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.
80
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/workflow/orchestration/skills/orchestration/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description has strong completeness with explicit 'Use when' and 'Triggers include' clauses, and good trigger term coverage for developer workflows. However, the specificity of actions could be improved with more concrete verbs, and the broad trigger terms (features, reviews, testing, documentation) create significant conflict risk with other skills that handle those tasks without multi-agent coordination.
Suggestions
Narrow the trigger conditions to emphasize scale/complexity indicators (e.g., 'Use when tasks are large enough to benefit from parallel execution' or 'when user explicitly requests multiple agents') to reduce conflict with single-agent skills
Replace abstract actions like 'sophisticated coordination' with concrete operations such as 'spawn parallel agents', 'track inter-task dependencies', 'aggregate results from multiple workers'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (multi-agent orchestration) and mentions specific tools (cc-mirror tasks, TodoWrite), but the actions are somewhat abstract ('orchestrate work', 'parallel work', 'sophisticated coordination') rather than concrete operations like 'spawn agents', 'track dependencies', or 'merge results'. | 2 / 3 |
Completeness | Clearly answers both what ('Multi-agent orchestration for complex tasks', 'orchestrate work using cc-mirror tasks for persistent dependency tracking and TodoWrite for real-time session visibility') and when ('Use when tasks require parallel work, multiple agents, or sophisticated coordination. Triggers include requests for features, reviews, refactoring, testing, documentation'). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'features', 'reviews', 'refactoring', 'testing', 'documentation', 'parallel work', 'multiple agents'. These are terms developers naturally use when requesting complex work. | 3 / 3 |
Distinctiveness Conflict Risk | While 'multi-agent orchestration' is specific, the trigger terms like 'features', 'reviews', 'refactoring', 'testing', 'documentation' are very broad and could easily overlap with single-agent skills for those same tasks. The phrase 'any work that benefits from decomposition' is particularly prone to over-triggering. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent actionable guidance with clear workflows, executable code, and well-organized references to supporting documentation. However, it is severely bloated with motivational content, ASCII art, personality coaching, and philosophical statements that waste significant token budget without adding operational value. The core technical content is strong but buried under unnecessary stylistic elements.
Suggestions
Remove all ASCII art boxes, motivational quotes, and personality coaching sections ('Your energy', 'Read Your Human', 'Remember Who You Are') - these consume ~40% of tokens without adding actionable guidance
Eliminate redundant explanations - the 'Iron Law' section repeats tool ownership information that appears again in the 'Tool Ownership' table
Cut the 'Vocabulary (What Not to Say)' and 'Communication That Wows' sections - Claude doesn't need coaching on communication style for a technical orchestration skill
Consolidate the worker agent instructions - the preamble template and example could be combined into a single reference block
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive ASCII art boxes, motivational content ('This is what AGI feels like'), personality coaching, and repeated explanations. Much of this is stylistic padding that doesn't add actionable value—Claude doesn't need instructions on 'swagger' or 'vibe checks'. | 1 / 3 |
Actionability | Despite verbosity, the skill provides fully executable commands (npx cc-mirror tasks create/update), complete code examples for TodoWrite sync, proper Task() invocations with worker preambles, and specific JSON output structures. The guidance is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear multi-step orchestration flow with explicit sequencing (decompose → create tasks → set dependencies → find ready work → spawn workers → mark complete → synthesize). Includes validation via JSON output parsing and feedback loops for dependency resolution. | 3 / 3 |
Progressive Disclosure | Well-structured with clear navigation tables pointing to domain references (references/domains/*.md), pattern guides, and examples. References are one level deep and clearly signaled. The main skill serves as an overview with appropriate delegation to reference files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 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 |
Total | 10 / 11 Passed | |
- Repository
- numman-ali/n-skills
- Commit
8de01ac
- Reviewed
Table of Contents
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.