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.

72

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A tightly structured, highly actionable multi-turn MCP interview skill with strong workflow checkpoints and clear sequencing. The main weakness is conciseness: the deferred-schema guard explanation and inline diagnosis message templates are wordier than necessary.

Suggestions

Compress the 'CRITICAL — deferred-schema guard' paragraph to the essential rule ('re-run the discovery query before every ouroboros_pm_interview call') and move the why into a one-line parenthetical.

Move the multi-line user-facing diagnosis message template into a collapsed/condensed form or a short reference, keeping only the action sequence inline.

Trim the parenthetical asides (e.g. 'idempotent — a no-op if already loaded') into shorter notes to reduce token weight without losing the guard's intent.

DimensionReasoningScore

Conciseness

The body is mostly concrete and operational, but the 'CRITICAL — deferred-schema guard' paragraph and the nested not-found diagnosis block explain runtime mechanics and reproduce user-facing message templates at length, which could be tightened; it is efficient in places but padded in others, matching the score-2 anchor.

2 / 3

Actionability

Provides exact tool names, argument blocks, bash commands, and literal AskUserQuestion option JSON (e.g. the decide_later/deferred skip options), making the guidance copy-paste ready and fully executable.

3 / 3

Workflow Clarity

A clear Step 1–5 sequence with explicit checkpoints: completion gated ONLY on meta.is_complete, a generation_failed retry loop, and a deferred-schema reload guard, plus error-recovery diagnosis — matching the score-3 anchor for fragile multi-step operations.

3 / 3

Progressive Disclosure

No bundle files exist, so all content lives in a single SKILL.md; it is well-organized into clearly signaled Step sections with no nested references, which is appropriate for a cohesive multi-turn loop skill and matches the 'well-organized sections' allowance.

3 / 3

Total

11

/

12

Passed

Description

90%

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 clear, third-person description with an explicit 'Use when' trigger clause and good natural keyword coverage. Its only weakness is specificity: it describes one core action rather than enumerating several concrete capabilities.

DimensionReasoningScore

Specificity

Names the domain (PM/PRD) and a couple of concrete actions ('Generate a PM through guided PM-focused interview', 'automatic question classification'), but it does not list multiple distinct concrete actions like the score-3 anchor, so it sits at the 'some actions, not comprehensive' level.

2 / 3

Completeness

Explicitly answers both 'what' (guided PM-focused interview that generates a PRD) and 'when' via a clear 'Use when...' clause, matching the score-3 anchor.

3 / 3

Trigger Term Quality

Includes natural user-facing triggers — 'ooo pm', 'prd', 'product requirements', 'PRD/PM document' — giving good coverage of terms a user would actually say, matching the score-3 anchor.

3 / 3

Distinctiveness Conflict Risk

The PM/PRD interview niche is specific and its triggers ('ooo pm', 'prd', 'product requirements') are distinct, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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.