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

70%

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

57%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 skill is highly actionable with a well-organized, verified reference structure, but it is severely over-long: large tracts are motivational persona content and redundant restatements of the same orchestrate-don't-execute rule. Workflow sequencing is clear but lacks validation checkpoints for confirming agent work before marking tasks complete.

Suggestions

Cut the persona/ASCII-art sections ('Who You Are', 'Remember Who You Are', the opening 'Conductor' box, 'Swarm Everything' pep examples) and collapse the four overlapping 'orchestrate-don't-execute' boxes into one; move the swagger guidance to a reference file to lift conciseness off anchor 1.

Add an explicit validation checkpoint in the flow (e.g. 'Read agent output; if it fails review criteria, re-spawn with feedback before npx cc-mirror tasks update --status resolved') to give the batch agent workflow a real feedback loop.

Move the full cc-mirror CLI reference and TodoWrite sync protocol into references/tools.md, keeping only the core command set inline, so SKILL.md functions as a leaner overview.

Dimension	Reasoning	Score
Conciseness	The ~790-line body is heavily padded with persona/ASCII-art content ('This is what AGI feels like', 'holy shit, that just happened', 'the swagger of someone who's very, very good at this') and restates 'orchestrate, don't execute' across multiple redundant boxes (Iron Law, Tool Ownership, When YOU Read vs Delegate, Anti-Patterns), matching the anchor 1 'padded with unnecessary context' example.	1 / 3
Actionability	It supplies copy-paste-ready cc-mirror CLI commands ('npx cc-mirror tasks create --subject ...', '--add-blocked-by', '--status resolved', '--json'), a documented JSON output structure, a complete worker prompt template with example, and a concrete TodoWrite sync snippet, meeting the anchor 3 'fully executable commands; copy-paste ready' bar.	3 / 3
Workflow Clarity	The orchestration flow is clearly sequenced (Vibe Check -> Clarify -> Decompose -> Set Dependencies -> Find Ready -> Spawn -> Mark Complete -> Synthesize), but there is no validation checkpoint verifying agent output quality before marking a task resolved; per the rubric, batch agent operations without verification feedback loops cap this at anchor 2.	2 / 3
Progressive Disclosure	The 'Load Your Domain Guide' and 'Additional References' tables give clear, one-level-deep navigation to references/domains/* and references/{patterns,tools,examples,guide}.md, all of which exist as real files, matching the anchor 3 'clear overview with well-signaled one-level-deep references'.	3 / 3
	Total	9 / 12 Passed

Description

82%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 answers both 'what' and 'when' with natural trigger terms and a clear, third-person voice. Its main weakness is distinctiveness: the trigger surface is so broad that it would fire for almost any software task, competing with more specialized skills.

Suggestions

Narrow the trigger guidance so orchestration activates only when parallelism/coordination is the dominant need, e.g. 'Use when a request clearly benefits from decomposing into 3+ parallel workstreams with dependencies' rather than listing features/reviews/refactoring/testing/documentation.

Replace abstract verbs ('orchestrate', 'decomposition') with concrete operations (create dependency-linked tasks, spawn background workers, mirror status to TodoWrite) to lift specificity toward anchor 3.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete mechanisms ('cc-mirror tasks for persistent dependency tracking and TodoWrite for real-time session visibility'), but the verbs ('orchestrate', 'decomposition') are abstract coordination concepts rather than the multiple concrete operations (e.g. extract/fill/merge) that anchor 3 calls for.	2 / 3
Completeness	It clearly states what the skill does ('orchestrate work using cc-mirror tasks... and TodoWrite...') and gives an explicit 'Use when...' clause with concrete triggers, satisfying both halves required for anchor 3.	3 / 3
Trigger Term Quality	'requests for features, reviews, refactoring, testing, documentation' plus 'parallel work' and 'multiple agents' give good coverage of natural terms a user would actually say, matching the anchor 3 example.	3 / 3
Distinctiveness Conflict Risk	The orchestration niche (cc-mirror + TodoWrite coordination) is distinguishable, but the trigger list ('features, reviews, refactoring, testing, documentation, or any work that benefits from decomposition') is broad enough to overlap heavily with specialized domain skills, so it is not the low-conflict anchor 3.	2 / 3
	Total	10 / 12 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: b1c6173

Reviewed: 8 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.