product-thinking

Think like a product manager before changing React Doctor's public surface — CLI commands/flags, the 0–100 score, config (doctor.config.*), the JSON report schema, package APIs (inspect()/diagnose()), the GitHub Action, the website, and the canonical prompts. A step-by-step runbook for a user-facing change — locate the surface, search for a reuse candidate, wire one telemetry metric, add the compatibility artifacts (changeset / schemaVersion / action tag), update docs, and record a kill metric. Not for lint rules, which have their own pipeline. Also runs when the user types `/product-thinking`.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 well-structured, highly actionable runbook with concrete commands, file paths, validation checkpoints, and decision gates. It stays lean and assumes competence; the main improvement is splitting a couple of inline reference-like sections (e.g. product principles) into bundled files for cleaner progressive disclosure.

Suggestions

Move the seven 'Product principles' into a references file (e.g. references/product-principles.md) and link to it one level deep, keeping the runbook focused on the steps.

Tighten the durability/trust filter prose in step 1 to bullet-style criteria to trim a few tokens without losing meaning.

Consider extracting the surface-location table into a reference if it grows, so the 'When to run it' section stays a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no basic concept explanations), with every section tied to a concrete surface or step; a few prose passages like the durability/trust filters and the seven product principles could be trimmed without losing clarity.	4 / 5
Actionability	Fully executable guidance throughout — copy-paste commands ('bunx @rayhanadev/truffler ...', 'rg -n ...', 'nr changeset', 'nr smoke:json-report', 'nr typecheck && nr test && nr lint') and precise file paths ('cli/utils/constants.ts', 'cli/utils/record-metric.ts', 'core/src/schemas.ts') cover the common cases.	5 / 5
Workflow Clarity	A clearly sequenced seven-step runbook with an explicit validation checkpoint at step 7 ('Run checks'), decision gates in 'Stop and ask when', and a fill-in brief template that folds into the PR; the breaking-contract scenarios are flagged before landing, so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a single inline checklist/brief, but all content lives in SKILL.md with no bundle files; sections like 'Product principles' (seven tie-breakers) could be split into a one-level-deep reference to reach a 5.	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, highly specific description that clearly states what the skill does and when it triggers, scoped tightly to React Doctor's public surface. The only weakness is the imperative 'Think like...' opening, which reads as second-person voice and slightly dilutes specificity.

Suggestions

Rephrase the opening in third person (e.g. 'Applies product-manager thinking before changing React Doctor's public surface') to avoid the second-person/imperative voice penalty.

Add one or two natural user-facing trigger phrases (e.g. 'Use when planning a user-facing change to React Doctor') alongside the slash-command trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('locate the surface, search for a reuse candidate, wire one telemetry metric, add the compatibility artifacts ... update docs, and record a kill metric') with comprehensive coverage, but the imperative opening 'Think like a product manager' is second-person voice, triggering a one-point specificity penalty per the rubric guideline.	4 / 5
Completeness	Explicitly answers both what ('A step-by-step runbook for a user-facing change' with enumerated steps) and when ('Also runs when the user types /product-thinking' plus 'Not for lint rules'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage across 'product manager', 'user-facing change', 'public surface', 'telemetry metric', 'kill metric', and an explicit '/product-thinking' trigger, though some natural phrasings a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche scoped to React Doctor's public surface with an explicit exclusion ('Not for lint rules, which have their own pipeline'), yielding minimal conflict risk with other skills.	5 / 5
	Total	18 / 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: millionco/react-doctor
Path: .agents/skills/product-thinking/SKILL.md
Commit: 83466a8

Reviewed: 5 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.