Name: pm-orchestrator
Rating: 88.6 (1 reviews)
Author: headout

pm-orchestrator

The PM Orchestrator is the central brain of Headout's PM OS. Use this skill when a PM has any product work to do and isn't sure which specialist to engage, wants a recommended workflow for their specific problem, or wants the full product cycle run end-to-end. Reads the problem, assesses what stage the PM is at, recommends which specialists to engage and in what order, and manages context passing between each stage. Trigger for: "where do I start with X", "run the full product cycle", "what should I do with this idea", "help me figure out the process", any vague brief needing routing, or any request that spans multiple specialists. When in doubt about which specialist to call, call the Orchestrator first.

1.20x

Quality

83%

Does it follow best practices?

Impact

99%

1.20x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

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

This is a strong orchestrator skill with excellent workflow clarity, concrete actionability, and a well-designed quality gate system. Its main weaknesses are moderate verbosity (motivational framing, repeated metaphors, explanatory 'Why' sections that could be trimmed) and a monolithic structure that could benefit from splitting path details or specialist references into separate files. The worked example and common issues section are particularly valuable additions.

Suggestions

Trim the 'Why' explanations after each path to single sentences or remove them — Claude can infer the reasoning from the specialist sequence and problem type.

Remove motivational/identity framing like 'You don't do the specialists' work. You enable it.' and 'Don't be a mechanical router' — these consume tokens without changing behavior.

Consider splitting the six path definitions into a referenced PATHS.md file to reduce the main skill's length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is well-structured but verbose in places — the 'Why' explanations after each path, the Standards section restating the orchestrator's value proposition, and some repetitive phrasing (e.g., 'the chain is only as strong as its weakest link' appears twice) add tokens without proportional value. The content assumes Claude needs motivational framing ('Use that judgment. Don't be a mechanical router.') which is unnecessary.	2 / 3
Actionability	The skill provides highly concrete, actionable guidance: a clear maturity assessment table, specific named paths (A-F) with exact specialist sequences, a structured handoff brief template, a detailed output format template, and a worked example with a real scenario. Every step tells Claude exactly what to do and produce.	3 / 3
Workflow Clarity	The multi-step workflow is exceptionally well-sequenced with explicit validation checkpoints: Step 2.5 forces blind-spot probing before committing, Step 3.5 requires self-critique before presenting, Step 5 mandates quality review before handoff, and Step 6 surfaces blockers. The feedback loop for weak specialist output is explicitly defined with a 'send it back' mechanism.	3 / 3
Progressive Disclosure	The skill references external memory files (active-pipeline.md, historical-pipeline.md, CLAUDE.md) appropriately, but the body itself is a monolithic ~300-line document with no references to separate detailed files for individual specialist instructions or path details. The six paths, output templates, and common issues could benefit from being split into referenced files, especially since this is an orchestrator that coordinates many specialists.	2 / 3
	Total	10 / 12 Passed

Description

89%

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

This is a strong skill description that excels at completeness and distinctiveness, clearly positioning itself as the meta-routing skill above specialist skills. The trigger terms are natural and well-chosen, covering both specific phrases and catch-all scenarios. The main weakness is that the specific capabilities described are somewhat abstract (assessing, recommending, managing context) rather than listing concrete deliverables or outputs.

Suggestions

Add more concrete action outputs beyond process descriptions, e.g., 'produces a sequenced action plan, generates specialist briefs, creates handoff documents between stages.'

Dimension	Reasoning	Score
Specificity	The description names the domain (PM workflow orchestration) and describes some actions like 'reads the problem, assesses what stage the PM is at, recommends which specialists to engage,' but the actions remain somewhat abstract and process-oriented rather than listing multiple concrete, tangible outputs or operations.	2 / 3
Completeness	Clearly answers both 'what' (reads the problem, assesses stage, recommends specialists, manages context passing) and 'when' (explicit trigger phrases, use cases like 'isn't sure which specialist to engage', and the fallback rule 'when in doubt, call the Orchestrator first').	3 / 3
Trigger Term Quality	Excellent trigger term coverage with natural phrases users would actually say: 'where do I start with X', 'run the full product cycle', 'what should I do with this idea', 'help me figure out the process', plus the catch-all 'any vague brief needing routing' and 'when in doubt' guidance. These are realistic user utterances.	3 / 3
Distinctiveness Conflict Risk	The description carves out a very clear niche as the routing/orchestration layer that sits above specialists. The explicit guidance 'when in doubt about which specialist to call, call the Orchestrator first' and the focus on multi-specialist coordination makes it highly distinct from any individual specialist skill.	3 / 3
	Total	11 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: headout/pm-os-marketplace
Commit: d8db811

Reviewed: 26 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.