CtrlK
BlogDocsLog inGet started
Tessl Logo

github-pr-comments

Resolve inline code review comments on a GitHub PR. Use when asked to "resolve review comments", "address PR feedback", "fix PR comments", or "work through review comments". Fetches every inline comment with its surrounding code context, then applies each change systematically.

74

Quality

91%

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

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, well-sequenced workflow with concrete commands, validation, and a feedback loop. The main weaknesses are a script path in the body that does not match the bundle location and a Rust-specific verify command that assumes the project type.

Suggestions

Align the fetch command path with the actual bundle location (e.g. 'bash scripts/pr-comments.sh [PR_NUMBER]') so the command is copy-paste ready.

Generalize the verify step beyond Rust ('cargo check && cargo nextest run') or state the project-type assumption explicitly, since the skill targets any GitHub PR.

Consider noting that the todo list should be re-checked after edits to confirm every comment thread is resolved, strengthening the batch-operation checklist.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: numbered sections, concrete commands, and no padding about what PR comments or diffs are; every line earns its place.

5 / 5

Actionability

Provides concrete, mostly copy-paste-ready commands and clear handling rules for both comment types, but the fetch command path ('.forge/skills/resolve-code/scripts/pr-comments.sh') does not match the bundled location ('scripts/pr-comments.sh') and the verify step hardcodes 'cargo', creating minor gaps.

4 / 5

Workflow Clarity

A clearly sequenced four-step workflow with an explicit validation checkpoint ('cargo check && cargo nextest run') and a feedback loop ('Fix any errors before marking the task complete'), plus a per-comment todo checklist for the batch operation.

5 / 5

Progressive Disclosure

Well-organized numbered sections under 50 lines with one real bundled script, but the referenced invocation path does not match the actual bundle structure, a minor organization gap.

4 / 5

Total

18

/

20

Passed

Description

95%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 strong, third-person description that clearly states what the skill does and when to invoke it, with rich natural trigger phrases. The only minor gap is action coverage breadth, which stops just short of fully comprehensive.

DimensionReasoningScore

Specificity

Names the domain ('GitHub PR', 'inline code review comments') and several concrete actions ('Fetches every inline comment with its surrounding code context', 'applies each change systematically'), with only minor coverage gaps versus the comprehensive anchor.

4 / 5

Completeness

Explicitly answers both what (resolve inline comments, fetch with context, apply changes) and when (a 'Use when...' clause with concrete trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Quotes four natural user phrases — 'resolve review comments', 'address PR feedback', 'fix PR comments', 'work through review comments' — giving comprehensive synonym coverage of how users actually request this.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (inline GitHub PR review comments) with distinct triggers, so it is unlikely to fire for unrelated 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
tailcallhq/forgecode
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.