CtrlK
BlogDocsLog inGet started
Tessl Logo

determinize-skill

Use when auditing an existing agent skill (SKILL.md) to find where it leans on LLM judgment for work that could be deterministic, and to emit runnable promptfoo assertions that validate the deterministic parts. Covers two axes — offloading AI steps to code, and constraining AI output format. Triggers for "/determinize-skill PATH", "make this skill more deterministic", "audit a skill for determinism", "where can this skill be deterministic".

77

Quality

97%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 highly actionable and well-structured with a clear sequenced workflow, explicit validation, and well-signaled one-level-deep references. Only minor conciseness trimming is possible; otherwise it is exemplary.

DimensionReasoningScore

Conciseness

Dense and assumes Claude's competence throughout — no elementary concept padding — but a few sections (axes table, output schema, common mistakes table) could be tightened slightly; mostly efficient with minor over-explanation.

4 / 5

Actionability

Provides fully executable guidance: exact exit-code contract (0/10/1), concrete grep patterns, fixed-schema YAML, specific promptfoo assertion types (is-json, regex, not-icontains), and pointer to a real template file.

5 / 5

Workflow Clarity

Mermaid flowchart sequences the work and includes an explicit validation checkpoint (run promptfoo, confirm all assertions pass before reporting ROI) with a feedback loop (fix assertion or underlying fix until all pass).

5 / 5

Progressive Disclosure

Overview body points to two real, one-level-deep reference files (pattern-catalog.md, promptfoo-template.yaml) via clear markdown links, with detail appropriately split out and easy navigation.

5 / 5

Total

19

/

20

Passed

Description

100%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 a model example: specific concrete actions, natural trigger phrases, explicit what-and-when guidance, and a distinct niche. It earns top marks on every dimension with no padding or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — auditing a skill for LLM-judgment steps, offloading to code, constraining output format, and emitting runnable promptfoo assertions — with comprehensive coverage and no vague filler.

5 / 5

Completeness

Explicitly answers both what (find nondeterministic steps and emit runnable assertions) and when ("Triggers for ..." with concrete trigger phrases), satisfying both halves concretely.

5 / 5

Trigger Term Quality

Provides natural trigger phrases users would actually say ("make this skill more deterministic", "audit a skill for determinism", "where can this skill be deterministic") plus the slash command, covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Occupies a clearly distinct niche (determinism auditing with promptfoo assertions) with specific trigger phrases unlikely to collide with general code-review or testing skills.

5 / 5

Total

20

/

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
AndreJorgeLopes/proof-of-skill
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.