CtrlK
BlogDocsLog inGet started
Tessl Logo

pm

Generate a PM through guided PM-focused interview with automatic question classification. Use when the user says 'ooo pm', 'prd', 'product requirements', or wants to create a PRD/PM document.

64

Quality

76%

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 ./.claude-plugin/skills/pm/SKILL.md

The canonical home for this skill is pm in Q00/ouroboros

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 highly actionable, well-sequenced orchestration skill with thorough validation, but it is materially overweight: pervasive rationale and emphatic restatement inflate the body well beyond what the concrete instructions require. Splitting the detailed contract and template material into reference files would improve both conciseness and navigability.

Suggestions

Trim the rhetorical emphasis and rationale: replace multi-line justifications (e.g. the 'grounds, never options' and 'do not look at the repositories yourself' passages) with one-line rules, keeping the executable guidance.

Extract the fan-out contract mechanics (A2/A3 lane handling, RFC #2222 rules) and the Refine-gate JSON templates into one-level-deep reference files (e.g. FANOUT.md, REFINE.md) linked from SKILL.md, so the overview stays scannable.

Consolidate the repeated 'Never…' prohibitions scattered across Step 3 into a single bulleted constraints list to remove restatement.

DimensionReasoningScore

Conciseness

The body is noticeably verbose: rules are repeated with rhetorical emphasis ('You do not look at the repositories yourself. Ever.') and each directive is followed by multi-line philosophical rationale that could be trimmed without losing clarity.

2 / 5

Actionability

Provides fully executable, copy-paste-ready guidance — exact MCP tool names, argument specs, JSON payloads, bash commands, and AskUserQuestion templates covering the common cases.

5 / 5

Workflow Clarity

Steps 0–5 are clearly sequenced with explicit validation checkpoints (version check, deferred-schema re-load, fail-closed, is_complete/generation_failed handling, Refine-gate confirmation) and feedback loops for error recovery.

5 / 5

Progressive Disclosure

The skill is a single monolithic file with no bundle/reference files; section headers give structure, but large blocks of contract mechanics, refine-gate templates, and RFC #2222 detail are inlined where separate reference files would aid navigation.

3 / 5

Total

15

/

20

Passed

Description

83%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, third-person description that clearly states capability and trigger conditions with concrete, natural activation phrases. Its only weakness is slightly limited breadth of trigger synonyms and the mildly abstract 'generate a PM' phrasing.

DimensionReasoningScore

Specificity

Lists several specific actions — 'guided PM-focused interview', 'automatic question classification', and generating a PM/PRD document — with only minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what it does ('Generate a PM through guided PM-focused interview with automatic question classification') and when to use it, with concrete trigger phrases.

5 / 5

Trigger Term Quality

Concrete natural triggers are present ('ooo pm', 'prd', 'product requirements', 'PRD/PM document') with synonyms, though a few common variations (e.g. 'spec', 'requirements gathering') are missing.

4 / 5

Distinctiveness Conflict Risk

The distinctive 'ooo pm' trigger gives it a clear niche, while 'prd'/'product requirements' carry only minor overlap risk with other product-document skills.

4 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Q00/ouroboros
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.