product-skills

Use when coordinating product work across the 12 bundled product sub-skills (RICE, OKRs, UX research, design tokens, competitive teardown, analytics, experiments, discovery, roadmaps, spec-to-repo, landing pages, SaaS scaffolding) or the 4 standalone product-team plugins (user stories, Apple HIG, code-to-PRD, research summarizer). Triggers on 'help me prioritize', 'plan a product experiment', 'we ship features nobody uses', 'run the discovery loop', 'is our OST sound'. Forks context to route to one sub-skill via a deterministic signal router and returns a digest; can also drive a continuous-discovery loop (Torres cadence tracker + OST linter as machine gates) or a full goal→plan→execute→verify→close run through the repo-wide agent-harness. Distinct from project-management (how to deliver vs what to build), marketing/landing (from-scratch pages), and engineering/agent-harness (the generic loop engine this orchestrator plugs into).

Quality

96%

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

92%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 well-structured orchestrator skill: executable routing and loop commands with exit-code semantics, an explicit gated workflow with feedback loops, and clean one-level-deep reference disclosure. Only minor conciseness trim is warranted around canon citations.

Suggestions

Tighten the forcing-question library by collapsing the per-item 'Canon:' citations into a single shared canon reference, removing repeated author/title attributions.

Drop the editorial framing line 'Modern discovery is a weekly habit, not a project phase (Torres)' or move it into the continuous_discovery_canon reference rather than the SKILL body.

Consider moving the long 'When to invoke' 16-row symptom table into a reference file, keeping only the routing-command summary in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes competence, but the 'Modern discovery is a weekly habit, not a project phase' framing and the per-forcing-question 'Canon:' citations (Reinertsen, Cagan, Bland) are minor instances of over-explanation that could be trimmed.	4 / 5
Actionability	Copy-paste-ready commands with full flags and documented exit codes (0/2/3 for routing, exit 5 for cadence, exit 2 for the linter) cover the common routing, discovery-loop, and build-scale cases.	5 / 5
Workflow Clarity	The discovery loop is a clear 5-step sequence (Observe→Choose→Act→Verify→Record/Repeat-or-stop) with explicit machine gates and feedback loops (fix-before-citing, stop states, named escalation), so validation is present rather than missing.	5 / 5
Progressive Disclosure	A clear overview with a dedicated References section linking three one-level-deep reference files, plus inline script and asset paths; all referenced bundle files exist on disk, making navigation easy.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An exceptionally strong description: third-person voice, concrete capabilities, explicit natural trigger phrases, and active disambiguation from adjacent skills. Both the 'what' and 'when' are unambiguous.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — routing to one sub-skill via a deterministic signal router, driving a continuous-discovery loop with Torres cadence tracker + OST linter gates, and a full goal→plan→execute→verify→close run — giving comprehensive coverage.	5 / 5
Completeness	Clearly answers both what (coordinate/route/drive-loop/run-through-harness) and when ('Use when coordinating product work…' + 'Triggers on…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Explicit 'Triggers on' phrases users would naturally say ('help me prioritize', 'plan a product experiment', 'run the discovery loop') plus sub-skill keywords (RICE, OKRs, OST), covering synonyms and variations.	5 / 5
Distinctiveness Conflict Risk	Explicitly disambiguates from project-management (deliver vs build), marketing/landing, and engineering/agent-harness, giving a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 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: product-team/skills/product-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.