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

88%

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

Quality

Content

85%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.

A well-structured, actionable conversational skill with a clear sequenced workflow and explicit checkpoints. Its main defect is progressive disclosure: the format-reference files it points to are absent from the bundle, leaving dangling links.

Suggestions

Add the referenced CONTEXT-FORMAT.md and ADR-FORMAT.md files to a references/ directory so the inline format links resolve, or inline the minimal format spec directly in SKILL.md.

Remove the redundancy between section 3 and the "Hard rules" block — keep the one-question-at-a-time and read-the-codebase rules in one place.

Either create ATTRIBUTION.md (cited in the trailing comment) or drop the attribution reference to avoid another broken link.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the "Hard rules" section repeats guidance already stated in section 3 ("One question at a time. Wait for the user." and the read-the-codebase rule), a minor redundancy that could be trimmed.	4 / 5
Actionability	Highly actionable for an instruction-only skill: a concrete opening question, a specific file-scan list, four sharpening modes each with example dialogue, a three-criterion ADR threshold, and a copy-paste closing summary template.	5 / 5
Workflow Clarity	A clear six-step sequence (anchor → pre-flight → grill → capture → stop → close) with explicit validation checkpoints: the three-true ADR threshold gate and the five stop conditions act as checklists.	5 / 5
Progressive Disclosure	Sections are well organized, but the body references [CONTEXT-FORMAT.md](CONTEXT-FORMAT.md), [ADR-FORMAT.md](ADR-FORMAT.md), and ATTRIBUTION.md, none of which exist in the bundle (no references/scripts/assets dirs) — these dangling links break navigation exactly where format guidance is needed.	3 / 5
	Total	17 / 20 Passed

Description

91%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.

A strong, specific description with excellent trigger coverage and explicit what/when guidance in third-person voice. Its only weakness is a minor overlap with the sibling grill-me skill that requires explicit disambiguation.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "Stress-test a plan, design, or idea against the project's domain language", "walks the decision tree", "captures crystallized terminology and decisions inline" — in third-person voice, but the actions are somewhat abstract compared to the verb-object precision of a 5.	4 / 5
Completeness	Explicitly answers both what (stress-test plans against CONTEXT.md and docs/adr, one question at a time, capture inline) and when ("THIS IS THE DEFAULT GRILLING SKILL — use for any interrogation in a real project" with concrete trigger phrases).	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage with synonyms users would actually say — "grill me", "grill this", "interrogate this plan", "stress-test this design", "walk me through the decisions", "challenge this" — plus the slash command.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche (interrogation against a real project's domain language) but must explicitly disambiguate from the closely related grill-me skill ("Use grill-me ONLY for pure green-field thinking"), indicating minor overlap risk.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: belchman/claude-skills
Path: plugins/agentic-engineering/skills/grill-with-docs/SKILL.md
Commit: 77a9e6b

Reviewed: 11 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.