grill-with-docs

Stress-test a plan, design, or idea against the project's domain language (CONTEXT.md) and recorded decisions (docs/adr/). One question at a time, walks the decision tree, captures crystallized terminology and decisions inline. THIS IS THE DEFAULT GRILLING SKILL — use for any interrogation in a real project, even if CONTEXT.md or docs/adr/ don't exist yet (they get created lazily on first term resolution / first ADR-worthy decision). Triggers: /grill-with-docs, "grill me", "grill this", "interrogate this plan", "stress-test this design", "walk me through the decisions", "challenge this". Use grill-me ONLY for pure green-field thinking with no codebase at all — rare.

Quality

96%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

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 is concise, highly actionable, and has excellent workflow clarity with a clear six-step process, embedded validation, and explicit stop conditions. The four sharpening modes with example dialogue give Claude precise behavioral guidance. The main weakness is the dependency on two referenced format files (CONTEXT-FORMAT.md, ADR-FORMAT.md) that are not provided in the bundle, which could leave Claude without critical formatting instructions.

Suggestions

Include CONTEXT-FORMAT.md and ADR-FORMAT.md in the bundle, or inline the essential format rules directly in the skill to ensure Claude can produce correct output even if the referenced files are missing.

Dimension	Reasoning	Score
Conciseness	Every section earns its place. No unnecessary explanations of what grilling is or how conversations work. The skill assumes Claude's intelligence and focuses on novel, project-specific instructions like the ADR threshold, sharpening modes, and stop conditions.	3 / 3
Actionability	Highly actionable: four concrete sharpening modes with example dialogue, a strict three-part ADR threshold test, explicit stop conditions, a copy-paste-ready closing summary template, and hard rules. Claude knows exactly what to do at each stage.	3 / 3
Workflow Clarity	Clear six-step sequence from anchoring a plan through pre-flight, grilling, inline capture, stop conditions, and closing summary. Validation is embedded throughout (check glossary conflicts, verify against code, ADR threshold gate). The inline-capture-not-batch rule acts as a continuous checkpoint.	3 / 3
Progressive Disclosure	References to CONTEXT-FORMAT.md and ADR-FORMAT.md are well-signaled and one level deep, which is good. However, these bundle files are not provided, so the references cannot be verified. The skill itself is well-structured with clear sections, but the missing bundle files limit the score since the skill depends on them for format specifications.	2 / 3
	Total	11 / 12 Passed

Description

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 a strong skill description that clearly articulates what the skill does (stress-tests plans against project context and ADRs), when to use it (explicit trigger phrases and situational guidance), and how it differs from a similar skill (grill-me). The description is detailed without being padded, uses third person voice appropriately, and provides excellent disambiguation guidance for skill selection.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: stress-test a plan/design/idea, walk the decision tree, capture crystallized terminology and decisions inline, reference CONTEXT.md and docs/adr/. These are specific, actionable capabilities.	3 / 3
Completeness	Clearly answers both 'what' (stress-test plans against domain language and recorded decisions, walk decision tree, capture terminology) and 'when' (explicit triggers listed, default grilling skill for real projects, distinction from grill-me for green-field). Has explicit 'Use when' equivalent guidance.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms: '/grill-with-docs', 'grill me', 'grill this', 'interrogate this plan', 'stress-test this design', 'walk me through the decisions', 'challenge this'. These are phrases users would naturally say.	3 / 3
Distinctiveness Conflict Risk	Clearly distinguishes itself from a related 'grill-me' skill by specifying this is for real projects with codebases while grill-me is for pure green-field. The domain-specific triggers ('/grill-with-docs') and explicit differentiation guidance make conflicts unlikely.	3 / 3
	Total	12 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: belchman/claude-skills
Commit: be88d6c

Reviewed: 23 days 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.