CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator-smoke-test

Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to run G3 (positive smoke) and G4 (negative smoke) gates against a candidate meta-skill SKILL.md. Cross-vendor: fixture-generation LLM != classifier LLM. Returns JSON.

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 ./src/opensquilla/skills/bundled/skill-creator-smoke-test/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 concise, well-structured, actionable spec for a single-purpose agent step with a sensible degraded/total-failure path; its main weakness is the lack of an explicit per-gate validation/recovery loop within the main workflow.

Suggestions

Add an explicit per-gate feedback step (e.g. 'If a gate fails, record which gate and the failure reason in the returned JSON before proceeding to the next gate') to close the validation loop.

Show the expected shape of the G3/G4 return records (fields like passed, reason, degraded) so the contract is unambiguous to the parent step.

DimensionReasoningScore

Conciseness

The body is lean and efficient, with no padding or explanations of concepts Claude already knows; every line (steps, degraded flag, fallback JSON) earns its place.

5 / 5

Actionability

Provides concrete, executable guidance: numbered steps, named function 'simulate_meta_resolution', named inputs, and a literal fallback JSON payload; minor gaps because the function signature and per-fixture invocation details are not shown.

4 / 5

Workflow Clarity

A clear 1-4 sequence is present and G3/G4 act as checkpoints, but per-gate failure handling is only implicit (the explicit fallback covers total agent failure, not how to recover/report when a single gate fails), leaving validation feedback loops underspecified.

3 / 5

Progressive Disclosure

Under 50 lines, single-purpose, no external references needed, and well-organized into an invocation-steps section plus a Fallback section, satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

47%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 specific and distinct for an internal agent step, but it relies entirely on technical jargon and lacks an explicit 'Use when...' trigger clause, so trigger-term quality and completeness are capped low despite a clear what.

Suggestions

Add an explicit trigger clause such as 'Use when the meta-skill-creator DAG needs to validate a candidate meta-skill SKILL.md via smoke gates.'

Introduce at least one natural-language keyword (e.g. 'smoke test', 'validate meta-skill') alongside the G3/G4 jargon so the trigger is legible beyond the DAG context.

DimensionReasoningScore

Specificity

Lists several concrete actions such as 'run G3 (positive smoke) and G4 (negative smoke) gates', 'Called by meta-skill-creator as a DAG step (kind: agent)', and 'fixture-generation LLM != classifier LLM', naming the mechanism and inputs with only minor coverage gaps.

4 / 5

Completeness

'What' is clear (runs G3/G4 smoke gates against a candidate meta-skill SKILL.md and returns JSON), and 'when' is only implied via 'Called by meta-skill-creator as a DAG step' with no explicit 'Use when...' clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

The terms present ('G3', 'G4', 'DAG step', 'cross-vendor', 'fixture-generation LLM') are pure technical/internal jargon with no natural user-facing keywords, matching the anchor for 'only technical jargon'; this is intentional for an internal agent step but still scores per the rubric.

1 / 5

Distinctiveness Conflict Risk

Occupies a clearly distinct niche (cross-vendor smoke-gating of meta-skill candidates with degraded-mode fallback) with trigger context unlikely to fire for any other skill.

5 / 5

Total

13

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
TokenRhythm/opensquilla
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.