CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autopilot-issue-accept

Use this skill to accept ONE microsoft/apm issue with a declared scope. The canvas Accept button, or a maintainer asking to accept an issue, starts it. Draft only from the latest triage proposed scope, get exact-text approval in this chat from a GOVERNANCE roster human, post that comment as that human, then add status/accepted. Do not invent scope, do not accept pull requests, and do not implement the issue.

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

The canonical home for this skill is autopilot-issue-accept in microsoft/apm

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 lean, highly disciplined governance workflow that is almost fully executable, with exceptional validation gating and stop-condition handling for a destructive public action. The only weaknesses are a missing command for the comment re-read verification step and unexplained environment variables, plus a single-file layout that inlines all spec blocks.

DimensionReasoningScore

Conciseness

The body is telegraphic and entirely instructional — 'Missing field -> stop.', 'If that brief is missing, stop.', 'ASCII only.' — with zero concept explanation or padding; every token earns its place.

5 / 5

Actionability

Provides exact executable commands ('gh issue comment "$ISSUE" --repo microsoft/apm --body-file "$BODY"', 'node scripts/governance/eligibility.cjs ...') and exact templates for the card, receipt, and comment fence, but the re-read verification step lists conditions without a command and $ISSUE/$BODY/$COMMENT_URL are never set up. These minor gaps keep it below the fully copy-paste-ready 5 anchor.

4 / 5

Workflow Clarity

The sequence (activation card, draft, chat approval, identity check, post, re-read, eligibility tool, label) is explicit with validation checkpoints and stop conditions at every failure point ('Require state: record-present', 'do not label', 'Any other token, bot, or login -> stop'), matching the explicit-validation anchor.

5 / 5

Progressive Disclosure

Well-organized sections (Activation card, Draft, Chat approval, Identity, Post/re-read/label) with all content needed at runtime appropriately inline and no buried references, but the ~170-line body inlines three full spec blocks in a single file with no bundle split, so it fits 'good structure, minor organization gaps' rather than the ideal split.

4 / 5

Total

18

/

20

Passed

Description

92%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 that states a concrete multi-step workflow, explicit trigger conditions, and clear negative boundaries in third person without padding. Its only shortcoming is trigger-term coverage that lacks natural synonyms beyond the core 'accept' phrasing.

DimensionReasoningScore

Specificity

The description lists the complete concrete action chain — 'Draft only from the latest triage proposed scope, get exact-text approval ... post that comment as that human, then add status/accepted' — plus three explicit exclusions ('do not invent scope, do not accept pull requests, and do not implement the issue'), giving comprehensive coverage with no gaps.

5 / 5

Completeness

It clearly answers both 'what' (draft from triage scope, get exact-text approval, post as that human, add status/accepted) and 'when' ('The canvas Accept button, or a maintainer asking to accept an issue, starts it') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Explicit natural triggers are present ('The canvas Accept button, or a maintainer asking to accept an issue, starts it', 'status/accepted'), but a few natural variations users might say (e.g., 'approve an issue', 'take this issue') are missing, so it stops short of the synonym-comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

A clear niche — accepting exactly one microsoft/apm issue under GOVERNANCE roster approval — with explicit fences against adjacent skills ('do not accept pull requests', 'do not implement the issue'), so conflict risk is minimal.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/governance/eligibility.cjs), 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

microsoft/apm

Path

packages/autopilot/autopilot-issue-accept/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.