grill-with-docs

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/grill-with-docs/SKILL.md

The canonical home for this skill is grill-with-docs in mattpocock/skills

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an admirably lean delegation instruction that correctly assumes Claude's competence and relies on one-level-deep sub-skills for detail. Its only weakness is underspecification: no arguments, call order, or output-integration guidance for the two sub-skill invocations.

Dimension	Reasoning	Score
Conciseness	The body is a single lean sentence ('Call the Skill tool twice, for "grilling" and "domain-modeling".') with zero padding and full assumption of Claude's competence. Every token earns its place, matching anchor 5.	5 / 5
Actionability	The instruction is concrete and directly executable (named tool, named skills, call count), but it specifies no arguments to pass, no call order, and no guidance on combining the two sub-skills' outputs — missing key details per anchor 3. Not 4: the gaps are substantive rather than minor.	3 / 5
Workflow Clarity	As a simple delegating skill, the single action is mostly unambiguous, but the sequencing between the two calls and what to do with results are unspecified — minor gaps matching anchor 4. Not 5: the action is not fully unambiguous; not 3: there are no risky or batch operations requiring validation.	4 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and its detail lives one level deep in the two named sub-skills; nothing that belongs elsewhere is inlined. Per the simple-skill guideline this matches anchor 5.	5 / 5
	Total	17 / 20 Passed

Description

50%Weight 40%Scale 1-5

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 communicates a clear and fairly distinct purpose (adversarial plan interviewing with doc byproducts), but it omits any 'when to use' trigger guidance and its keyword coverage lacks natural user phrasings. It reads as competent yet incomplete, scoring uniformly at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user has a plan, design, or proposal they want challenged, stress-tested, or refined.'

Include natural user phrasings/synonyms such as 'stress test', 'poke holes in', 'challenge', or 'pressure-test my plan' alongside 'interview'.

Replace the editorial word 'relentless' with concrete capability detail, e.g. what the interview covers (assumptions, edge cases, failure modes) and what artifacts are produced (ADR entries, glossary terms).

Dimension	Reasoning	Score
Specificity	The description names the domain ('interview to sharpen a plan or design') and 1-2 concrete actions ('creates docs (ADR's and glossary)'), but 'relentless' is editorial flavor rather than a concrete capability and coverage is not comprehensive. It does not reach anchor 4, which requires several specific listed actions.	3 / 5
Completeness	The 'what' is clear (relentless interview that sharpens a plan and creates ADRs/glossary), but there is no 'Use when...' clause or equivalent trigger guidance, capping this at anchor 3. It is not 4 because 'when' is not even weakly implied.	3 / 5
Trigger Term Quality	Some relevant keywords are present ('interview', 'plan', 'design', 'ADR', 'glossary'), but common natural variations users would say ('stress test my plan', 'challenge this design', 'refine my design') are missing. It is above anchor 2 because the terms are domain-relevant rather than generic.	3 / 5
Distinctiveness Conflict Risk	'Interview to sharpen a plan or design' is a somewhat specific niche, but without trigger guidance it could overlap with plan-review, code-review, or research skills. Not 4: the overlap risk with related review/critique skills is more than minor.	3 / 5
	Total	12 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: koenighotze/wheel-of-meeting
Path: .agents/skills/grill-with-docs/SKILL.md
Commit: 4aca8e3

Reviewed: 16 hours ago

Table of Contents

Discovery Implementation Validation

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.