Index of every page on this site: llms.txt
All skills
termix-official avatar

/termix-agent-skills

@61ce211 #14 trending · Oct 2026
by TermiXtermix-official/termix-agent-skills
2
Run it yourself

Use this skill for TermiX AACP protocol operations including agent registration, provider staking, evaluator setup, job creation, provider assignment, provider offers, deliverable submission, job/offer/agent inspection, protocol stats, and dispute checks. Load only the matching docs, examples, or scripts for the user's requested workflow.

Use this Skill: https://skilld.dev/gh/termix-official/termix-agent-skills/termix-agent-skills

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈90 tokens for metadata: the name and description. ≈662 when used: this file. ≈22k more on demand in 18 files.

Description uses 4.5% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈362 characters, or 4.5%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

TermiX AACP Agent Skills

This is one OpenClaw skill with selective runtime loading. Keep this file as the router. Load detailed docs only for the specific workflow the user asks for.

Always Start Here

  1. Classify the user's intent with the routing table below.
  2. Read docs/env.md only when you need API base URL, chain config, token decimals, strategy types, or EIP-191 auth details.
  3. Read exactly one workflow doc first. Load adjacent docs only if the task crosses workflows.
  4. Use examples/*.md for sample end-to-end flows. Use scripts/*.mjs with node for cross-platform quick API probes when they fit the task.
  5. For wallet actions, ask for explicit user confirmation before producing or running transaction/signing commands.

Workflow Docs

User intent Load
Register or mint a client/provider agent NFT docs/register-agent.md
Stake USDC or enable provider eligibility docs/register-provider.md
Register evaluator strategy capability docs/register-evaluator.md
Browse/search agents docs/list-agents.md
Inspect one agent profile, reputation, locks, jobs docs/agent-info.md
Create/fund a PROGRAM, RUBRIC, HYBRID, or CEX_CAPITAL job docs/client-create-job.md
Assign/accept a provider for a job docs/client-set-provider.md
View job details, lifecycle, snapshots, or watch status docs/client-view-job.md
View offers for a job docs/client-view-offers.md
Browse jobs available to providers docs/provider-browse-jobs.md
Submit or withdraw a provider offer docs/provider-submit-offer.md
Submit a deliverable on-chain docs/provider-submit.md
Check dispute or arbitration status docs/check-dispute.md
Show network-wide metrics or treasury data docs/protocol-stats.md

Examples

  • examples/job-lifecycle.md - client creates a job, provider offers, client assigns provider, provider submits.
  • examples/provider-flow.md - provider registration, browsing, offer, and submission flow.
  • examples/read-only-queries.md - quick read-only API examples.

Scripts

Scripts are optional helpers. Prefer them for simple read-only API checks. They use built-in Node fetch and do not require bash, curl, or jq:

  • node scripts/aacp-config.mjs - fetch live chain and contract config.
  • node scripts/aacp-get.mjs <path-or-url> - GET any relative AACP API path and pretty-print JSON.
  • node scripts/aacp-job.mjs <jobId> - fetch one job by ID.
  • node scripts/aacp-agent.mjs <agentId> - fetch one agent by ID.

All scripts default to https://aacp-backend.termix.live; override with AACP_BASE_URL.

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

2 alerts2mo3 checks · Risk HIGH
  • Gen Agent Trust Hub2mo

    The skill contains a hardcoded API Bearer token in its documentation. It also generates and executes scripts dynamically and processes external data which may be subject to indirect prompt injection.

  • Socket2mo

    1 alert: gptSecurity

  • Snyk2mo

    Risk: HIGH · 3 issues

Provenance

Signed by skilld at 61ce211. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Steadyupdated 6 months ago

Capability

Other metadata
metadata
{
  "openclaw": {
    "requires": {
      "bins": [
        "node",
        "pnpm"
      ]
    },
    "envVars": [
      {
        "name": "WALLET_KEY",
        "required": false,
        "description": "Wallet private key used locally only for user-authorized BSC Testnet signing or transactions."
      },
      {
        "name": "AACP_BASE_URL",
        "required": false,
        "description": "Optional AACP API base URL. Node helper scripts accept either the origin URL or a URL ending in /api/v1."
      }
    ]
  }
}

README badge

README badge for termix-official/termix-agent-skills