CtrlK
BlogDocsLog inGet started
Tessl Logo

scoring-checks

Add a new deterministic scoring check in src/scoring/checks/ that evaluates config quality. Follows the Check[] return pattern, uses point constants from src/scoring/constants.ts, and integrates via filterChecksForTarget() in src/scoring/index.ts. Use when user says 'add scoring check', 'new check', 'modify scoring criteria', or works in src/scoring/checks/. Do NOT use for display changes or refactoring scoring logic.

72

Quality

88%

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

The canonical home for this skill is scoring-checks in caliber-ai-org/ai-setup

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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-sequenced with strong validation checkpoints, making it easy to follow for the target task. Its main weakness is conciseness and progressive disclosure: content is verbose and entirely inline where splitting Examples/Common Issues into reference files would reduce the SKILL.md footprint.

Suggestions

Move the 'Examples' and 'Common Issues' sections into reference files (e.g. references/examples.md, references/troubleshooting.md) and link to them from SKILL.md to improve progressive disclosure and reduce the inline token load.

Trim the recurring 'Verify:'/'Check existing patterns:' asides into a single consolidated checklist at the end of each step rather than repeating them inline.

Condense the Common Issues section to the highest-frequency pitfalls, or relocate it to a troubleshooting reference, to tighten conciseness.

DimensionReasoningScore

Conciseness

Mostly actionable templates rather than concept explanation, but it could be tightened — repeated 'Verify:'/'Check existing patterns:' asides and a lengthy Common Issues section pad the body beyond what each token strictly earns.

2 / 3

Actionability

Provides complete, copy-paste-ready TypeScript check/test templates with concrete commands (`npm test ...`, `grep -r ...`) and clear placeholder substitution, fully executable once identifiers are filled in.

3 / 3

Workflow Clarity

Steps 1–5 are explicitly sequenced with validation checkpoints ('Verify ID uniqueness', 'Verify registration', 'Run tests... All must pass before shipping') and feedback loops for error recovery.

3 / 3

Progressive Disclosure

Well-organized into sections but monolithic — ~275 lines all inline with no bundle/reference files, and content like the Examples and Common Issues sections could be split into separate references rather than living in the overview.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 precise, action-oriented, and well-scoped: it states concrete capabilities, gives natural trigger phrases, and adds explicit exclusions. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Add a new deterministic scoring check', 'Follows the Check[] return pattern', 'uses point constants from src/scoring/constants.ts', and 'integrates via filterChecksForTarget()' — rather than vague language.

3 / 3

Completeness

Explicitly answers what (add a deterministic scoring check using the Check[] pattern and constants) and when ('Use when user says...'), with explicit trigger guidance.

3 / 3

Trigger Term Quality

Provides natural user phrasings — 'add scoring check', 'new check', 'modify scoring criteria', plus 'works in src/scoring/checks/' — that a user would realistically say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (deterministic scoring checks) with distinct triggers and explicit negative scoping ('Do NOT use for display changes or refactoring scoring logic'), minimizing conflict with adjacent skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
caliber-ai-org/ai-setup
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.