CtrlK
BlogDocsLog inGet started
Tessl Logo

review-pr

Review Apache ShardingSphere or user-authorized downstream pull requests and PR discussions from public or authorized repository evidence. Use for code-correctness or mergeability decisions, CI-focused review, root-cause and regression analysis, complete consolidated findings, copy-ready committer feedback, challenged findings, multi-round review, and formal review of local implementation candidates in the repository completion loop.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, gate-driven review workflow with strong progressive disclosure and clear sequencing including feedback loops. Its main weakness is conciseness — overlapping restatements across the style, completion, and decision contracts and some abstract prose could be consolidated.

Suggestions

Consolidate the overlapping rules repeated across the Mandatory Style Verification Gate, Completion Gate, and Formal Decision Contract into a single authoritative statement referenced by the others to cut redundancy.

Tighten the Canonical Assessment section by removing the abstract determinism prose ('Two reviews with the same effective candidate...') in favor of the concrete invariants that matter operationally.

Add one short worked example showing the end-to-end mapping from a sample finding through the gates to a final Formal Review block, to lift actionability from mostly-executable to fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is mostly lean directive prose that assumes Claude's competence (no beginner explanations of PRs or Checkstyle), but the Mandatory Style Verification Gate, Completion Gate, and Formal Decision Contract restate overlapping rules, and the Canonical Assessment section contains abstract restatement that could be tightened.

3 / 5

Actionability

It gives copy-ready commands ('scripts/build_review_inventory.py --format json', 'scripts/review_ledger.py validate-incomplete --ledger <ledger>', '--candidate-files <path>') and an exact output-format spec with precise headings and bold lines, but some abstract framing around contracts keeps it from being fully copy-paste ready across cases.

4 / 5

Workflow Clarity

The numbered 8-step Review Workflow is clearly sequenced with an explicit convergence feedback loop ('If it finds a new independent candidate, return to step 5') and multiple validation gates (Finding Proof Gate, Review Incomplete Proof Gate, Mandatory Style Verification Gate, Completion Gate).

5 / 5

Progressive Disclosure

The body is a clear overview with well-signaled one-level-deep references — [evidence-access.md](references/evidence-access.md), [high-risk-review.md](references/high-risk-review.md), [sql-parser-review.md](references/sql-parser-review.md), [review-corrections.md](references/review-corrections.md) — all of which exist as real files, with detailed material appropriately split out of SKILL.md.

5 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and clearly niche-scoped, explicitly stating both what the skill does and when to use it with concrete trigger phrases. It is written in correct third-person voice with strong natural keyword coverage.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions — 'code-correctness or mergeability decisions, CI-focused review, root-cause and regression analysis, complete consolidated findings, copy-ready committer feedback, challenged findings, multi-round review, and formal review of local implementation candidates' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

It explicitly answers both what ('Review Apache ShardingSphere or user-authorized downstream pull requests and PR discussions from public or user-authorized repository evidence') and when ('Use for code-correctness or mergeability decisions, CI-focused review, root-cause and regression analysis...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

It uses natural terms a reviewer would say ('pull requests', 'PR discussions', 'mergeability', 'CI-focused review', 'root-cause', 'regression analysis') including the PR/pull-request synonym pair, but a few colloquial variations are absent, keeping it just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

It targets a clear niche — Apache ShardingSphere or user-authorized downstream PR review — with distinct triggers and minimal overlap risk against generic review or coding skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 6 suspicious

Warning

Total

15

/

16

Passed

Repository
apache/shardingsphere
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.