CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

grill-with-docs

Grilling session that challenges your plan against the existing domain model, sharpens terminology, captures long-form rationale, and updates documentation (CONTEXT.md, ADRs, skills, TA notes) inline as decisions crystallise. Use when user wants to stress-test a plan, explain why a tool/guardrail was chosen, build teacher-assistant material, or align work with their project's language and documented decisions.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 delivers concrete, well-sequenced instructional guidance with strong approval gates and little wasted explanation. Its main defect is that both referenced format files are missing from the bundle, breaking navigation and leaving the CONTEXT.md and ADR formats unspecified.

Suggestions

Create the referenced CONTEXT-FORMAT.md and ADR-FORMAT.md bundle files (or inline compact format templates), since both links currently point to files that do not exist.

Consolidate the Project Thread guidance, which currently appears in both <what-to-do> and <supporting-info>, into one section to remove redundancy.

Trim the second ASCII directory tree (the multi-context example) to a one-line description of the CONTEXT-MAP.md convention to tighten token use.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, consisting almost entirely of project-specific non-obvious guidance (CONTEXT-MAP.md convention, #brain-joel Project Threads, the ADR three-condition gate). Minor padding exists in the two ASCII directory trees and the Project Thread guidance duplicated between <what-to-do> and <supporting-info>, fitting anchor 4 rather than 5.

4 / 5

Actionability

Guidance is highly concrete for an instruction-only skill: verbatim question scripts ("Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?"), an exact approval prompt to quote, and the three-condition ADR test. It falls short of anchor 5 because the CONTEXT.md and ADR formats are delegated to referenced files that are absent, leaving an executable gap.

4 / 5

Workflow Clarity

A clear sequence is present — interview one question at a time, explore the codebase where a question is answerable there, grill for long-form rationale, update CONTEXT.md inline, gate ADRs on the three conditions, and ask operator approval before creating a Project Thread — with explicit approval checkpoints. Not anchor 5 because the ordering across the <what-to-do>/<supporting-info> split must be inferred by the reader.

4 / 5

Progressive Disclosure

The body itself is well organized into clear sections, but both referenced format files — [CONTEXT-FORMAT.md](./CONTEXT-FORMAT.md) and [ADR-FORMAT.md](./ADR-FORMAT.md) — do not exist in the bundle, so the promised one-level-deep navigation is broken at runtime. This lands at anchor 3: decent structure but references that fail to resolve.

3 / 5

Total

15

/

20

Passed

Description

83%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 description that explicitly states both capabilities and trigger conditions with concrete phrases. Its only deductions are the second-person voice in the capability statement and somewhat thin synonym coverage for natural trigger terms.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions with named artifacts ("challenges your plan against the existing domain model, sharpens terminology, captures long-form rationale, and updates documentation (CONTEXT.md, ADRs, skills, TA notes) inline"), which would match anchor 5; however, the second-person phrasing "challenges your plan" triggers the rubric's third-person penalty, reducing the score by 1.

4 / 5

Completeness

Both what and when are explicitly and concretely answered: the what lists the grilling/sharpening/capture/doc-update actions, and the when clause ("Use when user wants to stress-test a plan, explain why a tool/guardrail was chosen, build teacher-assistant material, or align work with their project's language and documented decisions") provides four concrete trigger phrases, mirroring the anchor-5 example.

5 / 5

Trigger Term Quality

Natural user phrases like "stress-test a plan", "explain why a tool/guardrail was chosen", and "build teacher-assistant material" are present, but common variations such as "grill me", "interview me about", or "review my design" are missing, matching anchor 4 (good coverage, a few natural terms missing).

4 / 5

Distinctiveness Conflict Risk

The grilling-plus-inline-doc-capture niche is distinct with dedicated triggers, but the broad tail "align work with their project's language and documented decisions" could overlap with generic documentation or planning skills, placing it at anchor 4 (mostly distinct, minor overlap risk).

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

joelhooks/joelclaw

Path

skills/grill-with-docs/SKILL.md

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.