advisor-orchestrator-worker

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.

Quality

90%

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

88%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.

The body is highly actionable with executable snippets, a well-sequenced validation-heavy workflow, and clean one-level-deep reference navigation. Slight conciseness and organization gains remain from inline rationale and time-sensitive prose.

Suggestions

Move the 'current July 2026' model-version note into a small version/knobs section (or the existing 'Models are knobs' framing) so time-sensitive detail is isolated and easier to update.

Trim the inline rationale sentences (e.g. why --dangerously-skip-permissions and the empty dir are used) into a one-line caveat or relocate to references/fallbacks.md to tighten the hot path.

Consider pulling the worker/advisor dispatch recipe into references/ (e.g. worker-dispatch.md) so the body reads as overview-plus-loop, with the full bash kept one level deep.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich, assuming Claude's competence with no basic-concept padding; minor over-explanation in rationale sentences ('the permissions flag is required...') and inline time-sensitive content ('current July 2026') keep it just below 5.	4 / 5
Actionability	Fully executable, copy-paste-ready bash for both worker dispatch (mktemp, env -i, agy with model/effort/timeout pins) and advisor consult (perl alarm + claude), with specific flags, paths, batch size of 3, and a budget formula covering the common cases.	5 / 5
Workflow Clarity	Clear 7-step loop with explicit validation checkpoints ('run the actual command, read the actual output', PASS/FIX/ESCALATE, redispatch on failure, never silently accept partial pass) and feedback loops for this batch operation.	5 / 5
Progressive Disclosure	SKILL.md is an overview pointing to three real, one-level-deep, clearly signaled references (fallbacks.md, advisor-consult.md, worker-brief.md); minor inline operational rationale that could arguably live in a reference keeps it at 4.	4 / 5
	Total	18 / 20 Passed

Description

92%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.

The description is specific, trigger-rich, and clearly distinguishes itself via an explicit negative boundary, fully answering both what and when. Only minor: a couple of common synonyms are absent.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('parallel research or generation across many subtasks', 'orchestrate multiple models', 'split work across a model team', 'run an advisor-worker loop', 'stronger model review the plan while cheap workers execute') with comprehensive coverage of the niche.	5 / 5
Completeness	Explicitly answers both 'what' (orchestrate/split/review-while-execute) and 'when' ('Use when a task is too large for one model pass... or says "too big for one model" or "fan this out"') with concrete trigger phrases and a negative boundary.	5 / 5
Trigger Term Quality	Includes natural user phrases like "too big for one model", "fan this out", "orchestrate multiple models", and "split work across a model team"; a few synonyms (e.g. parallelize, distribute) are missing, keeping it just below a clean 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (multi-model advisor-worker orchestration) with distinct triggers and an explicit 'Not for single-file edits or tasks one model handles in one pass' boundary that minimizes conflict risk.	5 / 5
	Total	19 / 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: Shubhamsaboo/awesome-llm-apps
Path: agent_skills/advisor-orchestrator-worker/SKILL.md
Commit: 9848ec8

Reviewed: 2 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.