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.
Overall
score
78%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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' guidance and good trigger term coverage for development tasks. However, the specificity of actual capabilities is moderate, and the broad trigger terms (features, reviews, testing, documentation) create significant conflict risk with more specialized skills that handle these individual tasks.
Suggestions
Narrow the trigger terms to focus on complexity indicators like 'large-scale', 'cross-cutting', 'multiple files simultaneously' rather than generic task types that single-agent skills also handle
Add more specific concrete actions the orchestration performs, such as 'spawns parallel agents', 'manages task dependencies', 'coordinates merge conflicts'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (multi-agent orchestration) and mentions some actions like 'parallel work', 'sophisticated coordination', and 'decomposition into parallel subtasks', but the specific capabilities are not comprehensively listed - it's more about when to use than concrete actions performed. | 2 / 3 |
Completeness | Clearly answers both what ('Multi-agent orchestration for complex tasks', 'orchestrate work using cc-mirror tasks and TodoWrite') and when ('Use when tasks require parallel work, multiple agents, or sophisticated coordination' plus explicit trigger list). | 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 users would naturally use when requesting complex development tasks. | 3 / 3 |
Distinctiveness Conflict Risk | The triggers like 'features', 'reviews', 'refactoring', 'testing', 'documentation' are quite broad and could easily overlap with single-agent coding skills or individual testing/documentation skills. The multi-agent aspect provides some distinction but the trigger terms are generic. | 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 and good progressive disclosure to reference materials. However, it is severely bloated with motivational content, ASCII art, personality coaching, and verbose explanations that waste significant context window space. The core technical content is strong but buried under unnecessary fluff.
Suggestions
Remove all ASCII art boxes and motivational content ('This is what AGI feels like', 'You are the Conductor', personality coaching sections) - these waste tokens on concepts Claude doesn't need explained
Consolidate the 'Your energy', 'Read Your Human', and 'Core Philosophy' sections into a single brief behavioral note or remove entirely
Remove the 'Remember Who You Are' closing section and similar inspirational content - focus on actionable instructions only
Condense the anti-patterns table and vocabulary guidance into a compact list rather than elaborate tables with explanations
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive ASCII art boxes, motivational content ('This is what AGI feels like'), personality coaching, and repeated explanations. The core orchestration instructions could be conveyed in ~20% of the current length. | 1 / 3 |
Actionability | Provides fully executable bash commands for cc-mirror tasks, complete Python code examples for TodoWrite sync, concrete Task() spawn examples with proper preambles, and specific CLI reference with JSON output structures. | 3 / 3 |
Workflow Clarity | Clear multi-step orchestration flow with explicit sequencing (decompose → set dependencies → find ready work → spawn → mark complete → synthesize). Includes validation via JSON state checking and feedback loops for dependency resolution. | 3 / 3 |
Progressive Disclosure | Well-structured with clear references to domain guides (references/domains/*.md), patterns, tools, and examples files. One-level-deep navigation with explicit table mapping task types to reference files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%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 |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 13 / 16 Passed | |
- 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.