New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Caveman Experiment Manager

by JuliusBrussee in JuliusBrussee/caveman

Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Caveman Experiment Manager

skills CLI
$ npx skills add JuliusBrussee/caveman --skill caveman-manage -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JuliusBrussee/caveman caveman-manage --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JuliusBrussee/caveman.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/caveman-manage .claude/skills/caveman-manage && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
caveman-manage
GitHub stars
111k
Used in
1 other repo
Token cost
~975 tokens
SKILL.md length
411 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
Apache-2.0

At a glance

Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.

  • Works in 5 steps: Load project and experiment → Evaluate evidence → Propose one action → …
  • Reviewing the current state of a Caveman Cloud experiment
  • SKILL.md covers Non-negotiable gates, Step 1 — Load project and…, Step 2 — Evaluate evidence and Step 3 — Propose one action, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill treats every lifecycle change to a Caveman Cloud experiment as a production control action. The agent loads the project and experiment through the Caveman MCP tools, or the caveman cloud experiments commands as a fallback, then reports the lifecycle state, control and candidate sample sizes, the quality or eval result, latency, error and cost guardrails, and whether the result is pending, failed, promotable or active.

It then proposes a single action from a short allowed list that includes start, approve, cancel and rollback. Missing evidence is never treated as a pass, approval needs complete passing evidence, and unknown states or server errors are reported as blocks with the exact error code. The agent does not supply an organization id and does not run a lifecycle mutation even after you approve, because the current agent MCP is read-only.

When your agent uses it

  • Reviewing the current state of a Caveman Cloud experiment
  • Checking whether an experiment's evidence supports approval
  • Handling a request to start, cancel or roll back an experiment, which gets checked and reported rather than executed

Example prompts

  • “Show me the results for our latest Caveman experiment and tell me if it can be approved.”
  • “Can we roll back the active Caveman experiment? Check what the evidence says first.”
  • “List my Caveman experiments and flag any with incomplete evidence.”

Requirements

  • A logged-in Caveman Cloud identity
  • The Caveman MCP server or the caveman command line tool

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Load project and experiment
  2. Evaluate evidence
  3. Propose one action
  4. Block unsafe execution
  5. Re-read after external operator action

What it can do on your machine

Read from SKILL.md and the folder at commit 2e08b91. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Caveman Experiment Manager loads about 975 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 411 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~975

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JuliusBrussee/caveman at commit 2e08b91, republished under its Apache-2.0 licence (© JuliusBrussee). 411 words, ~975 tokens.

Download SKILL.mdSave it as .claude/skills/caveman-manage/SKILL.md (or your agent's skills folder).
name
caveman-manage
description
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.

Manage eval-gated experiments

Treat every lifecycle change as a production control action. Read current state and results, then report one supported recommendation or block. Current agent MCP is intentionally read-only: control-api does not yet enforce a complete lifecycle transition table and evidence gate atomically.

Non-negotiable gates

  1. A request to review, inspect, explain, or recommend authorizes reads only.
  2. Never approve an experiment whose results are pending, whose required guardrails are absent, or whose evidence reports a breach.
  3. Never convert experiment lift into verified_savings. Only active real traffic plus provider-causal, provider-complete ledger evidence can do that.
  4. Never supply an organization id. Project and tenant scope come from the logged-in Caveman identity and server RBAC.
  5. Never execute a lifecycle mutation, even after user approval. Exact <action>:<experiment_id> strings are agent-generatable and are not proof of human intent.
  6. Unknown states and server errors fail closed. Report exact cave_snake_code.

Step 1 — Load project and experiment

Prefer MCP:

text
caveman_context {}
caveman_experiment_get {"action":"get","experiment_id":"<id>"}
caveman_experiment_get {"action":"results","experiment_id":"<id>"}

Use {"action":"list"} when the user has not named an id.

CLI fallback:

bash
caveman cloud experiments list
caveman cloud experiments show <id>
caveman cloud experiments results <id>

Stop if login, project, experiment, or results are unavailable.

Step 2 — Evaluate evidence

Report:

  • current lifecycle state and safety class;
  • control and candidate sample sizes;
  • quality or eval result;
  • latency, error, cost, retry, drop, and escalation guardrails when present;
  • evidence cost;
  • rollback or hold reason;
  • whether result is pending, failed, promotable, or active.

Absence is not a pass. If a required field is absent, state evidence incomplete and do not propose approval.

Show full SKILL.md (170 more words)Show less

Step 3 — Propose one action

Allowed actions:

  • start — only from a startable draft or queued state with configured graders;
  • approve — only with complete passing evidence and a safety class the current role may approve;
  • cancel — stop a non-active experiment the user no longer wants;
  • rollback — revert an active or harmful change through the server's linked policy path. Current deployments may reject this honestly with cave_not_implemented; never describe that response as a rollback.

Show recommendation and id:

text
Proposed action: approve experiment 7f...
Reason: candidate passed quality and every configured guardrail.
Execution: blocked until server-authoritative lifecycle and evidence gates ship.

Do not treat earlier generic statements such as "manage it" or "do what is best" as mutation approval.

Step 4 — Block unsafe execution

Do not emit or run an executable lifecycle command. Explain that current server does not yet enforce every evidence/state transition atomically. CLI and MCP agent surfaces therefore expose experiment reads only.

Step 5 — Re-read after external operator action

If operator says they executed command, read detail and results again. Report server-observed post-state, audit or result response, and any policy-delivery status returned. Never infer success from operator intent alone.

Use this close:

text
Action: <action> <experiment-id>
Before: <state>
Server response: <status and cave_snake_code if any>
After: <re-read state>
Basis: experiment evidence only. Verified savings unchanged unless the signed
ledger independently records active, provider-causal real-traffic savings.

© JuliusBrussee, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/caveman-manage of JuliusBrussee/caveman.

Open the folder on GitHubat commit 2e08b91

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in JuliusBrussee/caveman, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Caveman Experiment Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Caveman Experiment Manager compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Caveman Experiment Manager this skillJuliusBrussee/caveman111k1 repos~975Automated safety check: PassApache-2.0
Agents Best PracticesDenisSergeevitch/agents-best-practices2.4k—~7.4kAutomated safety check: PassMIT
Octocode Benchmark Runnerbgauryy/octocode949—~2.1kAutomated safety check: PassMIT
AI Project Copilotsun461941-hub/ai-project-copilot97—~3kAutomated safety check: PassMIT
LLM Eval Pipeline Auditai-evals-course/evals-skills1.5k—~2.5kAutomated safety check: PassApache-2.0
Opik Evaluatecomet-ml/opik-mcp220—~2.5kAutomated safety check: NotesApache-2.0

Similar skills

  • Agents Best Practices

    DenisSergeevitch/agents-best-practices

    A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain.

    2.4k GitHub stars~7.4k tokensUpdated 6 days ago
    AI & LLM EngineeringAuto-check passed

  • Octocode Benchmark Runner

    bgauryy/octocode

    Runs blind pairwise comparisons of Octocode against a gh-based baseline over markdown research questions, scored by total characters through the model rather than self-report.

    949 GitHub stars~2.1k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • AI Project Copilot

    sun461941-hub/ai-project-copilot

    A skill your agent uses to turn an AI idea or existing repository into a credible open-source product and to run evidence-first repository engineering across codebase discovery, context-efficient…

    97 GitHub stars~3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • LLM Eval Pipeline Audit

    ai-evals-course/evals-skills

    Inspects an LLM evaluation setup for missing error analysis, unvalidated judges and vanity metrics, and ranks the problems by impact with fixes.

    1.5k GitHub stars~2.5k tokensUpdated 16 days ago
    AI & LLM EngineeringAuto-check passed

  • Opik Evaluate

    comet-ml/opik-mcp

    Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link.

    220 GitHub stars~2.5k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check: notes

  • Agent Eval Cases

    agentailor/fullstack-langgraph-nextjs-agent

    Decide which AI agent behaviors are worth an eval case, then write those cases — harness-, framework-, and language-agnostic.

    132 GitHub stars~5.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from JuliusBrussee/caveman

All 18 skills in this repo

  • Caveman Workflow Labeler

    JuliusBrussee/caveman

    Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow.

    111k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • Caveman Evidence Review

    JuliusBrussee/caveman

    Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.

    111k GitHub starsUsed in 1 repo~927 tokens
    Auto-check passed

  • Caveman Optimization Evaluator

    JuliusBrussee/caveman

    Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

    111k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed

  • Caveman Gateway Setup

    JuliusBrussee/caveman

    Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

    111k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check: warnings

  • Caveman Help Card

    JuliusBrussee/caveman

    Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".

    111k GitHub stars~690 tokensUpdated 2 days ago
    Auto-check passed

  • Caveman Mode

    JuliusBrussee/caveman

    Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact.

    111k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Caveman Experiment Manager

What does Caveman Experiment Manager do?

Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself. This skill treats every lifecycle change to a Caveman Cloud experiment as a production control action. The agent loads the project and experiment through the Caveman MCP tools, or the caveman cloud experiments commands as a fallback, then reports the lifecycle state, control and candidate sample sizes, the quality or eval result, latency, error and cost guardrails, and whether the result is pending, failed, promotable or active.

When should I use Caveman Experiment Manager?

Caveman Experiment Manager fits situations like: reviewing the current state of a Caveman Cloud experiment; checking whether an experiment's evidence supports approval; handling a request to start, cancel or roll back an experiment, which gets checked and reported rather than executed.

How do I install Caveman Experiment Manager in Claude Code?

Run `npx skills add JuliusBrussee/caveman --skill caveman-manage -a claude-code`. Or copy the skill folder (skills/caveman-manage in JuliusBrussee/caveman) into .claude/skills/caveman-manage in your project. Claude Code loads it when a task matches its description.

How do I install Caveman Experiment Manager in Codex?

Run `npx skills add JuliusBrussee/caveman --skill caveman-manage -a codex`. Or copy the skill folder (skills/caveman-manage in JuliusBrussee/caveman) into .agents/skills/caveman-manage in your project. Codex loads it when a task matches its description.

Can I use Caveman Experiment Manager in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JuliusBrussee/caveman --skill caveman-manage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/caveman-manage, .gemini/skills/caveman-manage, .github/skills/caveman-manage and .opencode/skills/caveman-manage in your project.

What does Caveman Experiment Manager need to run?

SKILL.md names no scripts, command-line tools or credentials: Caveman Experiment Manager is instructions for the agent only. Our summary lists: A logged-in Caveman Cloud identity; The Caveman MCP server or the caveman command line tool.

Does Caveman Experiment Manager access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Caveman Experiment Manager safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Caveman Experiment Manager use?

Caveman Experiment Manager is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Caveman Experiment Manager use?

About 975 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Caveman Experiment Manager?

Skills that share tags, products or a category with Caveman Experiment Manager: Agents Best Practices (DenisSergeevitch/agents-best-practices, 2.4k stars), Octocode Benchmark Runner (bgauryy/octocode, 949 stars), AI Project Copilot (sun461941-hub/ai-project-copilot, 97 stars) and LLM Eval Pipeline Audit (ai-evals-course/evals-skills, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Caveman Experiment Manager?

JuliusBrussee (a GitHub user) maintains it in JuliusBrussee/caveman, which has 110,815 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 9, 2026.

Source: JuliusBrussee/caveman on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.