CtrlK
BlogDocsLog inGet started
Tessl Logo

review-pr

Analyze a GitHub pull request including diff, comments, related issues, and local code context

64

Quality

77%

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 ./.claude/skills/review-pr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 tightly written, highly actionable PR-review workflow with concrete gh/git/python commands, explicit validation checkpoints, and good sectioning. Its one weakness is progressive disclosure: the body references identifier-normalization.md, but no such bundle file exists, so the link dangles.

Suggestions

Add the missing identifier-normalization.md reference file (under references/ or alongside SKILL.md) so the trigger-gated link resolves, or remove the link if the guidance is inlined.

Tighten the dependency-category explanation in step 3 (the four-bullet breakdown of main/optional/dev/merge categories) to reduce token weight.

Confirm the referenced script path tools/check_dependency_changes.py exists in the target repo, or note it as repo-specific so the command is not mistaken for a bundled asset.

DimensionReasoningScore

Conciseness

The body is lean procedural instruction with concrete commands and no padding of concepts Claude already knows; a few explanatory passages (e.g. the dependency-category breakdown) could be trimmed further.

4 / 5

Actionability

Provides copy-paste-ready, fully-specified commands throughout (e.g. `gh pr view PR_ID --json title,body,...`, `python tools/check_dependency_changes.py origin/devel`) with documented exit-code semantics covering the common cases.

5 / 5

Workflow Clarity

A clearly numbered 9-step sequence with an explicit worktree-cwd validation feedback loop, conditional branching (skip if pyproject.toml not in diff), and a test-scenario checklist before evaluation.

5 / 5

Progressive Disclosure

Well-sectioned body with a clearly signaled one-level-deep reference gated on explicit diff triggers, but the referenced identifier-normalization.md file is not present in the bundle, which breaks navigation.

4 / 5

Total

18

/

20

Passed

Description

66%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 clearly states what the skill does and names several concrete review dimensions, but it omits any "when to use it" trigger guidance and lacks synonym coverage, which together cap completeness and trigger-term quality. It is third-person and reasonably distinct from unrelated skills.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers (e.g. 'Use when the user asks to review a pull request / PR, check a PR diff, or assess code changes').

Include common synonyms and the file/URL form factor (e.g. 'pull request', 'PR', 'code review', 'diff', 'PR URL or number') to broaden trigger-term coverage.

Consider naming a couple of concrete output actions (e.g. 'produce a structured review with verdict and required fixes') to push specificity toward comprehensive.

DimensionReasoningScore

Specificity

Names the PR-review domain and lists several concrete facets ("diff, comments, related issues, and local code context"), but frames them under a single "Analyze" verb rather than multiple distinct actions, so it stops short of comprehensive.

4 / 5

Completeness

The "what" is clear and specific, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes natural terms users would say ("GitHub pull request", "diff", "comments", "related issues") but misses common synonyms such as "PR", "code review", or "code changes".

4 / 5

Distinctiveness Conflict Risk

The PR-review niche is mostly distinct, with only minor overlap risk against general code-review or git-diff skills; lacks the explicit distinct triggers needed for a 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
dlt-hub/dlt
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.