When the user wants to define their ideal customer profile, position an AI product, build messaging architecture, or validate product-market fit. Also use when the user mentions 'ICP,' 'ideal customer profile,' 'positioning,' 'PMF,' 'product-market fit,' 'messaging,' 'buyer persona,' 'enrichment signals,' 'market positioning,' or 'competitive positioning.' This skill covers market positioning, ICP definition, messaging architecture, and PMF validation for AI-native products. Do NOT use for technical implementation, code review, or software architecture.
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that covers all key dimensions well. It provides specific capabilities, comprehensive trigger terms including both abbreviations and full phrases, explicit 'when to use' guidance, and clear negative boundaries to prevent misuse. The only minor note is that it uses second person ('the user wants') but this is in the context of trigger conditions rather than capability descriptions, and the capability statements themselves use appropriate phrasing.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'define their ideal customer profile, position an AI product, build messaging architecture, or validate product-market fit.' These are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (market positioning, ICP definition, messaging architecture, PMF validation for AI-native products) and 'when' (explicit 'Use when' triggers with specific terms). Also includes a helpful negative boundary ('Do NOT use for technical implementation, code review, or software architecture'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including abbreviations ('ICP', 'PMF') and full phrases ('ideal customer profile', 'product-market fit', 'positioning', 'messaging', 'buyer persona', 'enrichment signals', 'competitive positioning'). These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to AI product marketing/positioning with distinct trigger terms. The explicit exclusion of technical implementation, code review, and software architecture further reduces conflict risk with engineering-focused skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is exceptionally actionable and well-structured with clear workflows, specific scoring models, concrete templates, and validation checkpoints. However, it is severely over-length, containing extensive inline content that should be split into reference files, and it explains many concepts (PMF, enrichment signals, April Dunford's framework) that Claude already understands. The content quality is high but the token efficiency is poor—this skill could deliver the same value at roughly one-third its current length.
Suggestions
Reduce the main file to ~100-150 lines by moving detailed tables (scoring criteria, competitor types, pricing models, Sean Ellis benchmarks) into separate reference files like `references/icp-scoring.md`, `references/competitive-positioning.md`, and `references/pmf-validation.md`.
Remove explanatory context Claude already knows—e.g., what PMF is, why AI markets move fast, what enrichment signals are, the general concept of April Dunford's methodology—and keep only the specific adaptations and decision rules.
Consolidate the 'Before Starting' discovery questions and Section 8 Implementation Playbook, which overlap significantly, into a single concise workflow.
Cut the AI Pricing Model Landscape table entirely since it's covered by the cross-referenced ai-pricing skill, and trim the buyer shift section (Section 5) to just the implications table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at 400+ lines. It explains concepts Claude already knows (what PMF is, what enrichment signals are, basic marketing frameworks), includes extensive tables that repeat common knowledge, and provides lengthy explanations of well-known methodologies like April Dunford's positioning framework. Much of this could be condensed to 25% of its current length or moved to reference files. | 1 / 3 |
Actionability | The skill provides highly concrete, actionable guidance throughout: specific scoring formulas with weights, detailed checklists with checkboxes, specific thresholds (e.g., confidence >= 0.85, Sean Ellis 40%+, respond in <4 hours), templates with fill-in-the-blank structures, and clear decision criteria. The implementation playbook is week-by-week with specific deliverables. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The ICP Definition Workflow has 7 ordered steps with a back-testing validation step. The 90-Day PMF Revalidation Cadence has week-by-week actions with specific outputs. The Implementation Playbook provides a 6-week sequenced plan with checkboxes. The enrichment waterfall includes explicit decision points with confidence thresholds. | 3 / 3 |
Progressive Disclosure | The skill references a `references/quick-reference.md` file and cross-references related skills, which is good. However, the main file is monolithic with enormous amounts of inline content (scoring models, competitor page structures, pricing landscapes, full April Dunford methodology) that should be split into separate reference files. The 400+ line body would benefit greatly from moving detailed tables and frameworks to linked documents. | 2 / 3 |
Total | 9 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
906a57d
Table of Contents
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.