CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-respond

Respond to all pending review comments on the current PR — fetch comments, apply fixes, verify accuracy, test, commit, and reply. Use when addressing Copilot reviews, GitHub PR reviews, or any batch of review feedback.

Quality

87%

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

75%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 well-constructed batch workflow: concrete commands, explicit tool-routing policy, and a real pre-commit verification gate with tests. The main gaps are unfilled placeholders in the gh/git commands and the absence of an explicit fix-and-re-verify loop after a failed check.

Suggestions

Add an explicit error-recovery loop to Step 5: after each verification check that fails, state 'fix the change and re-run the check before proceeding' (and re-run tests after fixes), so the workflow_clarity feedback loop is closed.

Make the commands copy-paste ready by resolving placeholders at runtime — e.g., instruct 'detect owner/repo with `gh repo view --json nameWithOwner`' and substitute the actual PR number and comment_id into the fetch/reply gh api calls.

Trim the rationale sentences (e.g., "Reviewer claims are not always correct; library behavior can change between versions") to one short clause, keeping only the operational rule, to push conciseness toward the lean anchor.

DimensionReasoningScore

Conciseness

The body is lean and dominated by project-specific routing policy Claude would not know (Serena over bare Read, Context7 before agreeing with a reviewer), with commands rather than prose. Not 5 because a few rationale sentences — "Reviewer claims are not always correct; library behavior can change between versions", "confirms the blast radius across the codebase" — exceed the operational minimum.

4 / 5

Actionability

Provides real executable commands with specific filters (`gh api … --jq '.[] | select(.position != null)…'`, `cargo t {command_name} -F all_features`, the reply endpoint), but `{owner}/{repo}`, `<changed files>`, and `{comment_id}` remain unfilled placeholders, so not every block is copy-paste ready.

4 / 5

Workflow Clarity

Nine clearly sequenced steps with an explicit pre-commit verification gate ("**Before committing**, verify accuracy of all changes") satisfy the batch-operation validation requirement. Not 5 because the gate lists checks without an error-recovery loop — nothing instructs what to do when a verification check or test fails.

4 / 5

Progressive Disclosure

No bundle files exist, so all content lives inline in a well-sectioned ~90-line body. Structure is good and nothing reference-like (API tables, long examples) needs extraction, but the skill exceeds the 50-line simple-skill exception and uses no reference splitting, so the appropriately-placed anchor at 4 fits best.

4 / 5

Total

16

/

20

Passed

Description

96%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 description: it enumerates the concrete actions of the workflow, uses natural trigger phrasing including the Copilot-specific case, and pairs an explicit what with an explicit when. The only minor risk is overlap with skills that create reviews rather than respond to them.

DimensionReasoningScore

Specificity

Lists six concrete actions spanning the full lifecycle — "fetch comments, apply fixes, verify accuracy, test, commit, and reply" — which matches the comprehensive-coverage anchor; score 4 would undercount since the workflow steps are enumerated end-to-end.

5 / 5

Completeness

Explicitly answers both what ("Respond to all pending review comments… fetch comments, apply fixes, verify accuracy, test, commit, and reply") and when ("Use when addressing Copilot reviews, GitHub PR reviews, or any batch of review feedback") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers the natural terms users would say — "Copilot reviews", "GitHub PR reviews", "batch of review feedback", "PR", "review comments" — including both the tool-specific name and generic synonyms, satisfying the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

The niche — responding to received review feedback rather than performing reviews — is distinct and triggered by specific phrases, but "review" wording creates minor overlap risk with sibling code-review/PR-review skills; not 5 because that adjacency remains.

4 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

dathere/qsv

Path

.claude/skills/review-respond/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.