CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

grill-me

A relentless interview to sharpen a plan or design.

Quality

75%

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-me/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 a maximally lean dispatcher: one sentence that unambiguously tells Claude how to run the session, with excellent token efficiency and clear single-action workflow. Its weaknesses are that all substance is delegated to an external, non-bundled resource with no failure guidance if that resource is missing.

Suggestions

Bundle the grilling skill (or its instructions) inside this skill's directory and reference it with a relative path, making the skill self-contained and portable.

Add a one-line fallback for when neither the Skill tool nor the referenced file is available, so the actionability gap (an unresolvable external dependency) is closed.

DimensionReasoningScore

Conciseness

The body is a single sentence — "Run a grilling session: call the Skill tool with 'grilling', or, in a harness with no Skill tool, load and follow ~/.agents/skills/grilling/SKILL.md" — with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching the lean-and-efficient anchor exactly.

5 / 5

Actionability

The guidance is concrete and executable as written: an exact tool invocation ("call the Skill tool with 'grilling'") plus an explicit fallback path. It falls short of fully executable, however, because the entire instruction depends on an external resource that is not part of the bundle and does not resolve in this environment, and no guidance is given for the case where neither the skill nor the path is available.

4 / 5

Workflow Clarity

This is a simple, single-task skill and the single action is unambiguous: invoke the grilling session via one of two clearly differentiated paths (Skill tool if available, else load the named file). The simple-skill exception applies, and there are no destructive or batch operations that would impose a validation cap.

5 / 5

Progressive Disclosure

The reference to the detailed material is clearly signaled and exactly one level deep, which is good structure. It does not reach 5 because the reference points outside the skill's own bundle to a home-directory path (~/.agents/skills/grilling/SKILL.md) that is not part of this skill and does not exist here, leaving the bundle with no content of its own and a non-portable organization gap.

4 / 5

Total

18

/

20

Passed

Description

50%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 is concise and grammatically clean, with a clear statement of what the skill does, but it is uniformly middling across all dimensions. It lacks any when-to-use trigger guidance, misses most natural trigger phrases a user would say, and carries moderate conflict risk from the ambiguous word "interview" and the broad plan/design domain.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to be grilled, stress-tested, or challenged on a plan, design, or decision before committing to it."

Include the natural phrases users would actually say — "grill me", "poke holes in this plan", "stress test", "challenge my assumptions" — to improve trigger term coverage.

Disambiguate "interview" from job-interview contexts, e.g., "interrogates the user with probing questions" instead of a bare "interview", reducing conflict risk.

DimensionReasoningScore

Specificity

"A relentless interview to sharpen a plan or design" names the mechanism ("relentless interview") and one concrete outcome ("sharpen a plan or design"), matching the anchor for domain plus 1-2 concrete actions that are not comprehensive. It is not a 4 because it lists no further specific actions (e.g., probing questions, identifying weaknesses, stress-testing assumptions), and not a 2 because the action verb is concrete rather than generic.

3 / 5

Completeness

The "what" is clearly stated ("A relentless interview to sharpen a plan or design") but there is no "when" guidance at all — no "Use when..." clause or equivalent trigger phrasing. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3, and the anchor for a clear 'what' with 'when' missing is an exact fit.

3 / 5

Trigger Term Quality

The description contains some relevant natural keywords ("interview", "plan", "design") but is missing common variations users would actually say such as "grill me", "stress test", "poke holes", "critique", or "challenge my assumptions". This matches the anchor for some relevant keywords with missing synonyms; more than "a few" natural terms are absent, so it does not reach 4.

3 / 5

Distinctiveness Conflict Risk

The phrase "interview" risks collision with job-interview-preparation skills, and the broad "plan or design" domain overlaps with plan-review, design-critique, and brainstorming skills. It is somewhat specific — the relentless-interview mechanism is distinctive — but could still overlap with similar skills, matching anchor 3 rather than 4's "minor overlap risk".

3 / 5

Total

12

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

phatblat/dotfiles

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.