CtrlK
BlogDocsLog inGet started
Tessl Logo

competitor-profiling

When the user wants to research, profile, or analyze competitors from their URLs. Also use when the user mentions 'competitor profile,' 'competitor research,' 'competitor analysis,' 'profile this competitor,' 'analyze competitor,' 'competitive intelligence,' 'competitor deep dive,' 'who are my competitors,' 'competitor landscape,' 'competitor dossier,' 'competitive audit,' or 'research these competitors.' Input is a list of competitor URLs. Output is structured competitor profile markdown files. For creating comparison/alternative pages from profiles, see competitors. For sales-specific battle cards, see sales-enablement.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./claude/skills/competitor-profiling/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 thorough, actionable multi-phase research workflow with concrete tool calls and a clear directory layout, supported by real one-level reference files. It is held back by an inlined full template that duplicates templates.md and the absence of explicit validation/error-recovery checkpoints for what is fundamentally a batch operation.

Suggestions

Remove the ~140-line inlined profile template from the body and replace it with a brief structural sketch plus a pointer to references/templates.md, since that file already holds the full templates.

Add an explicit validation/feedback loop for batch scraping (e.g., verify each Firecrawl scrape returned content before extracting fields, and retry or skip on failure) to lift workflow_clarity above the batch-operations cap of 3.

Tighten "Core Principles" by trimming self-evident guidance (e.g., honest assessment, facts over opinions) to reduce token overhead without losing the principles that genuinely guide behavior.

DimensionReasoningScore

Conciseness

Mostly efficient and well-structured, but the body inlines a ~140-line full profile template that duplicates references/templates.md, and sections like "Core Principles" state somewhat obvious guidance ("Don't exaggerate competitor weaknesses").

3 / 5

Actionability

Concrete, executable guidance throughout: specific MCP tool names (firecrawl_map, backlinks_summary, dataforseo_labs_google_ranked_keywords), explicit directory layout, and per-page extraction tables, with only minor gaps deferred to tool-reference.md.

4 / 5

Workflow Clarity

Clear three-phase sequence with raw-data persistence as a checkpoint, but this is a batch operation (many pages/competitors) with no explicit validate-then-proceed or error-recovery feedback loop in the main body, capping the score at 3 per the batch-operations guideline.

3 / 5

Progressive Disclosure

Good section structure with clearly signaled one-level-deep references to real files ([references/templates.md], [references/tool-reference.md]); the main gap is the large inlined template that overlaps content already delegated to templates.md.

4 / 5

Total

14

/

20

Passed

Description

95%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 description that clearly states what the skill does, when to trigger it, and its inputs/outputs, with a rich set of natural trigger terms and explicit boundary guidance to neighboring skills. Voice is appropriately third person.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("research, profile, or analyze competitors from their URLs") plus explicit input ("list of competitor URLs") and output ("structured competitor profile markdown files"), with only minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what (research/profile/analyze competitors, input URLs → output profile markdown) and when ("When the user wants to..." plus "Also use when the user mentions...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural phrases users would say, including many synonyms and variations ("competitor profile," "competitor deep dive," "who are my competitors," "competitive audit," "research these competitors").

5 / 5

Distinctiveness Conflict Risk

Clear niche (competitor profiling from URLs) with distinct triggers and explicit boundary guidance routing adjacent intents to other skills ("see competitors," "see sales-enablement"), minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
joshmanders/dotfiles
Reviewed

Table of Contents

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.