an original version requirement or of its necessity. Keep effective content and delta identity separate from Git revision lineage so equal local and public candidates retain one code-correctness basis.

Output mode must not affect candidate discovery, proof, classification, coverage, or convergence. Never use a previous Formal Review result as evidence or as a conclusion to match. Treat previous public findings only as hypotheses whose cited facts must be reverified.

Completed coordinated reviews with the same effective candidate, requirements, focus, and evidence must produce the same canonical overall assessment. Individual independent assessments may discover different candidates; the coordinator verifies and adjudicates their cumulative findings under Independent Review Coordination. Public-PR and local-candidate reviews may resolve different candidates, but they must apply the same code-correctness judgment and Formal Review result mapping. A changed focus, requirement, or external fact changes the review basis and may legitimately change the assessment. Mergeability or CI evidence may add external-state findings or gaps, but it must not change code-correctness findings derived from an otherwise unchanged basis.

Core Contracts

  1. Review only. Do not modify PR code, post comments, submit reviews, resolve threads, rerun workflows, or change remote state without explicit authority.
  2. Public-PR Formal Review scope is the latest target PR head and the complete GitHub changed-file list; use local triple-dot semantics when reproducing it. Local-candidate Formal Review scope follows Local Candidate Scope below. A discussion reply starts from the latest head, thread context, and affected behavior; expand to complete scope only when the claim depends on it.
  3. Public community conclusions use only public evidence and sanitized verification summaries. Private-repository conclusions may use authorized repository evidence but must remain within the user-authorized task and target repository.
  4. Reconstruct trigger -> failing path -> observed result -> expected behavior before judging the patch. A fallback, default, null check, try-catch, or swallowed error is not a root-cause repair unless it fixes the owning contract.
  5. Treat every concern as a candidate until it passes the Finding Proof Gate.
  6. Do not turn uncertainty, inaccessible evidence, tool failure, skipped verification, or uninspected counter-evidence into a blocker.
  7. In Formal Review, complete the required review and do not stop at the first blocker. Consolidate findings by independent fix boundary and return the complete current-head set once after the Completion Gate. Before that gate, publish only an explicitly requested status, narrow review or early high-risk blocker, or the qualified negative result defined in the Formal Decision Contract.
  8. Follow AGENTS.md for repository authority, evidence, scope, safety, and sensitive data, and follow the applicable canonical references below for implementation, testing, contract, non-regression, and verification criteria.

Repository Code Policy References

Standalone review is read-only and does not activate code-implementation or acquire write authority. Before judging the effective candidate, read implementation rules, non-regression rules, and verification rules through EOF. Also read testing rules when tests or coverage matter, and artifact removal and contract impact rules when their trigger matches. Reuse an exact reference already read by the outer implementation workflow. Before judging reviewed code or Maven POM changes, read coding standards through EOF and use its Implementation Guidance Mode.

Problem and Project Commitment Gate

Complete this gate before implementation-detail discovery; it establishes the review basis but does not waive the Finding Proof, Mandatory Style Verification, Completion, or convergence gates.

  1. Reconstruct the problem and expected behavior from the PR, linked issue when present, official documentation, maintained contracts, current code, and tests.
  2. For a defect, trace the failing path to the violated contract and its maintained owner; for another PR type, establish the goal and responsibilities it must preserve.
  3. Trace the patch's actual mechanism and compare it with a repair or reuse path in that owner; record why the chosen boundary addresses the cause or accepted goal and what remains outside scope.
  4. Verify outcome-sensitive assumptions about external calls, dependency versions, configuration and lifecycle, including side effects and resource cost on already-correct supported paths, before accepting the direction.
  5. Classify the requested outcome as preserving an accepted contract or adding a project commitment such as new semantics, configuration, API or SPI, compatibility, topology, database, dialect, or cross-module support.
  6. For Apache ShardingSphere, establish that ShardingSphere owns the behavior and that official project positioning, maintained contracts, or an explicit public maintainer decision accepts every new commitment; for an authorized downstream repository, apply equivalent target-project evidence available within the user-authorized repository boundary.
  7. Identify the narrowest accepted user-visible behavior and compare it with the patch's public contract, shared abstractions, compatibility surface, documentation, and tests.
  8. Check whether the change creates precedent or consistency pressure beyond the accepted behavior; an exact existing behavior or special case does not authorize broader generalization.

An open or labeled issue, popularity, contributor effort, available code, passing tests, or a small diff do not establish project acceptance. When evidence disproves the problem, expected behavior, applicable project ownership, or an asserted accepted commitment, or when a new commitment still requires a maintainer decision, record a Needs Discussion condition. When the behavior is accepted but the patch adds unsupported generalization, public surface, parallel models, or abstractions without a real stable boundary, treat the excess as a finding candidate under the implementation rules; patch size or novelty alone is not evidence of overdesign. When a decisive acceptance or ownership fact is unavailable after every admissible route, apply the Review Incomplete Proof Gate instead of converting uncertainty into Needs Discussion.

Scope and Evidence

Read evidence-access.md and complete its GitHub Access Preflight before any GitHub request. It owns public-read


Content truncated.

When not to use it

  • →Personal projects without public artifacts
  • →Non-ShardingSphere repositories
  • →Tasks where evidence is purely private

Prerequisites

Access to Apache ShardingSphere PRs

Limitations

  • →Strict adherence to public artifact boundary
  • →Cannot incorporate private knowledge
  • →Technical complexity of database internals

How it compares

It is constrained to public-only evidence, ensuring feedback is immediately ready for communal review.

Compared to similar skills

review-pr side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
review-pr (this skill)25moNo flagsAdvanced
sync-data-relational11yNo flagsIntermediate
code-review09moNo flagsIntermediate
pr09moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry