Name: pm-skills
Rating: 70.39999999999999 (1 reviews)
Author: alirezarezvani

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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is pm-skills in alirezarezvani/claude-skills

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.

A highly actionable, well-sequenced orchestrator body with executable commands and strong validation gates. The main lever is tightening the forcing-question and hard-rules sections, plus ensuring the referenced bundle files actually ship with the skill.

Suggestions

Trim the forcing-question library to one canonical example per lane and compress the hard-rules list so each rule is a single line, cutting tokens without losing the governance intent.

Ship the referenced `references/*.md` (flow_forecasting_canon, agentic_delivery_governance, pm_loop_playbook) and `scripts/*.py` (pm_goal_router, jira_snapshot_bridge, delivery_loop_gate) inside the skill bundle so the one-level-deep references resolve.

Clarify which references are part of this skill's bundle versus sibling repo paths (e.g. `engineering/agent-harness`, `../scrum-master/`) so navigation between the orchestrator and its dependencies is unambiguous.

Dimension	Reasoning	Score
Conciseness	Mostly lean and command-dense with no explaining of concepts Claude already knows, but the forcing-question library and the six-item hard-rules list run long and could be trimmed without losing clarity.	4 / 5
Actionability	Copy-paste-ready commands throughout — `python3 scripts/pm_goal_router.py --text "<the goal>" --output json`, the bridge commands with `--to flow`/`--forecast N`, and `delivery_loop_gate.py --mode plan\|close` with documented exit codes — fully executable and covering the common cases.	5 / 5
Workflow Clarity	The Observe→Choose→Act→Verify→Record loop is explicitly sequenced with validation checkpoints (gate exit codes 2/4, "Never adjudicate your own verification", enumerated terminal states), satisfying the destructive/batch feedback-loop requirement rather than capping at 3.	5 / 5
Progressive Disclosure	Well-organized overview with a clearly signaled one-level-deep References section pointing to canon/governance/playbook files, but the referenced `references/.md` and `scripts/.py` files are not present in the review bundle to verify, and several paths point to sibling skills/harness outside this skill's own bundle.	4 / 5
	Total	18 / 20 Passed

Description

87%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 explicitly covers what (route + delivery loop) and when (Use when + five natural trigger phrases) while disambiguating from sibling skills. Slightly dense; tightening the action list would lift specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete orchestration actions — "Forks context to route to one sub-skill via a deterministic signal router and returns a digest" and "drive a full goal→plan→execute→verify→close delivery loop ... with Jira MCP data bridged" — but the actions are meta/orchestration-level rather than the domain work itself, leaving minor coverage gaps.	4 / 5
Completeness	Opens with an explicit "Use when coordinating project-delivery work" clause plus concrete "Triggers on" phrases (when) and a clear statement of routing + looping behavior (what), explicitly answering both.	5 / 5
Trigger Term Quality	Explicit natural trigger phrases ("Triggers on 'our sprints feel off', 'project health report', 'audit our Jira permissions', 'when will it be done', 'run the delivery loop'") give good keyword coverage, though synonyms and file-extension variants are absent.	4 / 5
Distinctiveness Conflict Risk	Explicit disambiguation — "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)" — carves a clear PM-orchestrator niche with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	13 / 16 Passed

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

Reviewed: ~12 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.