task-decomposer
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.
75
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/skillEvaluation — 90%
↑ 2.43xAgent success when using this skill
Validation for skill structure
Discovery
77%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 is a well-structured description that clearly articulates both capabilities and usage triggers. The specificity of actions (decompose, identify, search, create) is strong, and the explicit 'Use when' clause covers key scenarios. However, trigger term coverage could be expanded with more natural user language variations, and some terms like 'complex requests' may cause overlap with other planning-oriented skills.
Suggestions
Add more natural trigger terms users might say, such as 'plan', 'orchestrate', 'step-by-step', 'break this down', or 'multi-part task'
Consider adding file type or domain specificity to reduce conflict risk with general automation or planning skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Decomposes complex user requests into executable subtasks', 'identifies required capabilities', 'searches for existing skills at skills.sh', and 'creates new skills when no solution exists'. | 3 / 3 |
Completeness | Clearly answers both what (decomposes requests, identifies capabilities, searches/creates skills) AND when ('when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'complex multi-step request', 'automate workflows', 'breaking down large tasks', but missing common natural variations users might say like 'plan', 'orchestrate', 'step-by-step', 'divide and conquer', or 'task planning'. | 2 / 3 |
Distinctiveness Conflict Risk | While it has a specific niche around task decomposition and skill orchestration, terms like 'complex requests' and 'workflows' could overlap with general planning or automation skills. The reference to 'skills.sh' adds distinctiveness but the broader triggers remain somewhat generic. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill attempts to be comprehensive but suffers from severe verbosity, repeating similar patterns multiple times and including extensive formatting templates that inflate token count. While the workflow structure is logical, it lacks explicit validation checkpoints and could benefit significantly from splitting content into referenced files for the capability taxonomy, templates, and examples.
Suggestions
Reduce content by 60-70%: consolidate the capability taxonomy to a brief list with a reference to a separate CAPABILITIES.md file, and remove redundant YAML examples
Add explicit validation checkpoints: 'Verify skill installed: npx skills list | grep skill-name' before proceeding to execution
Split into progressive disclosure structure: SKILL.md (overview + quick start), TEMPLATES.md (skill creation templates), EXAMPLES.md (detailed decomposition examples)
Remove the elaborate ASCII output format template - Claude can format output appropriately without 50+ lines of formatting instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400 lines with extensive repetition. The capability taxonomy table, multiple YAML examples showing the same patterns, and elaborate output formatting templates add significant token overhead. Much of this could be condensed to core principles and one example. | 1 / 3 |
Actionability | Provides concrete CLI commands (npx skills find/add) and YAML structures, but much content is template/pseudocode rather than executable. The skill creation template and execution plan formats are structural guides rather than copy-paste ready code. | 2 / 3 |
Workflow Clarity | Six phases are clearly sequenced, but validation checkpoints are weak. No explicit verification steps between phases (e.g., 'confirm skill installed before proceeding'). The 'verification' section in execution plan is mentioned but not enforced in the workflow. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including lengthy examples, templates, and tables that could be split into separate reference documents. The skill mentions integration with 'find-skills' but doesn't link to it properly. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.