CtrlK
BlogDocsLog inGet started
Tessl Logo

review-pr

Review CausalPy pull requests end-to-end by classifying PR type, checking branch freshness, mergeability, remote CI, correctness, security, tests, docs, and maintainer concerns. Use when asked to review a PR, assess a branch before merge, summarize PR risks, or request changes.

67

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/review-pr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A well-structured, actionable review workflow that assumes Claude's competence and supplies concrete commands, checklists, and an output template. Its main defect is that the body leans heavily on a resources/ bundle (workflow, per-PR-type checklists, patterns) that is not actually present, undermining both actionability and progressive disclosure.

Suggestions

Ship the referenced resources/ files (workflow.md, the pr-type-*.md checklists, code-patterns.md, review-patterns.md) or inline the essential parts so the skill is self-contained when the bundle is absent.

Tighten the 'Review Stance' prose to directive bullets so every token is instructional rather than motivational.

Confirm the full workflow lives somewhere reachable; if resources/workflow.md is the canonical sequence, either include it or fold its steps into the Intake section to remove the broken pointer.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no explanations of what a PR or CI is) and is densely instructional, but a few elaborative sentences in 'Review Stance' ('passing CI is evidence, not the conclusion') could be trimmed without losing the guidance.

4 / 5

Actionability

Concrete commands and targets are given throughout ('$CONDA_EXE run -n CausalPy <command>', 'gh pr checks', 'prek run --all-files', read 'AGENTS.md'/'ARCHITECTURE.md') plus a copy-ready output template, but the deferred resource files do not exist in the bundle, leaving a gap in executable guidance.

4 / 5

Workflow Clarity

A clear 7-step Intake sequence, a classification step, and a Universal Checks checklist provide good sequencing with checkpoints ('Verify contributor claims... before accepting them', 'Do not report no findings until these probes...'), but the 'full workflow' is deferred to a missing resources/workflow.md, leaving minor validation/sequencing gaps.

4 / 5

Progressive Disclosure

The in-document structure is well organized with clearly signaled one-level references (resources/workflow.md, pr-type-*.md, code-patterns.md, etc.), but none of the referenced files exist in the bundle, so the disclosure chain resolves to nothing and the promised detailed material is unavailable.

3 / 5

Total

15

/

20

Passed

Description

88%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.

A strong, specific description that clearly pairs capability with explicit 'Use when' triggers and a CausalPy-scoped niche. The only weak spot is that the trigger terms, while natural, are not themselves distinctive from a generic PR-review skill.

DimensionReasoningScore

Specificity

The description enumerates many concrete review actions — 'classifying PR type, checking branch freshness, mergeability, remote CI, correctness, security, tests, docs, and maintainer concerns' — giving comprehensive coverage rather than a single generic verb.

5 / 5

Completeness

It explicitly states both what ('Review CausalPy pull requests end-to-end by...') and when ('Use when asked to review a PR, assess a branch before merge, summarize PR risks, or request changes'), matching the anchor-5 pattern of concrete trigger phrases paired with a clear capability statement.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ('review a PR', 'assess a branch before merge', 'summarize PR risks', 'request changes'), but coverage stops short of synonyms (e.g. 'merge readiness') and there are no file-extension-style variants, so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

The 'CausalPy' qualifier carves a clear niche, but the trigger phrases themselves ('review a PR', 'request changes') are generic PR-review language that could overlap with a general code-review skill, leaving minor overlap risk.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pymc-labs/CausalPy
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.