CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An exemplary lean instruction-only skill: every sentence drives behavior, sequencing is unambiguous, and the decision-tracing command is fully specified with its no-op fallback documented. The only improvements would be a filled-in example of the trace call and slightly more explicit handling of when to stop probing a branch.

DimensionReasoningScore

Conciseness

The ~15-line body is lean and assumes Claude's competence: every line instructs behavior (ask one at a time, explore the codebase instead, record after the decision), and even the trace rationale ('written here and never read', 'unconfigured, the call is a silent no-op') is operationally necessary rather than padding. Matches anchor 5 with nothing to trim.

5 / 5

Actionability

Concrete, instruction-appropriate guidance including a fully specified copy-paste command ('sh scripts/trace.sh emit kind=grill.decision ... outcome=accepted|overridden ... || :') with inline argument semantics. Minor gaps keep it below anchor 5: the bracketed optional subject placeholder requires interpretation and no filled-in example call is shown.

4 / 5

Workflow Clarity

The interview loop is clearly sequenced: one question at a time, walk each branch resolving dependencies one-by-one, record each decision 'after the decision, never in place of it', terminate at shared understanding, with the accepted/overridden distinction acting as an outcome checkpoint. No further explicit validation is present, though the interactive, non-destructive nature makes anchor 5's error-recovery loops largely inapplicable — anchor 4 is the best fit.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external reference files; all content is appropriately inline and well-organized, and the only external touchpoints (the trace script, the LICENSE pointer, the '/grill-with-docs' alternative) are one level deep and clearly signaled. The missing-script case is explicitly handled ('unconfigured, the call is a silent no-op'), and the trace script is a run target, not a nested detail file, so the simple-skill exception applies cleanly.

5 / 5

Total

18

/

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 clearly states what the skill does and when to use it, with natural trigger phrases including the distinctive literal "grill me". Its only weaknesses are minor: a few missing natural synonyms and slight overlap risk with plan-review skills via the 'stress-test a plan' phrasing.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'Interview the user relentlessly about a plan or design', 'resolving each branch of the decision tree' — in third person. It falls short of anchor 5 only because coverage is not fully comprehensive (e.g., no hint of the per-question recommendation behavior), and it is well above anchor 3's '1-2 concrete actions'.

4 / 5

Completeness

Explicitly answers both parts: a clear 'what' ('Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree') and an explicit 'Use when' clause with concrete trigger phrases. This matches the anchor 5 example pattern directly.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say: 'stress-test a plan', 'get grilled on their design', and the literal trigger "grill me". Common variations like 'poke holes in my plan', 'challenge my design', or 'critique my plan' are missing, keeping it below anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The interactive-interview framing and the quoted "grill me" trigger give it a clear niche with minimal conflict risk, but 'stress-test a plan' and 'get grilled on their design' have minor overlap with general plan-review/critique skills, matching anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/trace.sh)

Warning

Total

13

/

16

Passed

Repository

agranado2k/agentic-sdlc

Path

.agents/skills/grill-me/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.