orchestration

Decepticon orchestrator patterns — delegation, state management, adaptive re-planning, context handoff protocols.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/decepticon/orchestration/SKILL.md

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a lean, highly actionable orchestration playbook with clear sequenced workflows, validation checkpoints, and feedback loops. Its main weakness is progressive disclosure: all material lives in one monolithic file with no external reference split.

Suggestions

Split the detailed delegation template and sub-agent selection matrix into a reference file (e.g., references/delegation.md) and link to it from a concise overview in SKILL.md.

Move the recon decision tree and re-planning logic into a separate references/ file, keeping SKILL.md as a high-level overview with one-level-deep links.

Add clearly signaled reference links (e.g., 'See [DELEGATION.md](references/delegation.md)') so navigation to detail is explicit.

Dimension	Reasoning	Score
Conciseness	The body is dense operational content (templates, file trees, decision trees, tables) with no explanations of concepts Claude already knows; every section earns its place, matching the score-3 anchor; not score 2 because there is no unnecessary explanation or padding to tighten.	3 / 3
Actionability	Provides a copy-paste task() delegation template with explicit fields, concrete file paths (plan/opplan.json, findings/FIND-*.md), and exact decision-tree steps — fully executable guidance matching score 3; not score 2 because the template is real code with fill-in placeholders rather than pseudocode.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced ('State Update Protocol' 1–5, 'After Recon Returns — Decision Tree' executed IN ORDER) with validation checkpoints ('Parse result — PASSED or BLOCKED?', 'Check completion') and feedback loops (BLOCKED → assess alternatives → retry/skip), matching score 3; not score 2 because checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	The body is well-sectioned with clear headers but is a single ~170-line monolithic file with no external references, and multi-facet content (delegation template, sub-agent matrix) that could be split is inline, matching score 2; not score 3 because there are no one-level-deep references, not score 1 because it is well-organized rather than a wall of text.	2 / 3
	Total	11 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 names a clear domain and several capability areas but leans on jargon and lacks an explicit 'Use when' trigger clause. It is adequately specific but not optimized for natural recall or completeness.

Suggestions

Add a 'Use when...' clause with natural trigger terms (e.g., 'Use when delegating to sub-agents, re-planning a blocked objective, or handing off context between phases').

Replace jargon-heavy phrasing like 'context handoff protocols' with natural language users would actually say.

Include common trigger variations ('delegate', 'orchestrate', 'blocked', 're-plan', 'hand off') directly in the description rather than only in metadata.when_to_use.

Dimension	Reasoning	Score
Specificity	Names the domain and several capability areas ('delegation', 'state management', 'adaptive re-planning', 'context handoff protocols'), but these are abstract pattern categories rather than concrete actions, matching the score-2 anchor; not score 3 because no specific concrete actions are listed, not score 1 because it does name multiple specifics.	2 / 3
Completeness	Answers 'what' (orchestrator patterns and sub-areas) but has no 'Use when...' clause or explicit trigger guidance, so per the judging guideline completeness is capped at 2; not score 3 because 'when' is entirely missing, not score 1 because 'what' is clearly stated.	2 / 3
Trigger Term Quality	Contains some natural terms a user might say ('delegate', 're-plan') but is dominated by jargon ('Decepticon orchestrator patterns', 'context handoff protocols') and misses common variations, fitting score 2; not score 1 because relevant keywords exist, not score 3 because coverage is jargon-heavy.	2 / 3
Distinctiveness Conflict Risk	The 'Decepticon' namespace gives it a niche, but generic orchestration terms ('delegation', 'state management') could overlap with similar agent-orchestration skills, matching score 2; not score 3 because triggers are not distinctly bounded, not score 1 because the namespace is fairly specific.	2 / 3
	Total	8 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/decepticon/orchestration/SKILL.md
Commit: e34afba

Reviewed: 10 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.