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

61%

Does it follow best practices?

Impact

—

No eval scenarios have been run

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

62%

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

This skill provides genuinely excellent orchestration guidance with concrete CLI commands, executable code examples, clear workflow sequencing, and well-structured task management protocols. However, it is severely undermined by extreme verbosity — roughly half the content is motivational fluff, personality coaching, decorative ASCII art, and tone guidance that wastes precious context window tokens. The actionable core is strong but buried under layers of unnecessary prose.

Suggestions

Cut all motivational/personality content ('Who You Are', 'Read Your Human', 'Remember Who You Are', 'Communication That Wows', signature blocks) — this alone would reduce the skill by ~40% without losing any actionable guidance.

Remove decorative ASCII boxes and replace with simple markdown headers — the boxes consume significant tokens for zero informational value.

Move the 'Swarm Everything' examples, vocabulary table, and anti-patterns into a separate reference file (e.g., references/orchestration-style.md) to keep the main skill focused on the mechanical workflow.

Consolidate the cc-mirror CLI reference into references/tools.md rather than inlining the full command reference, JSON schema, and computed fields table in the main skill.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~500+ lines. Massive amounts of motivational/personality content ('This is what AGI feels like', 'swagger', 'holy shit'), decorative ASCII boxes, and extensive coaching on tone/vibe that Claude doesn't need. The actual actionable orchestration content could be conveyed in a fraction of the space. Concepts like 'don't expose jargon' and 'celebrate wins' are personality instructions that bloat the skill enormously.	1 / 3
Actionability	Despite the verbosity, the skill provides highly concrete, executable guidance: specific CLI commands for cc-mirror tasks, complete Task() spawn examples with worker preambles, JSON output structures, TodoWrite sync protocols with real code, and model selection criteria. The commands are copy-paste ready and the examples are complete.	3 / 3
Workflow Clarity	The orchestration flow is clearly sequenced with an explicit flowchart (Vibe Check → Clarify → Decompose → Set Dependencies → Find Ready Work → Spawn Workers → Mark Complete → Synthesize). The sync protocol between cc-mirror tasks and TodoWrite includes validation/feedback loops (re-fetch state after blocker resolves, update icons). The task management flow example shows the complete lifecycle with numbered steps.	3 / 3
Progressive Disclosure	The skill references 8 domain guides and 4 additional reference files (patterns.md, tools.md, examples.md, guide.md) with clear navigation tables — good structure. However, no bundle files were provided, so we can't verify these references exist. More importantly, the SKILL.md itself is monolithic with enormous amounts of inline content (personality guidance, communication tables, anti-patterns, ASCII art) that could be split into separate reference files rather than bloating the main skill.	2 / 3
	Total	9 / 12 Passed

Description

59%

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 has good structural completeness with explicit 'Use when' and 'Triggers include' clauses, but suffers from overly broad trigger conditions that would cause it to match almost any complex coding request. The specificity of what the skill actually does is moderate — it names orchestration tools but doesn't clearly describe the concrete outcomes. The extremely wide trigger net ('any work that benefits from decomposition') creates high conflict risk with other skills.

Suggestions

Narrow the trigger conditions significantly — instead of 'any work that benefits from decomposition,' specify concrete thresholds like 'tasks requiring 3+ independent subtasks' or 'cross-file changes spanning multiple modules'

Reduce conflict risk by adding explicit exclusions or boundaries, e.g., 'Do NOT use for single-file edits, simple bug fixes, or tasks that can be completed sequentially in one pass'

Replace internal jargon like 'cc-mirror tasks' and 'TodoWrite' with user-facing language describing the outcomes, e.g., 'Splits complex work into parallel agent tasks with dependency tracking and progress monitoring'

Dimension	Reasoning	Score
Specificity	The description names the domain (multi-agent orchestration) and mentions some actions like 'orchestrate work using cc-mirror tasks' and 'TodoWrite for real-time session visibility,' but the concrete actions are more about mechanisms than user-facing capabilities. The listed triggers (features, reviews, refactoring, testing, documentation) are broad categories rather than specific concrete actions the skill performs.	2 / 3
Completeness	The description clearly answers both 'what' (multi-agent orchestration using cc-mirror tasks and TodoWrite for coordination) and 'when' (explicitly states 'Use when tasks require parallel work, multiple agents, or sophisticated coordination' and lists specific trigger scenarios). It has an explicit 'Use when...' clause with trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant keywords like 'parallel work', 'multiple agents', 'features', 'reviews', 'refactoring', 'testing', 'documentation', but many of these are extremely broad and would match a huge range of requests. Terms like 'cc-mirror tasks' and 'TodoWrite' are internal/technical jargon unlikely to appear in user requests. Missing more natural user phrases like 'break this into subtasks' or 'work on multiple things at once.'	2 / 3
Distinctiveness Conflict Risk	The trigger terms are extremely broad — 'features, reviews, refactoring, testing, documentation, or any work that benefits from decomposition' would match nearly any non-trivial coding request. The phrase 'any work that benefits from decomposition into parallel subtasks' is essentially unbounded and would conflict with virtually every other skill that handles coding tasks.	1 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 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: a518c67

Reviewed: about 2 months 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.