Tessl • The management layer for AI agent skills

SkillPublic

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

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/company-intel/SKILL.md

Quality

Content

63%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.

The content is a thorough, well-structured research workflow with strong actionable templates and a clear step sequence, but it is longer than necessary, repeats key material, and points to example files that are absent from the bundle. Tightening and fixing the dangling references would lift it comfortably above the midpoint.

Suggestions

Consolidate the four-entry-point material into one location instead of restating it in both Key Concepts and Step 1.

Either ship the referenced examples/executive-signal-refresh.md and -saas.md files or remove the links, since they currently dangle.

Move the full seven-lens definitions and the 11-section template into a reference file, keeping SKILL.md as an overview that links to them.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and rich in domain-specific guidance, but it repeats material (the four entry points appear in both Key Concepts and Step 1, lens descriptions recur) and explains concepts Claude already knows, so it could be tightened.	3 / 5
Actionability	It provides a copy-paste 11-section output template, specific heuristics (CPO tenure windows, job-posting language cues), a source-priority ladder, and a concrete handoff menu, but the web-search execution itself stays high-level with no concrete commands.	4 / 5
Workflow Clarity	Steps are clearly sequenced (Step 1 -> 1b -> 2 -> 3 -> 4 -> Rerun) with an explicit confirmation checkpoint in the discover-competitors flow and per-section quality checks, though the main research output lacks an explicit validate-and-fix feedback loop.	4 / 5
Progressive Disclosure	Sections are well headed, but bulk content (the full 11-section template, all seven lenses, heuristics) is inlined rather than split into reference files, and the referenced example files (examples/executive-signal-refresh.md, -saas.md) do not exist in the bundle, leaving dangling references.	3 / 5
	Total	14 / 20 Passed

Description

70%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.

The description clearly answers what and when with concrete domain language and a distinct PM-intel niche, but its action list is thin and the trigger phrasing could be more vivid and comprehensive. It sits solidly above the midpoint but short of the comprehensive anchor.

Suggestions

Replace the generic verb 'Research' with concrete actions the skill performs (e.g., 'Profile a company across seven lenses and produce a structured 11-section intel report').

Broaden the 'Use when' clause with concrete trigger phrases users actually say, e.g. 'Use when preparing a battlecard, SWOT, or positioning workshop, or running a competitive scan across 3-5 companies'.

Add a natural synonym or two ('competitive intelligence', 'company deep-dive') to widen trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('company, industry, or competitor set') and two concrete actions ('using web search' and 'seven analytical lenses'), but the actions remain minimal and not comprehensive, matching the anchor for 3.	3 / 5
Completeness	It states both what ('Research... using web search and seven analytical lenses') and when ('Use when you need structured intel that feeds downstream PM skills'), but the when clause is somewhat abstract and could be more specific.	4 / 5
Trigger Term Quality	It includes natural terms users would say ('company', 'industry', 'competitor set', 'structured intel') with good coverage, though a few natural synonyms like 'battlecard', 'SWOT', or 'competitor analysis' are absent.	4 / 5
Distinctiveness Conflict Risk	The 'seven analytical lenses' plus 'feeds downstream PM skills' framing carves a mostly distinct PM-intel niche with only minor overlap risk against generic company-research skills.	4 / 5
	Total	15 / 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
skill_md_line_count	SKILL.md is long (528 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
Revision: cfcb697

Reviewed: 1 month ago

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.

company-intel

Table of Contents

Is this your skill?