CtrlK
BlogDocsLog inGet started
Tessl Logo

gh-address-comments

Address actionable GitHub pull request review feedback. Use when the user wants to inspect unresolved review threads, requested changes, or inline review comments on a PR, then implement selected fixes. Use the GitHub app for PR metadata and flat comment reads, and use the bundled GraphQL script via `gh` whenever thread-level state, resolution status, or inline review context matters.

76

Quality

93%

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

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, concise, and actionable skill body that appropriately offloads detail to a real bundled script. The main gap is the absence of an explicit verification checkpoint in the fix-implementation workflow for what is effectively a batch operation.

Suggestions

Add an explicit validation/verification step to the Workflow (e.g., 'After implementing fixes, run the affected tests/build and confirm they pass before summarizing') to convert the batch fix operation into a validate -> fix -> retry loop.

In step 6, distinguish reporting supporting tests from actually running them: make verification a checkpoint that gates completion rather than just an item listed in the summary.

Clarify how to verify a single fix locally (e.g., reproduce the failing test or check the changed file compiles) so each selected thread has its own feedback loop before moving to the next.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and avoids explaining basic concepts; the opening paragraph lightly restates the description's connector-vs-gh rationale but each token still earns its place, so it clears the 'lean and efficient' anchor rather than dropping to the 'could be tightened' level.

3 / 3

Actionability

Gives concrete executable commands ('gh auth status', 'gh pr view --json number,url') and delegates thread-aware reads to a real bundled 'scripts/fetch_comments.py' with the fields it fetches; not score 2 because guidance is concrete and executable rather than pseudocode or abstract.

3 / 3

Workflow Clarity

A clear six-step sequence with a scope-confirmation checkpoint (step 4) is present, but implementing selected fixes is a batch operation and there is no explicit validation/verification checkpoint (e.g., run tests, verify build) before summarizing; per the rubric, batch operations missing validation cap this at 2 rather than 3.

2 / 3

Progressive Disclosure

The body is a concise overview organized into Workflow, Write Safety, and Fallback sections with a one-level-deep, clearly signaled reference to the real bundle file 'scripts/fetch_comments.py' (verified present); not score 2 because the structure and signaling are clean rather than weakly organized.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that states concrete capabilities, includes natural trigger terms, and gives an explicit 'Use when' clause. No weaknesses warranting suggestions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person ('Address actionable GitHub pull request review feedback', 'inspect unresolved review threads, requested changes, or inline review comments', 'implement selected fixes', 'fetch PR metadata and flat comment reads'), matching the multiple-specific-actions anchor; not score 2 because it goes well beyond naming a domain and a few actions.

3 / 3

Completeness

Explicitly answers what ('Address actionable... review feedback... implement selected fixes') and when ('Use when the user wants to inspect unresolved review threads, requested changes, or inline review comments on a PR'); not score 2 because the 'when' is an explicit trigger clause, not merely implied.

3 / 3

Trigger Term Quality

Natural terms a user would say appear throughout ('GitHub pull request review feedback', 'requested changes', 'inline review comments', 'PR'), giving good coverage; not score 2 because common variations are present rather than missing.

3 / 3

Distinctiveness Conflict Risk

A clear niche (GitHub PR review-comment handling) with distinct triggers unlikely to fire for unrelated skills; not score 2 because it is more specific than a generic 'works with PR files' overlap case.

3 / 3

Total

12

/

12

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
openai/plugins
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.