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.
Install with Tessl CLI
npx tessl i github:Demerzels-lab/elsamultiskillagent --skill task-decomposer75
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 main strengths are its specific action verbs and explicit 'Use when' guidance. However, it could benefit from more natural trigger terms that users would actually say and clearer differentiation from general planning or workflow skills.
Suggestions
Add more natural trigger terms users might say, such as 'plan this out', 'step-by-step', 'orchestrate', 'coordinate tasks', or 'help me organize this project'.
Strengthen distinctiveness by emphasizing the unique skill-search-and-creation aspect, e.g., 'Use when no single existing skill can handle the request' or 'when combining multiple capabilities is needed'.
| 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', 'workflow automation', 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 project management skills. The 'skills.sh' reference adds some distinctiveness. | 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 and poor organization. The core workflow is sound but buried under excessive templates, repeated examples, and explanatory content that Claude doesn't need. The lack of progressive disclosure makes this difficult to navigate, and the absence of concrete validation steps weakens the workflow for what is essentially an orchestration skill.
Suggestions
Reduce content by 60-70%: Remove the capability taxonomy table (Claude knows these), condense the YAML examples to one representative case, and eliminate explanatory text about principles Claude already understands.
Split into multiple files: Move the capability taxonomy to CAPABILITIES.md, skill template to TEMPLATES.md, and detailed examples to EXAMPLES.md, keeping only the core workflow in SKILL.md.
Add explicit validation checkpoints: After skill search, verify results before proceeding; after skill installation, confirm success; after skill creation, validate the SKILL.md structure.
Replace template placeholders with one complete, executable example showing the full workflow from user request to execution plan with real values.
| 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 format templates could be condensed significantly. Much content explains concepts Claude already understands (what atomicity means, what APIs are). | 1 / 3 |
Actionability | Provides concrete CLI commands (npx skills find, npx skills add) and YAML templates, but most examples are pseudocode/templates rather than executable code. The skill template and execution plan formats are structural guides rather than copy-paste ready implementations. | 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 the execution plan template is mentioned but not demonstrated with concrete checks. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including the full capability taxonomy, skill template, output format, and multiple examples. This should be split into separate reference files (CAPABILITIES.md, TEMPLATES.md, EXAMPLES.md). | 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.