Name: apm-strategy
Rating: 61.6 (1 reviews)
Author: microsoft

apm-strategy

Activate for changes to project positioning, release communication, community-facing artifacts, or breaking-change decisions in microsoft/apm. Triggers on README, MANIFESTO, PRD, CHANGELOG, release workflows, and issue templates.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.apm/skills/apm-strategy/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A token-efficient, well-structured instruction-only skill with a clean single reference, but it lacks executable gh CLI specifics and any validation checkpoint for its review workflow.

Suggestions

Add the concrete gh commands behind 'Ground every claim in gh CLI evidence' (e.g. `gh api repos/:owner/:repo` for stars/issues, `gh release list`, `gh pr list --state all`) so guidance is copy-paste ready.

Include a short verification step, such as confirming every breaking change has both a CHANGELOG entry and a migration note before approving, to add an explicit feedback loop to the review workflow.

Provide one minimal example of a one-line migration note so the 'ships with a one-line migration note' rule is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero padding — it never explains concepts Claude already knows and every line ('Ground every claim in gh CLI evidence', 'Every breaking change ships with a CHANGELOG.md entry and a one-line migration note') earns its place, matching the 'Lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	Rules are concrete directives, but 'Ground every claim in gh CLI evidence (stars, issues, PRs, releases, traffic, contributors)' names the evidence sources without giving the actual gh commands to fetch them, leaving key executable details missing as in the 'Some concrete guidance but incomplete; missing key details' anchor.	2 / 3
Workflow Clarity	'When to activate' and 'Key rules' are organized lists but not a sequenced process, and there is no validation/verification checkpoint for a reviewer that can block PRs; this matches 'Steps listed but validation gaps; checkpoints missing or implicit' rather than a clear validated sequence.	2 / 3
Progressive Disclosure	Under 50 lines with well-organized sections ('When to activate', 'Key rules') and a single clearly-signaled one-level reference ([APM CEO persona](../../agents/apm-ceo.agent.md)); per the simple-skill note, this satisfies the 'Clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	10 / 12 Passed

Description

72%Weight 40%Scale 1-3

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, trigger-rich description that is clearly distinguishable and uses natural terms, but it over-indexes on when to activate and under-specifies what the skill actually does once activated.

Suggestions

Add an explicit capability clause naming the action the skill performs, e.g. 'Reviews and critiques strategic positioning, release comms, and breaking-change decisions for microsoft/apm' before the trigger clause.

Lead with the 'what' (the APM CEO persona strategic review) so both what and when are unambiguous, mirroring the 'Extract text... Use when...' pattern.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ('project positioning, release communication, community-facing artifacts, or breaking-change decisions in microsoft/apm') and specific trigger files, but it states when to activate rather than the concrete actions the skill performs, so it stops short of the multi-action 'Lists multiple specific concrete actions' anchor.	2 / 3
Completeness	It has strong explicit 'when' guidance ('Triggers on...', 'Activate for...'), but the 'what does this do' side is only implied — it never states the capability (strategic review via the APM CEO persona), so it sits at the 'Has what, but when is missing or only implied' level inverted (strong when, weak what) rather than clearly answering both.	2 / 3
Trigger Term Quality	It lists natural terms a user would actually say — 'README, MANIFESTO, PRD, CHANGELOG, release workflows, and issue templates' — giving good coverage of concrete file and concept names, matching the 'Good coverage of natural terms users would say' anchor.	3 / 3
Distinctiveness Conflict Risk	It is scoped to a single repo ('microsoft/apm') and distinctive artifacts (MANIFESTO, PRD, APPROACH), giving it a clear niche unlikely to conflict with other skills, matching the 'Clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: .apm/skills/apm-strategy/SKILL.md
Commit: 634f7b6

Reviewed: 8 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.