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.
73
47%
Does it follow best practices?
Impact
90%
2.43xAverage score across 6 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/10e9928a/task-decomposer/SKILL.mdQuality
Discovery
67%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 is structurally complete with both 'what' and 'when' clauses clearly stated, which is its strongest aspect. However, the capabilities described are somewhat abstract and meta-level, making it harder to distinguish from other planning or orchestration skills. The trigger terms are reasonable but could be more varied and natural to improve matching.
Suggestions
Add more natural trigger terms users might say, such as 'plan this out', 'step by step', 'I need to do multiple things', or 'orchestrate'.
Increase specificity by giving a concrete example of the type of complex request this handles, e.g., 'such as setting up a full CI/CD pipeline or building a multi-component application'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names several actions—decomposing requests, identifying capabilities, searching for skills, creating new skills—but they are somewhat abstract and process-oriented rather than concrete end-user-visible actions. It describes a meta-process rather than specific tangible outputs. | 2 / 3 |
Completeness | The description clearly answers both 'what' (decomposes requests, identifies capabilities, searches for skills, creates new skills) and 'when' with an explicit trigger clause ('should be used 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', and 'breaking down large tasks', but these are somewhat generic. Users might say 'break this into steps' or 'plan this out' but the description lacks those more natural phrasings and common variations. | 2 / 3 |
Distinctiveness Conflict Risk | The skill is meta-level (orchestrating other skills), which gives it some distinctiveness, but terms like 'complex requests', 'automate workflows', and 'breaking down tasks' are broad enough to potentially overlap with project planning, task management, or workflow automation skills. | 2 / 3 |
Total | 9 / 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 is a comprehensive but excessively verbose framework document that reads more like a tutorial or design document than an efficient skill instruction. It explains many concepts Claude already understands (task decomposition principles, capability taxonomies) and includes extensive placeholder-heavy templates inline rather than in separate reference files. The core actionable content — use `npx skills find` to search, decompose tasks, create skills when gaps exist — could be conveyed in a fraction of the space.
Suggestions
Reduce content by 60-70%: Remove the Universal Capability Types table, Task Decomposition Principles section, and elaborate ASCII output format template — Claude already knows these concepts and can generate appropriate formats.
Extract the skill creation template, output format template, and capability taxonomy into separate reference files (e.g., TEMPLATE.md, OUTPUT_FORMAT.md, CAPABILITIES.md) and reference them from the main SKILL.md.
Add explicit validation/error-handling steps: What to do when `npx skills find` returns no results, when skill installation fails, or when a created skill doesn't work as expected — include concrete recovery commands.
Replace placeholder YAML examples with one complete, realistic end-to-end example that shows actual skill names and real commands rather than '{task name}' and '{capability_type}' placeholders.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. The 'Universal Capability Types' table, task decomposition principles, elaborate ASCII output format templates, and multiple full YAML examples are largely things Claude already knows how to do. The skill explains basic concepts like atomicity, single responsibility, and independence that don't need teaching. Much of this could be condensed to ~80 lines. | 1 / 3 |
Actionability | The skill provides concrete CLI commands (npx skills find, npx skills add, npx skills init) and structured YAML examples, which is good. However, much of the content is template/placeholder-heavy rather than truly executable — the YAML blocks use placeholder syntax like '{task name}' and the workflow is more of a conceptual framework than copy-paste-ready instructions. | 2 / 3 |
Workflow Clarity | The six phases are clearly sequenced and the overall flow is logical. However, validation checkpoints are weak — the 'verification' section in the execution plan template is just placeholders, and there are no explicit feedback loops for error recovery (e.g., what to do if skill search fails, if skill installation fails, or if a created skill doesn't work). The 'Handle errors gracefully' best practice is vague. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files and no references to external files. The capability taxonomy table, skill template, output format template, and multiple full examples are all inline when they could be split into separate reference files. The content would benefit enormously from splitting into overview + reference files. | 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.
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- 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.