company-intel

Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.

Quality

85%

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

Quality

Content

77%

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

A highly actionable, clearly sequenced research workflow with concrete templates, confirmation gates, and verification checklists. It loses points on conciseness (conceptual sections Claude already knows) and on progressive disclosure (a monolithic file whose only referenced example files are missing).

Suggestions

Create the referenced `examples/executive-signal-refresh.md` and `examples/executive-signal-refresh-saas.md` files, or remove the links — pointing at non-existent bundle files breaks navigation and trust.

Trim or relocate "Why This Works," "Key Distinctions to Maintain," and "Tensions Worth Surfacing" to a reference file; these restate concepts Claude already knows and pad the main flow.

Consider moving the full worked examples and the Downstream Composition Guide into separate reference files so SKILL.md stays an overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	The body runs ~500 lines and is mostly valuable domain guidance, but sections like "Why This Works," "Key Distinctions to Maintain," and "Tensions Worth Surfacing" explain PM concepts Claude already knows and could be tightened, matching the score-2 anchor of mostly-efficient-but-could-be-tightened.	2 / 3
Actionability	It provides a concrete 11-section output template, explicit step-by-step workflow (Steps 1–4), exact confirmation/handoff prompts to present, per-section quality checks, and a source-priority ladder — copy-paste-ready, actionable guidance of the kind the rubric rewards for instruction-only skills.	3 / 3
Workflow Clarity	The multi-step flow is clearly sequenced (detect entry point → discover competitors → research/output → cross-company → handoff → rerun) with an explicit confirmation gate, per-section quality-check checklists, and a diff-against-prior-output verification step in the rerun pattern.	3 / 3
Progressive Disclosure	Sections are well-organized, but the file is monolithic with no bundle files present, and the two referenced `examples/*.md` paths do not exist on disk — references are signaled but unresolvable, and content that could live separately (worked examples, full output template) is inline.	2 / 3
	Total	10 / 12 Passed

Description

92%

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 description: concrete actions, natural trigger terms, and an explicit "Use when" clause that covers both what and when. The main weakness is overlap with a documented sibling `company-research` skill, which it does not explicitly differentiate from in the description itself.

Suggestions

Add a half-clause distinguishing company-intel from the sibling company-research skill (e.g., "deeper and broader than a profile") so the description self-disambiguates and reduces wrong-skill triggering.

Consider swapping the slightly jargon-y "competitor set" for the more natural "competitors" alongside it to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Research a company, industry, or competitor set using web search and seven analytical lenses" names the domain plus multiple concrete actions (web search, applying seven lenses, producing structured intel), matching the score-3 anchor that lists several specific concrete actions.	3 / 3
Completeness	It answers both what ("Research a company... using web search and seven analytical lenses") and when via an explicit "Use when you need structured intel that feeds downstream PM skills" clause, satisfying the score-3 anchor for explicit triggers on both axes.	3 / 3
Trigger Term Quality	Natural user-facing terms are present — "company," "industry," "competitor set," and "intel" — which are the words a user would actually say when needing this skill; coverage is good rather than just "some relevant keywords."	3 / 3
Distinctiveness Conflict Risk	The description carves a niche (seven lenses, competitor sets, downstream PM intel), but the skill's own References document a sibling `company-research` skill covering the same domain, so it "could still overlap with similar skills" rather than being unlikely to conflict.	2 / 3
	Total	11 / 12 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
skill_md_line_count	SKILL.md is long (526 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 14 suspicious	Warning

	Total	13 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/company-intel/SKILL.md
Commit: 9971018

Reviewed: 3 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.