Name: grill-with-docs
Rating: 68 (1 reviews)
Author: alirezarezvani

grill-with-docs

Docs-anchored grilling session — challenges a plan against the project's existing language (CONTEXT.md) and recorded decisions (docs/adr/), and updates those files inline as terminology and decisions crystallise. Use when user wants to stress-test a plan against documented domain language, or mentions "grill with docs".

Quality

83%

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

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

Quality

Content

73%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 skill body with a strong validated workflow, held back by missing bundle files. Several referenced paths (CONTEXT-FORMAT.md, ADR-FORMAT.md, references/*.md, scripts/*.py) do not exist, undermining the progressive-disclosure structure the body promises.

Suggestions

Provide the referenced bundle files (CONTEXT-FORMAT.md, ADR-FORMAT.md, and the three references/*.md) or remove the links to avoid dangling references.

Bundle the three scripts the body invokes (context_md_linter.py, adr_scanner.py, glossary_code_consistency.py) under scripts/ so the executable commands actually run.

Trim the top provenance/derivation paragraph to a single line; the full attribution already lives in the frontmatter metadata.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes competence, but the top provenance paragraph and the wrapper-intro lines plus mild table/bullet redundancy add over-explanation that could be trimmed.	4 / 5
Actionability	Concrete executable commands (scripts/context_md_linter.py CONTEXT.md, adr_scanner.py docs/adr/) and the precise 3-criteria ADR test give clear direction, but some dialogue snippets are illustrative rather than literal steps.	4 / 5
Workflow Clarity	Clear 3-phase sequence (Pre-flight / During / Closing) with explicit validation re-runs (re-run linter after structural edits, re-run scanner after writing an ADR, final consistency run).	5 / 5
Progressive Disclosure	The body signals one-level-deep references (CONTEXT-FORMAT.md, ADR-FORMAT.md, references/.md, scripts/.py) but none of the referenced bundle files exist, so the disclosure is not actually backed by real artifacts.	2 / 5
	Total	15 / 20 Passed

Description

92%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, concise description that names a precise niche, concrete actions, and an explicit trigger clause with a natural phrase. Trigger-term breadth is the only minor limitation, being a single coined phrase plus one scenario rather than a spread of synonyms.

Dimension	Reasoning	Score
Specificity	Concrete actions are explicit: "challenges a plan against the project's existing language (CONTEXT.md) and recorded decisions (docs/adr/)" and "updates those files inline as terminology and decisions crystallise", covering its niche comprehensively.	5 / 5
Completeness	Explicitly answers both "what" (challenges a plan, updates CONTEXT.md/docs/adr inline) and "when" ("Use when user wants to stress-test a plan against documented domain language, or mentions \"grill with docs\"").	5 / 5
Trigger Term Quality	Natural trigger phrases are present ("stress-test a plan against documented domain language", mentions "grill with docs"), but coverage is narrower than a 5-anchor list of synonyms/extensions.	4 / 5
Distinctiveness Conflict Risk	Clear niche (docs-anchored grilling against CONTEXT.md glossaries and ADRs) with a distinct trigger phrase ("grill with docs"), minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/grill-with-docs/SKILL.md
Commit: 19392f7

Reviewed: ~8 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.