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.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pm/SKILL.md

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.

The skill body is highly actionable and exceptionally well-sequenced with strong validation gates, but it is token-heavy due to pervasive design-rationale prose and monolithically inlines content that progressive disclosure would split into reference files.

Suggestions

Trim design-rationale paragraphs (e.g., 'Why it takes the round rather than riding beside the answer', 'It was built the other way first...') to the operational rule only, cutting hundreds of tokens without losing guidance.

Move the detailed evidence-lane fan-out rules (Step 3-A2) and the refine-gate JSON templates into a reference file under references/ and link to it one level deep, raising progressive disclosure and reducing inline weight.

Clarify the ambiguous 'Generate a PM' phrasing in the description to something concrete like 'Produce a Product Requirements Document (PRD) via a guided interview'.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, mixing operational instruction with extensive design rationale ('It was built the other way first, with a second parameter for findings...', 'What this does not license', repeated anti-pattern justifications) that pads tokens without aiding execution; it is above the severely-verbose anchor but below the mostly-efficient one.	2 / 5
Actionability	Provides copy-paste-ready tool-call blocks, exact JSON payloads for AskUserQuestion, concrete bash commands, and explicit argument templates covering the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Clear Step 0-Step 5 sequence with explicit validation checkpoints (deferred-schema guard, fail-closed on tool-not-found, refine-gate confirmation, meta.is_complete completion check, generation_failed retry) and error-recovery feedback loops throughout.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and all ~450 lines are inlined in SKILL.md; sections are well-organized, but large bodies like the fan-out/evidence-lane rules and refine-gate templates are inline content that could live in separate files, matching the some-structure-but-could-be-better-organized anchor.	3 / 5
	Total	15 / 20 Passed

Description

82%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 well-constructed: third-person voice, explicit 'Use when' trigger guidance, and concrete trigger phrases. Its main weakness is the ambiguous 'Generate a PM' phrasing, which blurs the 'what' slightly.

Dimension	Reasoning	Score
Specificity	Names the domain and 1-2 concrete actions ('guided PM-focused interview', 'automatic question classification', 'create a PRD/PM document') but the phrase 'Generate a PM' is ambiguous jargon and coverage is not comprehensive, matching the anchor for a clear domain with limited action detail.	3 / 5
Completeness	Explicitly answers both what ('Generate a PM through guided PM-focused interview with automatic question classification') and when via a concrete 'Use when the user says...' clause with specific trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes several natural trigger phrases users would say ('ooo pm', 'prd', 'product requirements', 'PRD/PM document') with good coverage; a few synonyms/extensions are missing, so it sits above the midpoint but not at the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The 'ooo pm' command trigger and 'prd' keyword carve a clear niche with minimal overlap risk against other skills, matching the distinct-triggers anchor.	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: Q00/ouroboros
Path: skills/pm/SKILL.md
Commit: 80333ae

Reviewed: 3 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.