CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman-setup

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

70

Quality

85%

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

88%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-engineered integration skill: highly actionable with executable per-framework recipes, a clearly sequenced five-step workflow with real-request verification, and explicit failure templates for error recovery. It is dense but not padded, with only minor conciseness trim and no need for bundle-file splitting given its scope.

DimensionReasoningScore

Conciseness

The body is dense and purposeful — per-SDK wiring recipes and curl commands with no padding about what SDKs or LLMs are — though explanatory prose like 'Two facts that make the wiring safe (both are gateway-enforced, not hopes)' could be trimmed slightly, fitting the efficient-with-minor-trim anchor rather than the fully lean 5.

4 / 5

Actionability

Copy-paste-ready executable code is given for each major SDK (OpenAI TS/Python, Anthropic, Vercel, LangChain, LiteLLM, raw HTTP) plus concrete verification curl commands, covering the common cases and matching the fully-executable top anchor.

5 / 5

Workflow Clarity

Steps 1–5 are explicitly sequenced with a validation checkpoint in Step 4 ('Success = HTTP 200 with a usage block') and verbatim failure templates that supply fix-and-retry feedback loops for each error class, matching the clear-sequence-with-explicit-validation anchor.

5 / 5

Progressive Disclosure

Structure is clear with section headers and the only out-of-file references ('<docs origin>/docs/integrations/' and 'discover-workflows.md') are well-signaled and one level deep; because no bundle files exist, the inline per-SDK recipes are appropriately placed, though the body is a single dense file rather than split reference material, keeping it just under the top anchor.

4 / 5

Total

18

/

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 tight, third-person description that clearly states both the capability and explicit trigger phrases, with a distinct product niche that minimizes conflict risk. Its only weakness is modest action specificity — it describes one wiring action rather than enumerating several concrete operations.

DimensionReasoningScore

Specificity

Names the domain and the core actions — 'Wire a repository through the Caveman Cloud gateway' and 'every LLM request is measured, with no behavior change' — but it is essentially one wiring action rather than a list of several specific actions, so it fits the 1-2 concrete actions anchor rather than the 4 anchor.

3 / 5

Completeness

Explicitly answers both what ('Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change') and when ('Use for "set up caveman" or adding LLM spend observability') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases 'set up caveman' and 'adding LLM spend observability' that a user would plausibly say, giving good keyword coverage; it is short of a 5 because it lacks synonyms or file-extension-style variants.

4 / 5

Distinctiveness Conflict Risk

The 'Caveman Cloud gateway' / 'set up caveman' niche is highly specific with a distinct product trigger, so overlap with other skills is minimal; it matches the clear-niche, minimal-conflict anchor.

5 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.