caveman-manage

Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.

Quality

93%

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

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.

An exceptionally tight, actionable control-plane skill with explicit validation checkpoints and feedback loops appropriate to destructive lifecycle gating. The only structural opportunity is extracting the gate catalogue into a reference file for cleaner progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Lean and token-efficient; it assumes Claude's competence, explains no generic concepts, and every line carries operational weight.	5 / 5
Actionability	Provides exact MCP and CLI commands, copy-paste-ready report templates, and per-action guardrail conditions, fully covering the common cases.	5 / 5
Workflow Clarity	A clear five-step sequence with explicit fail-closed checkpoints ('Stop if login, project... unavailable', 'Absence is not a pass') and a re-read feedback loop after operator action.	5 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with no nested references; no bundle files exist, so splitting is limited, and the inline gate list is reasonable but could live in a reference file.	4 / 5
	Total	19 / 20 Passed

Description

87%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, specific description that pairs a clear capability statement with an explicit trigger clause tied to concrete lifecycle verbs. Minor gains would come from adding synonyms or state-name variations to the trigger list.

Dimension	Reasoning	Score
Specificity	Names the domain ('Caveman Cloud's experiment lifecycle') and concrete actions ('Inspect', 'block unsafe execution'), with minor gaps in enumerating the full inspection surface.	4 / 5
Completeness	Clearly answers both 'what' (inspect lifecycle and block unsafe execution) and 'when' with an explicit 'Use when...' clause naming concrete trigger actions.	5 / 5
Trigger Term Quality	'Use when asked to start, approve, cancel, promote or roll back a Caveman experiment' lists natural verb-based triggers a user would say, though a few synonyms or state-name variations are missing.	4 / 5
Distinctiveness Conflict Risk	The 'Caveman Cloud experiment lifecycle' niche is highly specific with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	18 / 20 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: JuliusBrussee/caveman
Path: skills/caveman-manage/SKILL.md
Commit: 15581d1

Reviewed: 4 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.