address-github-comments

Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-address-github-comments/SKILL.md

Quality

Content

53%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 body is a compact, logically sequenced workflow with authentic gh commands, but it is capped by execution gaps: the respond/resolve step's command does not actually resolve review threads, fixes are never validated before the 'Addressed' reply is posted, and circular filler sections dilute an otherwise lean document.

Suggestions

Replace the misleading `gh pr comment <PR_NUMBER>` step with the actual thread-resolution flow (e.g. `gh api` GraphQL mutation to resolve review threads, or `gh pr review --reply`) and show how to obtain the PR number.

Add a validation checkpoint before responding: run tests/build, confirm the fix addresses the comment, and only then reply and resolve — the batch 'address all comments' flow currently has no feedback loop.

Delete the circular "When to Use" and boilerplate "Limitations" sections and either point to the concrete custom script path or drop the vague reference to it.

Dimension	Reasoning	Score
Conciseness	Concrete commands are tight, but padded filler remains: "This skill is applicable to execute the workflow or actions described in the overview" is circular, and the generic "Limitations" section ("Do not treat the output as a substitute for... expert review") adds no skill-specific value. This matches anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened'), not anchor 4 which requires only minor trimmable instances.	3 / 5
Actionability	Real commands exist ("gh auth status", "gh pr view --comments", "gh pr comment <PR_NUMBER> --body \"Addressed in latest commit.\""), but step 3 gives no guidance for applying fixes, <PR_NUMBER> is never resolved, and the shown comment command posts a general PR comment rather than responding to or resolving the review threads step 4 claims. Anchor 3 ('some concrete guidance but incomplete; missing key details') fits; not anchor 4 because a core step's command does not perform the described action.	3 / 5
Workflow Clarity	Four sequenced steps exist with one checkpoint ("Wait for user confirmation on which comments to address first"), but there is no validation before replying "Addressed in latest commit" — no verification that fixes work (tests/build) and no confirmation the thread was actually resolved. Because addressing many comments is a batch operation, the batch-validation cap holds workflow clarity at 3 even though the sequence itself is clear.	3 / 5
Progressive Disclosure	The skill has no bundle files and its ~60-line body is organized into clear sections (Prerequisites, numbered Workflow, Common Mistakes), fitting anchor 4 ('good structure; most content appropriately placed; minor organization gaps'). It misses anchor 5 due to the dangling "Or use a custom script if available to list threads" — an unsignaled, pathless reference — and the filler sections that add no navigational value.	4 / 5
	Total	13 / 20 Passed

Description

65%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 has a clear, explicit trigger clause and a well-scoped niche, with good natural trigger terms. Its main weakness is a thin 'what': it names the task and tool but lists no concrete capabilities (reply to threads, resolve reviews, apply fixes), leaving it at the generic-action level.

Suggestions

Enumerate the concrete capabilities, e.g. 'Fetch PR review threads, apply fixes, reply to and resolve comments, and post follow-up comments using the gh CLI.'

Add the natural synonyms users actually say — 'PR feedback', 'respond to review comments', 'resolve review threads' — to strengthen trigger coverage.

Split the single merged sentence into a what-clause plus a distinct when-clause so both are independently explicit.

Dimension	Reasoning	Score
Specificity	"address review or issue comments ... using the gh CLI" names the domain and tool but the action is generic; it never states concrete actions like replying to threads, resolving review comments, or pushing fixes, matching anchor 2 ('names the domain but actions are minimal or generic'). It falls short of anchor 3 because 'address comments' is a single abstract action rather than 1-2 concrete ones.	2 / 5
Completeness	Both parts are present in one sentence: what ("address review or issue comments ... using the gh CLI") and an explicit "Use when you need to..." trigger clause, matching anchor 4 ('has both what and when; one could be more explicit'). Not anchor 5 because the what is a single thin clause with no concrete capability list; not anchor 3 because the when is explicit, not merely implied.	4 / 5
Trigger Term Quality	Natural terms users would say are present: "review", "issue comments", "GitHub", "Pull Request", "gh CLI". Anchor 4 ('good keyword coverage; a few natural terms missing') fits because common variations like "PR feedback", "respond to comments", or "resolve review comments" are absent; it exceeds anchor 3 since coverage goes beyond a single generic keyword.	4 / 5
Distinctiveness Conflict Risk	The niche is clear — addressing comments on an open GitHub PR via gh — and unlikely to trigger for unrelated skills, fitting anchor 4 ('mostly distinct; minor overlap risk'). It stops short of anchor 5 only because it could softly overlap with general code-review or reviewer-response skills given the generic word 'review'.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-address-github-comments/SKILL.md
Commit: 7390864

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.