metis-strategy/metis-legal-drafting
Draft Statements of Work (SOWs) from client templates and Metis proposals, and review/redline Master Services Agreements (MSAs) from the Supplier perspective. Triggers on SOW drafting, MSA review, contract redlining, scope creep analysis, deliverable tables, invoice schedules, IP carve-outs, or any mention of SOW, MSA, master agreement, statement of work, redline, or contract review in the context of Metis Strategy engagements.
73
92%
Does it follow best practices?
Impact
—
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 clearly articulates specific capabilities (SOW drafting, MSA redlining), provides comprehensive trigger guidance with natural keywords consultants would use, and establishes a distinct niche tied to Metis Strategy consulting engagements. The description uses proper third-person voice throughout and balances thoroughness with clarity. The only minor concern is that it's somewhat lengthy, but the detail is substantive rather than padded.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: drafting SOWs from templates and proposals, reviewing/redlining MSAs, risk analysis, scope creep checking, preparing legal documents. Also mentions specific sub-tasks like deliverable tables, invoice schedules, IP carve-outs, and indemnification review. | 3 / 3 |
Completeness | Clearly answers both 'what' (draft SOWs, review/redline MSAs from supplier perspective) and 'when' with an explicit and detailed 'Use this skill whenever...' clause covering multiple trigger scenarios and specific keyword mentions. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'SOW', 'MSA', 'master agreement', 'statement of work', 'redline', 'contract review', 'draft an SOW', 'populate a client SOW template', 'risk analysis', 'scope creep', 'deliverable tables', 'invoice schedules', 'IP carve-outs', 'indemnification review'. These are terms consultants would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: SOW drafting and MSA redlining specifically in the context of Metis Strategy consulting engagements from the Supplier perspective. The domain-specific terms (IP carve-outs, indemnification, Metis proposals) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with well-structured multi-step workflows, concrete code examples, and clear validation checkpoints. Its main weakness is length — at ~300 lines, it includes substantial inline content (technical patterns, key protections summaries, calibration guidance) that could be offloaded to reference files, and some sections like 'Metis Strategy Context' add marginal value. The workflows themselves are excellent, with proper gating (don't start without both documents, don't edit without approval) and practical error-handling patterns.
Suggestions
Move the Technical Patterns section to a separate reference file (e.g., references/docx-patterns.md) and link to it from the main skill — this would save ~60 lines of context window space.
Consider moving the 'Key Protections for Consulting Firms' and 'Calibrating Recommendations' sections into references/msa-risk-checklist.md since they duplicate content that file should already contain.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-written and most content earns its place, but there's some verbosity — e.g., the 'Metis Strategy Context' section tells Claude things it doesn't need (team structure, deliverable formats), the tone/relationship management section is somewhat preachy, and some instructions repeat points already covered in referenced files (e.g., 'Key Protections for Consulting Firms' summarizes the risk checklist). However, the technical patterns and workflow steps are tight and useful. | 2 / 3 |
Actionability | The skill provides fully executable python-docx code snippets for text replacement, smart quote handling, SDT extraction, paragraph insertion, table formatting, and file locking. Workflows have concrete steps with specific questions to ask, exact formatting specs (e.g., #1F3864 header color), and clear output expectations (deliverable tables, risk analysis format, Word Compare workflow). | 3 / 3 |
Workflow Clarity | Both main workflows are clearly sequenced with numbered steps, explicit validation checkpoints (scope comparison before finalizing SOW, risk analysis approval before editing MSA), and feedback loops (get consultant approval before making edits, flag scope creep for review). The cross-document consistency check adds another validation layer. The 'never edit without explicit direction' gate in MSA review is a strong safety checkpoint. | 3 / 3 |
Progressive Disclosure | The skill references external files well (references/firm-metadata.md, references/sow-patterns.md, references/msa-risk-checklist.md) with clear signals to read them before starting each workflow. However, no bundle files were provided to verify these exist, and the SKILL.md itself is quite long (~300 lines) with substantial inline content (Key Protections, Insurance Comparison, Scope Comparison Methodology, Technical Patterns) that could arguably live in reference files. The technical patterns section in particular could be a separate file. | 2 / 3 |
Total | 10 / 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.
Reviewed
Table of Contents