metis-strategy/metis-capability-map
Generate L1-L3 business capability maps organized across three pillars: Customer/Guest Journey, Value Chain, and Supporting Domains. Produces PPTX, XLSX, and HTML outputs with optional maturity heat mapping. Works for any industry from first principles.
73
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 an excellent skill description that thoroughly covers what the skill does, when to use it, and provides extensive natural trigger terms. It uses proper third-person voice, lists concrete actions and output formats, and occupies a clearly distinct niche. The only minor concern is that the description is quite long, but the length is justified by the breadth of trigger terms rather than being padded with fluff.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate L1–L3 capability maps, value chain mapping, capability heat maps, capability maturity assessments, journey-to-capability alignment, capability investment prioritization, and operating model design. Also specifies output formats (PPTX, XLSX, HTML) and optional lenses. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate L1–L3 business capability maps aligned to journey stages, with multiple output formats and lenses) and 'when' (explicit 'Use this skill whenever...' clause with extensive trigger phrases and scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'capability map,' 'capability model,' 'capability gap analysis,' 'business architecture,' 'map our capabilities,' 'what capabilities do we need,' 'where should we invest,' 'who owns what capability,' and 'product operating model.' These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on business capability mapping aligned to journey stages. The specific domain terminology (L1–L3 capability maps, capability maturity, journey-to-capability alignment) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive and well-structured conceptually, covering a complex business capability mapping domain with clear pillar definitions, optional lenses, supplemental tabs, and industry adaptation examples. However, it is significantly over-verbose — much of the conceptual explanation and detailed lens/tab specifications could be condensed or moved to reference files. The lack of validation checkpoints in the workflow and the absence of inline executable code (deferred to external files) weaken its actionability and workflow clarity.
Suggestions
Move the detailed supplemental tab specifications (People/Process/Tools, Industry Benchmark, Roadmap, Capability Definitions) into a separate reference file like references/supplemental-tabs.md, keeping only a brief summary and link in the main SKILL.md.
Cut conceptual explanations that Claude can infer — e.g., remove paragraphs explaining why pillars are separate, what L2 vs L3 means conceptually, and why shared tags exist. Replace with terse rules.
Add explicit validation checkpoints: after Step 2, verify L3 count per L2 is within 2-5 range, verify all shared tags reference valid L1 names, and verify no duplicate L3 names within the same L2. After Step 3, verify the output file was created and is non-empty.
Include at least one inline executable Python code snippet showing the core XLSX generation pattern (e.g., creating the Capability Map sheet with headers and conditional formatting) rather than deferring all code to external files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines with extensive explanations of conceptual models, pillar relationships, and lens definitions that Claude could derive from much shorter instructions. Tables explaining what 'Ad-hoc' vs 'Optimized' means, lengthy descriptions of what each pillar represents, and detailed explanations of why shared capabilities exist all consume tokens explaining concepts Claude already understands. | 1 / 3 |
Actionability | The skill provides a clear workflow (gather context → generate → build output) and specific column structures, naming conventions, and formatting rules. However, the actual code for generating outputs is deferred to external reference files (references/output-formats.md, design-system.md), and no executable code examples are provided inline beyond the Python environment setup. The generation logic itself is conceptual rather than executable. | 2 / 3 |
Workflow Clarity | The three-step workflow (Gather Context → Generate → Build Output) is clearly sequenced with substeps, and the input modes are well-defined. However, there are no validation checkpoints — no step to verify the generated map is complete, no check that all L1s have appropriate L2/L3 depth, no verification that shared tags are consistent, and no feedback loop for when output generation fails. | 2 / 3 |
Progressive Disclosure | The skill appropriately references external files (references/output-formats.md, design-system.md, layout-grids.md) for format-specific details, which is good progressive disclosure. However, the main SKILL.md itself is a monolithic wall of text with massive inline content about supplemental tabs (People/Process/Tools, Industry Benchmark, Roadmap, Capability Definitions) that could each be separate reference files, keeping the main skill leaner. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (501 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents