pm-skills

Use when coordinating project-delivery work across the 8 project-management sub-skills — sprint/velocity analytics, portfolio health, Jira/JQL, Confluence, Atlassian admin, templates, meeting analysis, team comms. Triggers on 'our sprints feel off', 'project health report', 'audit our Jira permissions', 'when will it be done', 'run the delivery loop'. Forks context to route to one sub-skill via a deterministic signal router and returns a digest; can also drive a full goal→plan→execute→verify→close delivery loop through the repo-wide agent-harness with Jira MCP data bridged into the domain's analytics tools. Distinct from product-team (what to build vs how to deliver it), business-operations (internal ops), and engineering/agent-harness (the generic loop engine this orchestrator plugs into).

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

88%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.

An exceptionally actionable, well-sequenced orchestrator body with real, verified bundle scripts and one-level-deep references. The main opportunity is to relocate the lengthy forcing-question library into its own reference file to raise both conciseness and progressive disclosure.

Suggestions

Move the per-lane forcing-question library into references/pm_forcing_questions.md and replace it with a one-line pointer, reducing inline tokens and improving progressive disclosure.

Collapse the overlap between 'Hard rules' and 'Anti-patterns' (e.g. the agent-ownership and auto-transition points appear in both) into a single section to tighten conciseness.

Confirm the cross-repo paths (engineering/agent-harness/...) resolve from the skill's working directory, or note the expected repo layout, since they are invoked inline but not bundle-local.

Dimension	Reasoning	Score
Conciseness	Densely actionable with no padding of concepts Claude already knows; every line carries a script, exit code, or rule. Minor redundancy between the 'Hard rules' and 'Anti-patterns' sections keeps it just below the lean anchor.	4 / 5
Actionability	Copy-paste-ready commands with explicit exit-code semantics ('exit 0 → route_to', 'exit 2 = blocked', 'exit 4 = close refused') and flags (--forecast N, --sample) all verified against the bundled scripts, covering the common routing and loop cases.	5 / 5
Workflow Clarity	The delivery loop is a clearly numbered Observe→Choose→Act→Verify→Record sequence with explicit validation gates and feedback loops ('refuses on < 10 completed items', gate exit codes); destructive/batch operations carry required verification, exempting it from the cap.	5 / 5
Progressive Disclosure	A clear overview with well-signaled one-level-deep references to three confirmed reference files (flow_forecasting_canon, agentic_delivery_governance, pm_loop_playbook); the forcing-question library is fairly long inline where a pointer to a reference would tighten it, so it sits just below the top anchor.	4 / 5
	Total	18 / 20 Passed

Description

92%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 pairs concrete orchestrator actions with an explicit trigger clause and active disambiguation from neighboring skills. Its only weak spot is trigger-term breadth: a couple of the 8 lanes lack a natural user phrasing.

Suggestions

Add a natural-language trigger for the meeting-analysis and team-communications lanes (e.g. "summarize this meeting transcript" or "draft the weekly stakeholder update") so every lane has a quotable trigger phrase.

Consider including the most common user phrasing for Confluence content audits, which currently has no direct trigger example in the description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'forks context to route to one sub-skill via a deterministic signal router', 'drive a full goal→plan→execute→verify→close delivery loop', 'bridge [Jira MCP data] into the domain's deterministic analytics tools' — with comprehensive coverage of the orchestrator's routing, looping, gating, and bridging duties.	5 / 5
Completeness	Explicitly answers both what ('Use when coordinating project-delivery work across the 8 … sub-skills') and when (a dedicated 'Triggers on' clause with concrete trigger phrases), matching the highest anchor.	5 / 5
Trigger Term Quality	Includes natural user phrasings via the explicit 'Triggers on' clause ('our sprints feel off', 'project health report', 'audit our Jira permissions', 'when will it be done', 'run the delivery loop') plus a 'Use when coordinating…' clause, covering several lanes; a few common synonyms across the 8 lanes are missing, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Explicitly disambiguates three adjacent domains ('Distinct from product-team … business-operations … and engineering/agent-harness'), carving a clear PM-delivery niche with minimal trigger-conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: project-management/skills/pm-skills/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours 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.