agentleFS
juancruzmunozalbelojuancruzmunozalbelo/swarmclaw/.claude/skills/setup-minimax/SKILL.md

setup-minimax

Skill1 starsChanged 9 months agoMITView on GitHub

Configure NanoClaw + Claude Code to use MiniMax via the Anthropic-compatible endpoint. Use when user says "minimax", "MiniMax-M2.5", "anthropic compatible", "base url", or wants cheaper tokens with Claude Code.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Do NOT commit secrets to git.

    line 24
  2. Very specific:

    If you want to use a .env, keep it minimal and gitignored:

    line 55
  3. Distinctive:

    Run NanoClaw and trigger an agent run.

    line 72
  4. Distinctive:

    If Apple Container is used:

    line 74
  5. Distinctive:

    If Docker is used:

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Setup MiniMax (Anthropic-Compatible)

Goal: make NanoClaw containers call MiniMax (not Anthropic) using the Anthropic-compatible API.

1) Preconditions (macOS)

Check runtime:

uname -s
which container && container system status || true
which docker && docker info >/dev/null 2>&1 && echo "docker ok" || true

NanoClaw can run on Apple Container or Docker. Prefer Apple Container on Apple silicon if already installed.

2) Configure Host Environment Variables

Do NOT commit secrets to git.

Required:

  • MINIMAX_API_KEY (your MiniMax key)

Recommended:

  • ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic
  • ANTHROPIC_MODEL=MiniMax-M2.5
  • ANTHROPIC_SMALL_FAST_MODEL=MiniMax-M2.5
  • ANTHROPIC_SMALL_MODEL=MiniMax-M2.5
  • ANTHROPIC_SMALL_REASONING_MODEL=MiniMax-M2.5
  • ANTHROPIC_SONNET_MODEL=MiniMax-M2.5

Optional:

  • API_TIMEOUT_MS=3000000
  • CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1

Sanity check (should print without errors, but never print the key):

echo "${MINIMAX_API_KEY:+MINIMAX_API_KEY set}"
echo "${ANTHROPIC_BASE_URL:-missing}"
echo "${ANTHROPIC_MODEL:-missing}"

3) Configure NanoClaw Auth

NanoClaw passes secrets to the agent container via stdin. It can read:

  • .env in the project root (keys: CLAUDE_CODE_OAUTH_TOKEN or ANTHROPIC_API_KEY)
  • host env vars as a fallback (recommended for MiniMax)

If you want to use a .env, keep it minimal and gitignored:

cat > .env <<'EOF'
# Secrets (optional). Prefer host env vars.
# ANTHROPIC_API_KEY=...
EOF

4) Build Agent Image

./container/build.sh

5) Verify in Practice

Run NanoClaw and trigger an agent run. If the key is wrong you will see an auth error.

If Apple Container is used:

container system status

If Docker is used:

docker info >/dev/null

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.