grill-with-docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has good completeness with an explicit 'Use when' clause and a distinctive niche combining plan review with domain modeling and documentation updates. However, the specificity could be improved by replacing metaphorical language ('grilling session', 'sharpens') with more concrete actions, and trigger term coverage could be broadened to include more natural user phrasings. The use of second person ('your plan') should also be noted as a minor style issue.
Suggestions
Replace metaphorical language like 'grilling session' and 'sharpens terminology' with concrete actions such as 'Reviews and challenges proposed plans against the existing domain model, identifies terminology inconsistencies, and updates documentation'.
Add more natural trigger term variations in the 'Use when' clause, e.g., 'review my plan', 'validate design decisions', 'check against domain model', 'architecture review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('plan', 'domain model', 'terminology') and some actions ('challenges your plan', 'sharpens terminology', 'updates documentation'), but the actions are somewhat abstract—'grilling session' and 'sharpens terminology' are more metaphorical than concrete. It does mention specific artifacts (CONTEXT.md, ADRs) which adds some concreteness. | 2 / 3 |
Completeness | Clearly answers both 'what' (challenges plan against domain model, sharpens terminology, updates CONTEXT.md and ADRs) and 'when' (explicit 'Use when user wants to stress-test a plan against their project's language and documented decisions'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'stress-test', 'plan', 'domain model', 'ADRs', 'CONTEXT.md', and 'terminology', but misses common natural variations a user might say such as 'review my plan', 'domain-driven design', 'architecture review', 'challenge my design', or 'validate decisions'. The trigger terms are somewhat niche. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'grilling session', domain model challenge, terminology sharpening, and specific artifact updates (CONTEXT.md, ADRs) creates a clear niche that is unlikely to conflict with generic planning, documentation, or code review skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%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 conversational skill that is concise, highly actionable for its domain (interactive design review), and uses progressive disclosure effectively by referencing format files. Its main weakness is the lack of an explicit workflow sequence or session completion criteria — the behaviors are described as concurrent concerns rather than a clear process with checkpoints.
Suggestions
Consider adding brief session completion criteria or a wrap-up step (e.g., 'End the session when all branches of the design tree are resolved and CONTEXT.md reflects all agreed terms').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what grilling sessions are or how interviews work. The file structure examples are compact and directly useful for orientation. Instructions are directive and assume Claude's competence. | 3 / 3 |
Actionability | Provides concrete, specific guidance: exact phrases to use when challenging terminology ('Your glossary defines X...'), precise criteria for ADR creation (three conditions), explicit file formats referenced, and clear behavioral instructions (ask one at a time, update inline, don't batch). The guidance is instruction-oriented rather than code-oriented, which is appropriate for this conversational skill. | 3 / 3 |
Workflow Clarity | The session workflow is implicit rather than explicitly sequenced — it describes behaviors to exhibit during the session (challenge glossary, sharpen language, discuss scenarios, cross-reference code, update CONTEXT.md) but doesn't clearly sequence them or define when the session is complete. There's no explicit validation checkpoint or completion criteria, though the inline-update-as-you-go approach is a partial feedback loop. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections (what-to-do, supporting-info with subsections). References to CONTEXT-FORMAT.md and ADR-FORMAT.md are one level deep and clearly signaled. Content is appropriately split — the skill overview stays lean while pointing to format details in separate files. | 3 / 3 |
Total | 11 / 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.
- Repository
- mattpocock/skills
- Commit
0288510
- 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.