CtrlK
BlogDocsLog inGet started
Tessl Logo

check-scripts

Run a phased scripts audit in scripts/*.py: validate Script overrides (init/title/show) first, then verify ui() output compatibility with run() or process() parameters.

59

Quality

68%

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 ./.github/skills/check-scripts/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, clearly sequenced audit workflow with strong pass/fail criteria and good organization, but it is somewhat verbose and lacks executable code examples or concrete mismatch/fix illustrations that would make it fully copy-paste ready.

Suggestions

Tighten the verbose checklist bullets in Required Checks A/B/C (e.g., merge the 'method exists / signature valid / returns non-empty' lines) to reduce token cost.

Add one or two short concrete examples of a detected mismatch and its minimal fix (e.g., a ui() returning 4 values feeding a run() with 3 positional params) to lift actionability.

Optionally add the explicit validation command/workflow (how to run the audit and confirm pass criteria) so the procedure is executable end-to-end.

DimensionReasoningScore

Conciseness

The body is mostly efficient task-specific guidance with little padding of concepts Claude already knows, but it is fairly long and several checklist items are verbose or repeat surrounding context, so it could be tightened.

2 / 3

Actionability

It gives concrete, specific audit instructions and references real contract files (modules/scripts_manager.py, modules/scripts_postprocessing.py), but provides no executable code/commands or concrete examples of mismatches and fixes — guidance is instructive but not copy-paste executable.

2 / 3

Workflow Clarity

It lays out a clearly sequenced phased procedure (A: overrides first, B: ui vs run/process, C: runner compatibility) with an explicit numbered Procedure, a Reporting Format, and a Pass Criteria including a conditional-pass feedback loop for dynamic cases that cannot be proven statically.

3 / 3

Progressive Disclosure

The body is well-organized into clearly labeled sections (When To Use, Scope, Required Checks A/B/C, Procedure, Reporting Format, Pass Criteria); no bundle files exist to reference and the content is appropriately self-contained at one level, which suits a sub-50-section single-purpose skill.

3 / 3

Total

10

/

12

Passed

Description

67%

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 concrete and specific with a clearly distinct niche around script-class contract auditing, but it lacks an explicit 'Use when...' trigger clause and leans on framework jargon rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when adding or changing scripts/*.py, when a script crashes on selection/execution, or before a PR to gate script API compatibility').

Include natural trigger terms users would actually say (e.g., 'script crash', 'UI args mismatch', 'script API compatibility', 'pre-PR check') alongside the current framework jargon.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (validate Script overrides for init/title/show, verify ui() output compatibility with run()/process() parameters) and names the exact target files (scripts/*.py).

3 / 3

Completeness

It clearly answers 'what does this do' (phased scripts audit validating overrides and ui/run/process contracts) but has no 'Use when...' clause; the 'when' is only implied, so completeness is capped at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Contains relevant technical terms like 'scripts audit', 'Script overrides', 'ui()', 'run()', 'process()', but these are framework jargon rather than natural phrases a user would say, and it lacks common trigger variations a user might actually utter.

2 / 3

Distinctiveness Conflict Risk

The niche is narrow and highly specific (Script class overrides and ui()->run()/process() parameter contracts in scripts/*.py), making it clearly distinguishable and unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

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
vladmandic/sdnext
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.