orchestration

Multi-agent orchestration for complex tasks. Use when tasks require parallel work, multiple agents, or sophisticated coordination. Triggers include requests for features, reviews, refactoring, testing, documentation, or any work that benefits from decomposition into parallel subtasks. This skill defines how to orchestrate work using cc-mirror tasks for persistent dependency tracking and TodoWrite for real-time session visibility.

Quality

73%

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 ./skills/workflow/orchestration/skills/orchestration/SKILL.md

Quality

Content

53%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 skill is genuinely actionable with a clear orchestration workflow and well-organized external references, but it is undermined by pervasive theatrical padding and missing validation checkpoints for the destructive/batch agent work it coordinates. Trimming the persona prose and adding a verify-agent-output step before marking tasks complete would materially raise both conciseness and workflow clarity.

Suggestions

Cut the ASCII-art banners and motivational persona sections ("Who You Are", "Remember Who You Are", "This is what AGI feels like") — they are padding that inflates token cost without aiding execution.

Add an explicit validation checkpoint in the Orchestration Flow: before `npx cc-mirror tasks update <id> --status resolved`, verify the worker's output (read the changed files, run tests/lint) and re-spawn on failure.

Move the detailed cc-mirror CLI command reference and JSON structure into references/tools.md, keeping only the essential create/update/mark-complete commands inline to avoid duplication with the existing reference file.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with substantial decorative padding — multiple ASCII-art banners and theatrical persona prose such as "This is what AGI feels like", "the swagger of someone who's very, very good at this", and "holy shit, that just happened" that do not advance execution; not a 1 because genuine concrete guidance (CLI commands, JSON structure, templates) is present underneath, and not a 3 because the padding is pervasive rather than occasional.	2 / 5
Actionability	Provides mostly executable guidance — copy-pasteable cc-mirror CLI commands, the full JSON output structure, and a complete worker-agent prompt template with a worked example — fitting the mostly-executable anchor; not a 5 because some sections (model selection, sync protocol) describe behavior in prose rather than giving ready-to-run snippets for every common case.	4 / 5
Workflow Clarity	The Orchestration Flow diagram and 10-step "What you DO" list give a clear sequence, but there is no validation/verification checkpoint confirming agent output quality before marking tasks resolved; because this orchestrates agents that perform destructive and batch operations (writing code, running commands), the missing-feedback-loop cap of 3 applies and takes precedence.	3 / 5
Progressive Disclosure	References are well-signaled and one level deep in clear task-type tables, and every referenced path (references/domains/*.md, patterns.md, tools.md, examples.md, guide.md) exists as a real file; not a 5 because the body inlines a large "cc-mirror tasks CLI Reference" section that overlaps with the existing references/tools.md rather than deferring to it.	4 / 5
	Total	13 / 20 Passed

Description

83%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 strong: third-person voice, explicit what-and-when with concrete trigger phrases, and distinct orchestration niche. Its main weakness is that the trigger terms are broad enough to overlap with specialized skills, and one phrase ("sophisticated coordination") is generic.

Dimension	Reasoning	Score
Specificity	Lists several concrete mechanisms — "cc-mirror tasks for persistent dependency tracking" and "TodoWrite for real-time session visibility" alongside "decomposition into parallel subtasks" — fitting the several-specific-actions anchor with minor gaps; not a 5 because "sophisticated coordination" is generic and the actions are methodological rather than comprehensive operations.	4 / 5
Completeness	Explicitly answers both what ("Multi-agent orchestration... defines how to orchestrate work") and when via a concrete "Use when..." clause plus a "Triggers include..." enumeration, matching the clear-what-and-when-with-concrete-triggers anchor; it is not below because both halves are explicit and specific.	5 / 5
Trigger Term Quality	Natural user-facing terms are well covered — "features, reviews, refactoring, testing, documentation" plus "parallel work, multiple agents" — matching good-keyword-coverage with a few common variations missing; not a 5 because no synonyms or tool-name variants broaden the set.	4 / 5
Distinctiveness Conflict Risk	The multi-agent orchestration / parallel-decomposition niche is mostly distinct with minimal core conflict, but the broad trigger list (reviews, testing, documentation) creates minor overlap with dedicated specialized skills; not a 5 because those broad triggers could fire for the wrong skill.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (794 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 8 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 16 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: numman-ali/n-skills
Path: skills/workflow/orchestration/skills/orchestration/SKILL.md
Commit: fdabc47

Reviewed: 13 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.