CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

describe-pr

Generate comprehensive PR descriptions following repository templates

Quality

76%

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/describe_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 strongly actionable, well-sequenced workflow with concrete gh commands, explicit verification checkpoints, and error-recovery paths. Its main weaknesses are minor: a few motivational lines could be trimmed and the 'Important notes' section overlaps with the steps. The description frontmatter, not the body, is the skill's weak point.

DimensionReasoningScore

Conciseness

The body is command-driven and assumes Claude's competence (no explanations of git or PR concepts), with only minor trimmable lines such as 'Read the template carefully to understand all sections and requirements' and 'This helps reviewers understand the journey, not just the destination'. It is efficient with minor over-explanation, fitting the level-4 anchor rather than 5.

4 / 5

Actionability

Every step provides copy-paste-ready commands with exact flags (e.g., 'gh pr view --json url,number,title,state 2>/dev/null', 'gh pr diff {number}', 'gh pr edit {number} --body-file ...'), concrete file paths, and explicit checkbox formats ('- [x]' / '- [ ]'). Concrete commands cover the common cases including missing template, missing PR, and gh repo set-default errors.

5 / 5

Workflow Clarity

Steps 1-9 form a clear sequence with explicit validation checkpoints: step 3 detects and reads an existing description, step 6 runs verification commands with pass/fail handling ('If it passes, mark the checkbox as checked... If it fails, keep it unchecked and note what failed'), and step 4 includes error recovery for the missing-default-remote failure. This matches the level-5 anchor of explicit validation with feedback loops.

5 / 5

Progressive Disclosure

The body is well-sectioned (Steps, Important notes) and self-contained with no external bundle files to misnavigate. It is over 50 lines so the simple-skill 5 exception does not strictly apply, and the 'Important notes' section partially duplicates step content (e.g., 'Always attempt to run verification commands' restates step 6), leaving minor organization gaps consistent with the level-4 anchor.

4 / 5

Total

18

/

20

Passed

Description

53%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 states a clear, moderately specific purpose but entirely lacks a 'when to use' trigger clause, which caps completeness and limits trigger-term quality. It is distinct enough within the PR/git niche, though it could name more concrete actions and natural trigger phrases.

Suggestions

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

Include natural trigger variations such as 'pull request', 'describe a PR', and 'PR body' so the skill surfaces for common phrasings.

Name additional concrete actions to lift specificity, e.g., 'analyze the PR diff, run verification commands, and update the PR body from the repository template.'

DimensionReasoningScore

Specificity

The description names the domain ('PR descriptions') and one concrete action ('Generate'), with 'following repository templates' as a qualifier. It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' — it does not list several specific actions like analyzing diffs, running verification, or updating the PR, so it is not a 4.

3 / 5

Completeness

It has a clear 'what' ('Generate comprehensive PR descriptions following repository templates') but no 'Use when...' clause or equivalent trigger guidance. The judging guidelines explicitly cap completeness at 3 for a missing 'when' clause.

3 / 5

Trigger Term Quality

'PR descriptions' and 'repository templates' are relevant keywords a user might say, but common variations and synonyms ('pull request', 'describe a PR', 'PR body') are absent. This fits 'Some relevant keywords but missing common variations or synonyms'; it is not a 4 because coverage is thin rather than 'good with a few missing'.

3 / 5

Distinctiveness Conflict Risk

'PR descriptions' is a distinct niche with only minor overlap risk against closely related skills (e.g., commit-message generation). It is not a 5 because without explicit trigger phrases, a generic 'generate descriptions' request could plausibly match other skills.

4 / 5

Total

13

/

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

parcadei/Continuous-Claude-v3

Path

.claude/skills/describe_pr/SKILL.md

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.