Express Spec-Driven Development for setting up project-aware change workflows, documenting domains, planning and applying changes in stages, verifying outcomes, and archiving completed work. Use only when the user explicitly asks for ESDD, references an ESDD command or artifact, or wants to continue an existing ESDD change.
74
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
85%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 well-structured skill description that clearly defines what the skill does with multiple concrete actions and provides an explicit, restrictive 'Use when' clause that minimizes false triggers. Its main weakness is that the trigger terms are heavily reliant on the user knowing the 'ESDD' acronym, which limits discoverability for users who might describe the same workflow in natural language without using that term.
Suggestions
Consider adding a few natural language trigger variations beyond the acronym, such as 'spec-driven development', 'staged change workflow', or 'domain documentation' to improve discoverability for users who may not use the ESDD acronym directly.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'setting up project-aware change workflows, documenting domains, planning and applying changes in stages, verifying outcomes, and archiving completed work.' These are distinct, enumerated capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (setting up project-aware change workflows, documenting domains, planning and applying changes in stages, verifying outcomes, archiving completed work) and 'when' ('Use only when the user explicitly asks for ESDD, references an ESDD command or artifact, or wants to continue an existing ESDD change'). | 3 / 3 |
Trigger Term Quality | The acronym 'ESDD' is a strong trigger term for users who know the methodology, and 'ESDD command or artifact' adds specificity. However, the terms are fairly niche/technical and lack natural language variations a user might say (e.g., 'spec-driven', 'change workflow', 'staged changes'). Users unfamiliar with the acronym wouldn't naturally trigger this. | 2 / 3 |
Distinctiveness Conflict Risk | The description is highly distinctive with the 'ESDD' acronym and the explicit constraint 'Use only when the user explicitly asks for ESDD.' This creates a very clear, narrow trigger that is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that serves as an efficient dispatcher/router. It's concise, actionable, and clearly structured with proper init gating, conditional logic, and progressive disclosure to supporting files. The only minor concern is that without bundle files to verify, we trust the referenced files exist and contain appropriate content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every line serves a purpose—routing logic, gate checks, and action dispatch. No unnecessary explanations of concepts Claude already knows. | 3 / 3 |
Actionability | Provides concrete, executable guidance: a specific CLI command for the init gate check, clear conditional logic for each scenario, and explicit file references for each action. The dispatch table and gate conditions are unambiguous. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced: parse action → check init gate (with specific conditionals and outcomes) → dispatch to action file. Validation is built into the init gate with explicit stop/continue/warn behaviors for each condition. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: SKILL.md serves as a concise router/overview, with clear one-level-deep references to help.md, docs/commands.md, and individual action files (init.md, document.md, etc.). Navigation is well-signaled and organized. | 3 / 3 |
Total | 12 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
2384118
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.