CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-description

Draft or update a GitHub PR description that explains the problem, changed behavior, and review concerns in plain language.

62

Quality

73%

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/pr-description/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.

A tight, highly actionable instruction skill: a concrete workflow with built-in validation steps, a complete worked example, and specific measurable targets. The only notable weaknesses are mild redundancy between the body, the Voice section, and the closing checklist, and no offloading of the longer example material to reference files.

DimensionReasoningScore

Conciseness

The body teaches non-obvious house rules (format, labels, length, evidence) without padding or explaining concepts Claude already knows. Minor trim opportunities: the 'Voice' section partly restates how Claude already writes ('plain words, contractions, and short connected sentences'), and the closing checklist duplicates rules stated in the body.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: explicit argument syntax with invocation examples ('/pr-description 3534 --fixes 123,456'), a complete worked example PR description, and concrete numeric targets ('under 200 words', '3 to 6 labeled bullets'). Per the rubric's scoring note, the absence of code is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

A clear 5-step sequence with explicit validation checkpoints: step 2 checks the existing description before rewriting, step 5 re-reads the draft without the diff to catch missing context, and a final self-check checklist closes the loop. This is not a destructive or batch operation, so no cap applies.

5 / 5

Progressive Disclosure

Single-file skill with no bundle files; sections are clearly headed (Arguments, Instructions, Format, Length and evidence, Voice, Checklist) and the worked example is properly fenced and labeled. Not 5: the skill exceeds 50 lines, and the long worked example plus detailed section guidance could arguably live in a reference file, though splitting a cohesive style guide is a judgment call.

4 / 5

Total

18

/

20

Passed

Description

58%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 clear, concrete 'what' with a distinct GitHub-PR niche, but the description lacks any 'when to use it' trigger clause and natural keyword variations like 'pull request'. Adding a Use-when clause with common user phrasings would lift completeness and trigger quality substantially.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user asks to draft, update, or write a PR description or pull request body.'

Include natural synonyms such as 'pull request', 'PR body', or 'PR write-up' alongside 'PR description' so the description matches varied user phrasings.

Optionally mention checking/improving an existing PR description, since that is a distinct capability the body supports.

DimensionReasoningScore

Specificity

"Draft or update a GitHub PR description" names concrete actions, and "explains the problem, changed behavior, and review concerns" enumerates the specific content the output covers. Not 5: it omits capabilities the body covers (checking/rewriting an existing description, linking closing issues).

4 / 5

Completeness

The 'what' is clear and specific (draft or update a PR description explaining problem, changed behavior, review concerns), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

"GitHub PR description" is a phrase users would naturally say, but common variations and synonyms ("pull request", "PR body", "draft a PR") are missing. Fits the anchor 'some relevant keywords but missing common variations or synonyms' better than the sparse anchor at 2 or the good-coverage anchor at 4.

3 / 5

Distinctiveness Conflict Risk

"GitHub PR description" carves out a clear niche distinct from general writing or commit-message skills. Not 5: no trigger phrases reinforce the niche, leaving minor overlap risk with adjacent Git-writing skills.

4 / 5

Total

14

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pipecat-ai/pipecat
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.