Index of every page on this site: llms.txt
All skills
shubhamsaboo avatar

/advisor-orchestrator-worker

@14c5f8f
Run it yourself

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple models, split work across a model team, run an advisor-worker loop, have a stronger model review the plan while cheap workers execute, or says "too big for one model" or "fan this out". Not for single-file edits or tasks one model handles in one pass.

Use this Skill: https://skilld.dev/gh/shubhamsaboo/awesome-llm-apps/advisor-orchestrator-worker

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

referencesworker-brief.md

≈300 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Worker Brief Format

Every worker dispatch is one stateless call (an agy CLI run, or a Gemini API request on the fallback path) containing this brief. The worker has no memory, no follow-ups, and sees nothing but this text. Inputs must be pasted inline in full; never reference material the worker cannot see. For code subtasks that means the entrypoint, file layout, and exact run commands; otherwise workers invent their own.

You are a worker completing ONE subtask of a larger project. This brief
is everything you get. No follow-ups are possible.

SUBTASK: <one-line goal>
INPUTS: <everything needed, inline and complete>
ACCEPTANCE CRITERIA (output fails if any fail):
1. <criterion>
2. <criterion>
3. <criterion>
OUTPUT FORMAT: <exact structure, length, style>

Rules: do only the subtask, no scope expansion, no editorializing. If an
input is missing or contradictory, write INPUT GAP plus one line naming
it at the top, then proceed with what you have. Return only the
deliverable, no preamble.

Redispatch rule: when a result comes back FIX, send a new brief that quotes the failed criterion and names the specific failure. Never reply to the old call; every dispatch is fresh.

Source: SKILL.md on GitHub

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.

3 warnings16d3 checks · Risk MEDIUM
  • Gen Agent Trust Hub16d

    The skill orchestrates a multi-model workflow using CLI tools and API fallbacks. Security risks include a potential shell injection vulnerability when passing prompts to the `agy` CLI using command substitution, and the use of a flag to bypass security permissions during command execution. The skill implements positive security practices such as temporary directory isolation for subtasks and safe JSON handling for its API communication fallbacks.

  • Socket2mo

    1 alert: gptAnomaly

  • Snyk16d

    Risk: MEDIUM · 1 issue

Signed by skilld at 14c5f8f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 months ago
Other metadata
metadata
{
  "author": "Shubham Saboo",
  "version": "1.0.0",
  "source": "https://github.com/Shubhamsaboo/awesome-llm-apps"
}
compatibility
Makes network calls: workers via the Antigravity CLI (agy), falling back to the Gemini API (GEMINI_API_KEY or GOOGLE_API_KEY); advisor via the claude CLI, falling back to the Anthropic API (ANTHROPIC_API_KEY). Needs jq. All snippets are bash. Runs in any harness that can execute shell commands.

README badge

README badge for shubhamsaboo/awesome-llm-apps/advisor-orchestrator-worker