CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman-discover

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

67

Quality

81%

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

81%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.

A well-structured, highly actionable instruction-only skill with a clear five-step workflow, explicit validation, and a feedback loop for the code-changing operation. It is slightly held back by minor redundancy in the intro and the absence of copy-paste code examples for each SDK.

Suggestions

Consolidate the 'operator-invoked / propose-then-apply' guidance into one place; it is currently repeated in the intro and again in Step 3.

Add one short copy-paste code snippet per major SDK (e.g. the defaultHeaders block for the OpenAI/Anthropic SDK) so the labeling mechanism is fully executable rather than described.

Consider moving the per-SDK labeling mechanism table into a references file and linking to it from Step 3 to tighten the SKILL.md overview.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no basic-concept padding), but the operator-invoked / 'propose then apply' point is stated twice (intro and Step 3), which is a minor instance of over-explanation that could be trimmed, keeping it at 4 rather than 5.

4 / 5

Actionability

It gives concrete, specific guidance — exact header name 'x-cave-workflow', slug grammar, per-SDK option names, dashboard path, and the 400 error code — but it names options without copy-paste code syntax for each SDK, so it is mostly-executable rather than fully copy-paste ready, fitting the 4 anchor.

4 / 5

Workflow Clarity

Five clearly sequenced numbered steps each with their own section, an explicit validation checkpoint in Step 4, and an error-recovery feedback loop ('the gateway rejects an invalid label with 400 ... fix the slug if so'), plus a propose-before-apply checkpoint, matching the anchor for clear sequence with explicit validation and feedback loops.

5 / 5

Progressive Disclosure

The content is well-organized into clear ## sections and external references (the setup skill, docs path) are one level deep and signaled, but the skill is ~107 lines with no bundle files and the per-SDK labeling mechanism list is inlined rather than split out, leaving minor organization gaps that fit 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

82%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.

A strong, third-person description that clearly states both the capability and when to invoke it, with a distinct niche and low conflict risk. The only soft spot is specificity, which lists just two concrete actions rather than a comprehensive set.

DimensionReasoningScore

Specificity

The description names the domain (LLM workflows in a repository) and two concrete actions ('Find and label every LLM workflow'), matching the anchor for 1-2 concrete actions that are not comprehensive; it does not list several actions, so it stays at 3 rather than 4.

3 / 5

Completeness

It explicitly answers both 'what' (find and label every LLM workflow so Caveman Cloud groups spend by workflow) and 'when' (an explicit 'Use for ...' clause with concrete trigger phrases), matching the anchor for a clear and explicit what-and-when with concrete triggers.

5 / 5

Trigger Term Quality

It includes natural trigger phrases a user would say ('discover workflows', 'breaking LLM spend down by workflow') giving good keyword coverage, but is missing common synonyms such as 'tag' or 'categorize workflows', so it is 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The niche is highly specific (LLM workflow labeling for Caveman Cloud spend grouping) with distinct triggers and minimal overlap risk with other skills, matching the clear-niche anchor.

5 / 5

Total

17

/

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

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
JuliusBrussee/caveman
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.