CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rag-change-lab

Compatibility alias for the rag skill. Use only when the user explicitly invokes the older rag-change-lab name; otherwise use rag for offline-first retrieval and answer validation.

Quality

90%

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

100%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 model compatibility alias: a fully executable delegation to a specific file, explicit anti-duplication guidance, and zero wasted tokens. It is a simple single-purpose skill and satisfies every rubric dimension at the top anchor under the rubric's simple-skill provisions.

DimensionReasoningScore

Conciseness

Three lean lines with zero padding, no explanation of concepts Claude already knows, and every token earning its place (including the anti-duplication directive). This matches anchor 5 exactly.

5 / 5

Actionability

"Read and follow `.agents/skills/rag/SKILL.md`" is a concrete, executable instruction with a specific path, and the delegation covers the alias's single use case completely. Per the rubric's scoring notes, absence of code in an instruction-only skill is not penalized when the guidance is actionable, which it fully is.

5 / 5

Workflow Clarity

The simple-skill exception applies: this is a single-task skill (delegate to rag) with an unambiguous single action, and it involves no destructive or batch operations that would require validation checkpoints. Anchor 5 under the simple-skill allowance.

5 / 5

Progressive Disclosure

At under 50 lines with no external references needed, the simple-skill allowance scores well-organized content 5; its one reference (`.agents/skills/rag/SKILL.md`) is clearly signaled and exactly one level deep, and no bundle files exist to introduce structural problems.

5 / 5

Total

20

/

20

Passed

Description

75%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 an exemplary compatibility-alias description: it answers what and when explicitly, and actively defuses trigger conflict with the newer rag skill. Its only weakness is thin keyword coverage and specificity, since the concrete capabilities described belong to the target skill and lack common synonyms.

Suggestions

Add natural synonyms for the underlying capability (e.g., "retrieval-augmented generation", "RAG pipeline") so users' natural phrasing matches the trigger terms.

Briefly enumerate one or two more concrete functions of the target rag skill (e.g., "chunks and indexes documents, validates answers against sources") to raise specificity beyond the two currently named.

DimensionReasoningScore

Specificity

Names the domain and 1-2 concrete functions ("offline-first retrieval and answer validation") but these describe the target rag skill rather than actions this alias performs, and coverage is not comprehensive. It clears anchor 2 by naming concrete capabilities, but does not list several specific actions needed for anchor 4.

3 / 5

Completeness

"Compatibility alias for the rag skill" clearly answers what this is, and "Use only when the user explicitly invokes the older rag-change-lab name" is an explicit, concrete when-clause with routing guidance otherwise. It matches anchor 5 (both what and when with concrete trigger phrases); the when cannot be made more explicit.

5 / 5

Trigger Term Quality

Contains relevant keywords ("rag", "rag-change-lab", "retrieval", "answer validation") but misses common variations and synonyms a user would naturally say, such as "retrieval-augmented generation" or "RAG pipeline". This matches anchor 3 (some relevant keywords, missing common variations) rather than anchor 4's good-but-incomplete coverage.

3 / 5

Distinctiveness Conflict Risk

The description explicitly disambiguates against the sibling skill ("otherwise use rag") and restricts triggering to explicit old-name invocation, giving it a clear niche with minimal conflict risk. It fits anchor 5; anchor 4's "minor overlap risk" understates how directly the conflict with rag is resolved.

5 / 5

Total

16

/

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

BigSimmo/PsychSift

Path

.agents/skills/rag-change-lab/SKILL.md

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.