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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 with executable code and a well-sequenced, validation-gated workflow, but it is verbose for the context window and keeps all material in one large file with no progressive disclosure via references.

Suggestions

Tighten the body by collapsing the repeated 'Verify before proceeding:'/'Verify:' prompts into a single concise checklist and trimming placeholder comments in the code and test templates.

Move the 'Common Issues' troubleshooting list and/or the full unit-test template into a reference file under references/, linking to it from the relevant step to reduce the main SKILL.md footprint and improve progressive disclosure.

Consider shortening the three 'Examples' to one canonical end-to-end example plus a pointer, since the code template in the Instructions already conveys the pattern.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and project-specific, but the ~275-line body includes a full test template with placeholder comments, eight 'Common Issues' entries, and repeated 'Verify before proceeding:'/'Verify:' prompts that could be tightened without losing clarity.	2 / 3
Actionability	Provides fully executable TypeScript templates for the check function, constants, registration, and tests, plus concrete commands such as 'grep -r "'your_unique_check_id'" src/scoring/checks/' and 'npm test src/scoring/__tests__/accuracy.test.ts'; substitution placeholders are clearly labeled rather than pseudocode.	3 / 3
Workflow Clarity	Five numbered steps (constants, check function, platform filtering, registration, tests) are clearly sequenced, each with an explicit validation checkpoint (e.g., grep for ID uniqueness, run npm test) and a troubleshooting 'Common Issues' section for error recovery.	3 / 3
Progressive Disclosure	Well-organized into labeled sections, but it is a single ~275-line monolithic file with no bundle references; content that could live in separate files (full test template, Common Issues) is inline, so it does not meet the one-level-deep reference structure of the top anchor.	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 specific, action-oriented, and answers both what and when with explicit natural-language triggers and a clear negative guardrail. It is distinguishable from other skills and uses correct third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with specific artifacts: 'Add a new deterministic scoring check in src/scoring/checks/', 'Follows the Check[] return pattern', 'uses point constants from src/scoring/constants.ts', and 'integrates via filterChecksForTarget() in src/scoring/index.ts'.	3 / 3
Completeness	Clearly answers what ('Add a new deterministic scoring check... Follows the Check[] return pattern, uses point constants... integrates via filterChecksForTarget()') and when ('Use when user says...'), with explicit positive and negative triggers.	3 / 3
Trigger Term Quality	Provides natural quoted phrases users would say ('add scoring check', 'new check', 'modify scoring criteria') plus the concrete working-location cue 'works in src/scoring/checks/', giving good coverage of likely utterances.	3 / 3
Distinctiveness Conflict Risk	A narrow niche (scoring checks in a specific codebase path) with distinct triggers, reinforced by an explicit negative trigger ('Do NOT use for display changes or refactoring scoring logic') that sharply reduces the chance of firing for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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: caliber-ai-org/ai-setup
Path: .claude/skills/scoring-checks/SKILL.md
Commit: 7950921

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.