agent-orchestration-skill

Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor / canvas-designer / coder, etc.). **Not for**: single-step Q&A / reads / simple side effects (master Agent handles directly), or scenarios where `Agent` is already confirmed and `subagent_type` is known.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./apps/server/src/ai/builtin-skills/agent-orchestration/en/SKILL.md

Quality

Content

75%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.

A well-structured, actionable reference that routes delegation decisions through clear tables, flow diagrams, and concrete tool-call examples. It is efficient and easy to navigate, with only minor room to tighten and to split detail into reference files.

Dimension	Reasoning	Score
Conciseness	Mostly lean: tables and ASCII flow diagrams convey dense information efficiently and the content is system-specific rather than restating general knowledge; a few rationale columns and the streaming-events detail could be trimmed without loss.	4 / 5
Actionability	Provides concrete, copy-pattern-ready invocation examples (Agent {…}, SendMessage {…}, parallel fan-out) plus exact parameter and limit tables; minor gaps in that subagent prompt bodies are illustrative rather than filled in.	4 / 5
Workflow Clarity	The Delegation Decision tree gives a clear, sequenced routing flow with explicit branches, and Common Misjudgments act as guardrails; no explicit validate-then-proceed checkpoints, but this is a decision-routing skill rather than a destructive/batch operation.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no monolithic wall and no nested references; as a single ~130-line file with no bundle files it is appropriately structured, though all detail lives inline rather than being split out.	4 / 5
	Total	16 / 20 Passed

Description

76%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.

A strong, explicit description that clearly states what it does, when it triggers, and when not to use it. Its main weakness is trigger phrasing grounded in internal system vocabulary rather than the natural language users actually say.

Suggestions

Add user-facing trigger phrases alongside the system terms, e.g. 'Use when the user asks to scrape a site, edit a long document, analyze a spreadsheet, or OCR a PDF' so natural synonyms map to the skill.

Tie each named subagent to the concrete user task it serves (browser→web scraping/forms, extractor→OCR) to convert jargon into recognizable triggers.

Include common file extensions or task verbs users mention (e.g. '.xlsx', 'screenshot', 'convert PDF') to broaden natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete delegation targets (browser / doc-editor / data-analyst / extractor / canvas-designer / coder), giving specific coverage rather than a single abstract action, but the core action ('outsource sub-tasks') is itself one verb repeated across targets.	4 / 5
Completeness	Explicitly answers both what ('outsource sub-tasks to built-in subagents') and when ('Triggers when the master Agent faces a multi-step complex task'), plus a concrete 'Not for' exclusion set, satisfying the explicit-trigger requirement.	5 / 5
Trigger Term Quality	Triggers lean on system-internal jargon ('master Agent', 'subagents', 'subagent_type') rather than natural user phrases like 'scrape this site' or 'analyze this spreadsheet'; relevant keywords exist but common user-facing synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	The 'Not for' exclusions (single-step Q&A/reads, Agent already confirmed with known subagent_type) carve out a clear niche and reduce overlap, though 'multi-step complex task' is still a broad trigger.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: itsablabla/openloaf-web
Path: apps/server/src/ai/builtin-skills/agent-orchestration/en/SKILL.md
Commit: a1ab5be

Reviewed: 4 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.