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

73%

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 ./.agents/skills/pm-soul/SKILL.md

Quality

Content

70%

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

The skill body is admirably concise and well-organized for a simple instruction-only skill, but it stops at describing the work rather than giving fully actionable, verifiable steps — the extraction and connection steps are abstract, and durable memory writes lack validation checkpoints.

Suggestions

Make the procedure actionable: specify how to extract each field from project-soul-memory.md (e.g., which section/heading maps to 'user promise' vs 'acceptance criteria') rather than leaving 'Extract ... open loops' as an abstract directive.

Add a validation checkpoint before emitting ## Memory Events (e.g., 'Confirm the update is durable and non-conflicting before emitting a Memory Event') since shared-memory writes are destructive/batch-like and currently cap workflow_clarity at 2.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — a 4-step procedure and a one-line output contract, every token earning its place — and it does not explain PM concepts Claude already knows, so it matches the 'lean and efficient' anchor.	3 / 3
Actionability	It gives specific file/section targets ('.agentlas/project-soul-memory.md', '## Memory Events') and a concrete output shape, but the steps are directions rather than executable commands, and how to 'extract' or 'connect sitemap changes to product intent' is left unspecified, so guidance is incomplete.	2 / 3
Workflow Clarity	A numbered 1–4 sequence is present and an explicit output schema is defined, but there are no validation checkpoints for the durable memory writes (## Memory Events are themselves a risky/destructive shared-state change), and the body's own guidance says not to silently rewrite shared memory yet offers no verify step, capping clarity at 2.	2 / 3
Progressive Disclosure	This is a short single-purpose skill with no external bundle files; it is organized into clear Procedure and Output sections with no nested references, which the simple-skill rule rewards with a 3.	3 / 3
	Total	10 / 12 Passed

Description

77%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description has a clear 'Use when' trigger and a distinct, well-scoped niche, but it lists nouns to preserve rather than concrete actions and leans on internal jargon ('product-manager continuity layer') that users would not naturally say. Specificity and trigger-term naturalness are the weakest points.

Suggestions

Lead with the concrete action the skill performs (e.g., 'Captures and preserves product intent, acceptance criteria, and open-loop decisions...') instead of naming only the nouns to preserve, to lift specificity to a 3.

Replace 'the product-manager continuity layer of an agent team' with phrasing a user would actually say (e.g., 'PM context', 'product decisions across agent handoffs') to improve trigger-term naturalness.

Dimension	Reasoning	Score
Specificity	Names a domain (product-manager continuity) and several objects (product intent, acceptance criteria, decision memory, open loops, roadmap context), but no concrete actions are described — only the noun phrases to preserve, which reads more like a scope list than executable capabilities.	2 / 3
Completeness	It opens with an explicit 'Use when...' clause answering when to invoke it, and the enumerated nouns answer what it preserves, so both what and when are present.	3 / 3
Trigger Term Quality	'Use when preserving product intent, acceptance criteria, open loops, roadmap context' includes several natural PM-ish phrases a user might say, but it leans on internal jargon like 'product-manager continuity layer of an agent team' that a user would rarely utter verbatim, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The niche is narrow and explicit — preserving PM continuity/memory for an agent team — which is unlikely to overlap with generic file or doc skills, and its triggers ('decision memory', 'open loops', 'acceptance criteria') are distinct.	3 / 3
	Total	10 / 12 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: 2eb39ad

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.