CtrlK
BlogDocsLog inGet started
Tessl Logo

update-pr-description

Evaluate a PR's title and description against its actual implementation, then iteratively suggest and apply updates. Use when the user asks to check, fix, or update a PR title or description.

72

Quality

89%

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

86%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 tight, command-driven workflow with a clear sequence and an early-exit checkpoint plus iterative user confirmation. It would benefit from a fully resolved apply example and an explicit post-apply verification, but is otherwise strong for a simple skill.

Suggestions

Add a complete `gh pr edit` example with concrete `--title`/`--body` values rather than ellipsis placeholders to close the actionability gap.

Add an explicit post-apply verification step (e.g. re-running `gh pr view --json title,body` to confirm the change landed) to strengthen the workflow checkpoint.

Clarify the iterative-suggest loop's stopping condition (e.g. 'until the user accepts or declines further changes') so the feedback loop is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean — a numbered workflow with concrete `gh` commands and a short notes list — and assumes Claude's competence without explaining PR or git concepts, so every token earns its place.

5 / 5

Actionability

Provides concrete, runnable commands (`gh pr view <pr> --json title,body`, `gh pr edit <pr> --title ... --body ...`) for the core cases, but the apply step uses placeholders rather than a fully resolved copy-paste example, leaving a minor gap.

4 / 5

Workflow Clarity

Steps are clearly sequenced (resolve → gather → evaluate → report → suggest iteratively → apply) with an explicit stop checkpoint ('If not, stop here') and per-change user confirmation, but there is no explicit re-validation that the applied edit landed correctly, a minor checkpoint gap.

4 / 5

Progressive Disclosure

For a simple, single-purpose skill under 50 lines with no external references needed, the content is well organized into a Workflow section and a Notes section, satisfying the simple-skill exception for a top score.

5 / 5

Total

18

/

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, action-oriented, and explicitly pairs a clear 'what' with a concrete 'Use when' trigger clause. It is written in third person and avoids fluff; the only minor gap is slightly narrower trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Evaluate a PR's title and description against its actual implementation', 'iteratively suggest and apply updates' — covering the full evaluate/suggest/apply lifecycle, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both 'what' (evaluate title/description against implementation, suggest and apply updates) and 'when' ('Use when the user asks to check, fix, or update a PR title or description') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases like 'check, fix, or update a PR title or description', though synonyms like 'pull request' spelled out or 'body' as an alternative trigger term are absent, leaving minor gaps versus the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (PR title/description accuracy) with triggers tied to a specific user request and the `gh`-based PR workflow, leaving minimal overlap with other skills.

5 / 5

Total

19

/

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
storybookjs/storybook
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.