CtrlK
BlogDocsLog inGet started
Tessl Logo

autopilot-issue-delivery-scheduler

Use this skill to queue maintainer-accepted microsoft/apm issues (`status/accepted`) and fan them out through an isolated pool (default 2) of autopilot-issue-delivery-worker sessions. Any accepted type is eligible. Advisory `triage/recommended` is not authorization. Does not triage. Does not review PRs. Works in a local session, Copilot App automation, Cloud Agent, Remote Agent, or Agentic Workflow.

59

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/autopilot-issue-delivery-scheduler/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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, actionable governance skill with concrete commands, templates, and validation gates, but it carries moderate redundancy and runs a batch fan-out without an explicit result-verification feedback loop. Resolving one unbundled script reference would round out its progressive disclosure.

Suggestions

Consolidate the repeated 'does not triage / does not review PRs' rule and the Hard nos section so each constraint appears once; cross-reference from Hard nos instead of restating Selection and Fan-out rules.

Add an explicit worker-result verification step in the Procedure (e.g., collect each slot's PR/exit status, re-validate eligibility before reporting, and define a retry-or-escalate path on worker failure) to give the batch fan-out a validate->fix->retry feedback loop.

Either bundle scripts/governance/eligibility.cjs or reword the reference so it does not point to a file absent from the skill bundle, keeping one-level-deep references resolvable.

DimensionReasoningScore

Conciseness

Lean prose that assumes Claude's competence, but 'does not triage / does not review PRs' is repeated in three places and the 'Hard nos' section largely duplicates Selection and Fan-out rules, so it could be tightened.

3 / 5

Actionability

Concrete, specific guidance including 'gh issue list' on status/accepted, an exact session name format, mandatory table columns, and fill-in activation/exit templates, with minor gaps such as the abstract 'Probe worker-code on disk' step and a referenced unbundled script.

4 / 5

Workflow Clarity

A clearly sequenced Procedure with validation gates ('Missing sibling -> stop', 'Missing table...-> stop. Do not spawn.'), but as a batch fan-out operation it lacks an explicit worker-result verification or validate->fix->retry feedback loop, capping it at 3.

3 / 5

Progressive Disclosure

Well-organized sections with one clearly-signaled one-level-deep reference to the real bundled assets/fan-out-pool.md, but scripts/governance/eligibility.cjs is referenced while no scripts/ directory exists in the bundle.

4 / 5

Total

14

/

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 strong, specific description with a clear trigger, concrete actions, and excellent boundary discipline that minimizes conflict with sibling scheduler skills. The main gap is the absence of explicit 'Use when...' user-facing trigger phrases, which keeps completeness and trigger_term_quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Names concrete actions ('queue maintainer-accepted microsoft/apm issues' and 'fan them out through an isolated pool (default 2) of autopilot-issue-delivery-worker sessions') plus boundary statements, but only two core verbs with negations rather than comprehensive multi-action coverage.

4 / 5

Completeness

Clear 'what' (queue and fan out accepted issues) and 'when' via the 'Use this skill to queue maintainer-accepted...issues' trigger guidance, but the 'when' lacks explicit concrete user trigger phrases.

4 / 5

Trigger Term Quality

Good domain keyword coverage ('queue', 'accepted issues', 'fan out', 'delivery workers', 'status/accepted') with a clear 'Use this skill to' trigger, though jargon-heavy and missing some natural synonyms.

4 / 5

Distinctiveness Conflict Risk

Clear niche with explicit boundary statements ('Does not triage. Does not review PRs.') and isolation from sibling schedulers, yielding minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 1 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
microsoft/apm
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.