CtrlK
BlogDocsLog inGet started
Tessl Logo

grill-with-docs

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

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 admirably lean and gives a concrete delegation instruction, but as a workflow it lacks any guidance on sequencing, integrating the two sub-skills' outputs, or structural organization. Adding a brief note on order and expected outputs would raise workflow_clarity and progressive_disclosure.

Suggestions

Specify the order and purpose of the two sub-skills (e.g., run grilling first to refine the plan, then domain-modeling to produce ADRs/glossary), and how their outputs combine.

Add minimal section structure (e.g., a short header) even for a one-line skill so the intent is unambiguous.

Include a one-line expectation of the resulting artifacts (ADR(s) and glossary entries) so the end state is clear.

DimensionReasoningScore

Conciseness

The entire body is a single sentence ("Call the Skill tool twice, for "grilling" and "domain-modeling".") with zero padding and no explanation of concepts Claude already knows. Every token earns its place.

5 / 5

Actionability

It gives concrete, executable guidance naming exactly which two Skill tool calls to make ("grilling" and "domain-modeling"), but provides no detail on what to do with the sub-skills' outputs or how to integrate them. Mostly executable with a minor gap.

4 / 5

Workflow Clarity

A two-step delegation is sequenced ("Call the Skill tool twice"), but there is no guidance on ordering, integration of the two sub-skills' outputs, or any checkpoint. The sequence is present yet checkpoints/coordination are missing.

3 / 5

Progressive Disclosure

No bundle files exist and the body references none, which is acceptable for a sub-50-line skill, but the body has no section headers or organization at all — just a single unstructured line. Some structure is present implicitly but it is not well-organized.

3 / 5

Total

15

/

20

Passed

Description

53%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 conveys what the skill does with two concrete actions and a distinct niche, but lacks an explicit "Use when..." trigger clause and comprehensive trigger terms. Adding when-to-use guidance would lift completeness and trigger_term_quality.

Suggestions

Append an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when refining a plan/design or producing ADRs/glossary entries).

Add natural trigger terms and synonyms users would actually say (e.g., 'refine a plan', 'stress-test a design', 'architecture decision records', 'ADR').

Expand the action list slightly for more comprehensive capability coverage rather than two high-level actions.

DimensionReasoningScore

Specificity

Names the domain ("interview to sharpen a plan or design") and two concrete actions ("sharpen a plan or design", "creates docs (ADR's and glossary)"), but coverage is not comprehensive. It sits at the anchor listing 1-2 concrete actions without being a full inventory.

3 / 5

Completeness

The description gives a clear "what" (relentless interview that sharpens a plan/design and creates docs) but no "when"/"Use when..." clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords exist ("interview", "plan or design", "ADR's", "glossary", "docs") but common user-facing variations are missing and there is no natural trigger phrase. It has some relevant keywords without comprehensive synonym coverage.

3 / 5

Distinctiveness Conflict Risk

The pairing of an adversarial "interview to sharpen a plan or design" with "ADR's and glossary" output carves a fairly specific niche with only minor overlap risk against generic planning skills.

4 / 5

Total

13

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
The-Vibe-Company/companion
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.