CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autopilot-comment

Use this skill to post or patch ONE GitHub comment for a microsoft/apm autopilot run. It owns public vs debug body assembly and the AI disclaimer footer. Never labels, assigns, requests reviewers, or merges. Autopilot skills that write comments must load this skill and must not call gh comment APIs themselves.

69

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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-structured, highly actionable instruction skill with concrete gh commands, explicit fail-closed validation checkpoints, and clean sectioning. Its only minor weakness is light redundancy between the rules and the Hard nos list.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, but the 'Hard nos' section repeats prohibitions already stated in the activation rules and description, adding minor redundancy.

4 / 5

Actionability

Provides copy-paste-ready commands ('gh issue comment <target> --body-file ...', 'gh pr comment', 'gh api -X PATCH ...'), an exact footer template, and a fully specified activation card covering the common post/patch cases.

5 / 5

Workflow Clarity

Clear sequence (Activation card -> Assemble -> Write -> Exit receipt) with explicit validation checkpoints ('Missing field -> stop', 'Mismatch -> stop', fail-closed 'unknown -> unattended') and a dry-run path via 'write: off'.

5 / 5

Progressive Disclosure

Self-contained single-purpose skill with no bundle files needed; content is well-organized into clearly labeled sections (Activation card, Assemble, Write, Hard nos) with no nested references.

5 / 5

Total

19

/

20

Passed

Description

78%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 tightly scoped, concrete description that clearly defines a single responsibility and when to load it. It is strong on distinctiveness and concrete actions but slightly less natural as user-facing trigger phrasing.

Suggestions

Add a user-facing 'Use when...' phrasing or natural synonyms (e.g. 'GitHub comment', 'PR comment', 'review comment') so the trigger reads as something a user would actually say.

Surface the most common trigger scenarios explicitly (e.g. 'Use when an autopilot run needs to publish or update a comment on a microsoft/apm issue or pull request') to strengthen the 'when' clause beyond the skill-to-skill directive.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'post or patch ONE GitHub comment', 'owns public vs debug body assembly and the AI disclaimer footer', and explicit prohibitions (labels/assigns/reviewers/merge) — but coverage is narrow to a single comment-writing task rather than a broad action set.

4 / 5

Completeness

Clearly answers 'what' (post/patch a comment, assemble body and footer) and provides an explicit 'when' clause ('Autopilot skills that write comments must load this skill'), but the trigger guidance is programmatic and could be more user-facing.

4 / 5

Trigger Term Quality

Includes natural domain terms like 'GitHub comment', 'post or patch', and 'autopilot run' that fit the niche, though it lacks synonym/extension variations and is framed for skill-to-skill invocation rather than user phrasing.

4 / 5

Distinctiveness Conflict Risk

Scoped tightly to microsoft/apm autopilot comment writing with explicit ownership ('must not call gh comment APIs themselves'), giving it a clear niche with minimal conflict risk.

5 / 5

Total

17

/

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

microsoft/apm

Path

.agents/skills/autopilot-comment/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.