pm-soul

Use when preserving product intent, acceptance criteria, decision memory, open loops, roadmap context, or the product-manager continuity layer of an agent team.

Quality

82%

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

Quality

Content

86%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 tight, well-structured instruction skill that says exactly what to read, extract, emit, and return without wasted tokens. The only soft spot is step 3 ('Connect sitemap changes to product intent'), which is more abstract than the other concrete steps.

Suggestions

Make step 3 more actionable: specify what 'connect' produces (e.g. 'Note drift between sitemap changes and the recorded product intent under drift_risks').

Add a light validation checkpoint, e.g. 'Confirm extracted acceptance criteria and open loops are non-empty before returning; note gaps in drift_risks.'

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; every line carries actionable content.	5 / 5
Actionability	Concrete guidance with specific file path ('.agentlas/project-soul-memory.md'), explicit items to extract, and concrete output fields; 'Connect sitemap changes to product intent' is slightly less actionable than the rest.	4 / 5
Workflow Clarity	A clear numbered sequence (read, extract, connect, emit) plus a guardrail ('instead of silently rewriting shared memory'), but no explicit validation checkpoint; acceptable since the task is read/extract/emit rather than destructive.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references, organized into well-labeled 'Procedure' and 'Output' sections — meets the simple-skill exception for a top score.	5 / 5
	Total	18 / 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 well-targeted description with an explicit 'Use when' trigger and concrete PM-domain terms, distinguishable from other skills. Its main weakness is that the capability ('what') and the trigger ('when') are expressed in a single merged clause rather than separate what/when statements.

Suggestions

Separate the 'what' from the 'when': lead with the capability ('Preserves product intent, acceptance criteria, decision memory, open loops, and roadmap context for an agent team.'), then the trigger ('Use when ...').

Add a couple of common synonyms or looser phrasings a user might naturally say (e.g. 'product decisions', 'PM context', 'project goals') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete items it preserves ('product intent, acceptance criteria, decision memory, open loops, roadmap context') with the 'preserving' action, though the action verb is repeated rather than varied.	4 / 5
Completeness	Has an explicit 'Use when...' trigger and the what ('preserving...') but the what and when collapse into a single clause, so the what could be more distinctly stated.	4 / 5
Trigger Term Quality	Includes natural PM phrases ('product intent', 'acceptance criteria', 'roadmap context', 'open loops') that users would say, though a few common synonyms are missing and 'continuity layer' is jargon.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche ('product-manager continuity layer of an agent team') with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agentlas-ai/Agentlas-OS
Path: .agents/skills/pm-soul/SKILL.md
Commit: a7988bb

Reviewed: 4 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.