CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/pm-soul/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is an exemplar of token efficiency for a simple instruction-only skill — tight, well-sectioned, and free of padding. Its weakness is executability: two of four procedure steps lack the concrete detail (what 'connecting' sitemap changes means, what a Memory Event looks like) needed to act on them unambiguously.

Suggestions

Show a one-line example of a ## Memory Events entry so the required output format is unambiguous.

Make step 3 operational: replace 'Connect sitemap changes to product intent' with a concrete check or mapping instruction (e.g. what to compare and what to emit when a sitemap change conflicts with recorded intent).

Specify where memory_events are written and how drift_risks are derived, since both appear in the Output contract with no producing step.

DimensionReasoningScore

Conciseness

Lean and efficient with zero padding: every line instructs ('Read .agentlas/project-soul-memory.md when present', 'Emit ## Memory Events... instead of silently rewriting shared memory') and nothing explains concepts Claude already knows.

5 / 5

Actionability

Concrete anchors exist (specific memory-file path, extraction field list, output keys), but 'Connect sitemap changes to product intent' gives no operational instruction and the ## Memory Events entry format is unspecified, leaving key details missing.

3 / 5

Workflow Clarity

A clear four-step sequence (Read → Extract → Connect → Emit) with an implicit safety guard ('instead of silently rewriting shared memory'); minor gaps remain with no validation checkpoint on emitted memory events, and the operations are neither destructive nor batch so the cap does not apply.

4 / 5

Progressive Disclosure

Under 50 lines, single-purpose, no external references needed (no bundle files exist), and cleanly organized into Procedure and Output sections, which merits the top score under the simple-skill guideline.

5 / 5

Total

17

/

20

Passed

Description

53%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.

The description is a well-scoped trigger clause with a distinct PM-continuity niche, but it is structurally when-only: it never says what the skill actually does, and several trigger terms are internal jargon rather than natural user phrasing. It sits at the midpoint of the rubric.

Suggestions

Add an explicit 'what' statement before the trigger clause, e.g. 'Maintains the product-manager continuity layer: extracts and updates product intent, acceptance criteria, and open loops. Use when...'

Replace or supplement jargon trigger terms ('decision memory', 'open loops', 'continuity layer') with natural user phrasings such as 'product context', 'unresolved decisions', or 'PM handoff'.

Include common synonym variations of the trigger terms (e.g. 'roadmap', 'product roadmap', 'acceptance criteria', 'definition of done') to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Names the PM-continuity domain and its objects ('product intent, acceptance criteria, decision memory, open loops, roadmap context') with a single action verb ('preserving'), but never states distinct concrete actions the skill performs.

3 / 5

Completeness

The 'when' is explicit ('Use when preserving...') but the 'what' is only weakly implied through the trigger clause; there is no separate statement of what the skill does, matching the clear-what/weak-when anchor inverted at the same level.

3 / 5

Trigger Term Quality

Some relevant keywords ('product intent', 'acceptance criteria', 'roadmap') but heavier on system-internal jargon ('decision memory', 'open loops', 'continuity layer of an agent team') and missing natural synonyms or everyday phrasings users would actually say.

3 / 5

Distinctiveness Conflict Risk

'the product-manager continuity layer of an agent team' carves a clear niche with distinct triggers; minor overlap risk remains with generic memory or continuity skills.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

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.