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 adequately covers both what the skill does and when to use it, earning good marks for completeness. However, it reads as a meta-orchestration skill with somewhat abstract language that could overlap with many other skills. The trigger terms lean toward technical/internal jargon rather than natural user language.
Suggestions
Replace abstract terms like 'decomposes complex user requests into executable subtasks' with more concrete examples of what kinds of tasks this handles (e.g., 'Plans and coordinates multi-tool projects like building apps, setting up CI/CD pipelines, or migrating codebases').
Add more natural trigger terms users would actually say, such as 'plan this out', 'step by step', 'organize this project', 'I need to do multiple things', or 'help me figure out how to approach this'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names several actions (decomposes requests, identifies capabilities, searches for skills, creates new skills) but they are somewhat abstract and process-oriented rather than concrete end-user actions. 'Decomposes complex user requests into executable subtasks' is more of a meta-description than a specific capability. | 2 / 3 |
Completeness | Clearly answers both 'what' (decomposes requests, identifies capabilities, searches for existing 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', 'breaking down large tasks', and 'skills.sh', but many of these are not natural phrases users would say. Users are more likely to say things like 'plan this out', 'help me organize this project', or 'create a workflow' rather than 'decompose into subtasks'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is fairly meta and orchestration-focused, which gives it some distinctiveness, but terms like 'complex requests' and 'automate workflows' are broad enough to potentially conflict with many other skills. The mention of 'skills.sh' adds some specificity but the overall scope is quite wide. | 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 significantly over-engineered and verbose for what it does. It explains many concepts Claude already understands (task decomposition principles, capability taxonomies, generic skill templates) and includes extensive placeholder-heavy templates that add length without proportional value. The core workflow idea is sound but buried under excessive scaffolding that should either be trimmed or split into reference files.
Suggestions
Reduce content by 60-70%: Remove the Universal Capability Types table, Task Decomposition Principles section, and generic skill template — Claude already knows these concepts. Focus on the specific CLI commands and the search-then-create decision flow.
Split the output format template, capability taxonomy, and skill creation template into separate reference files (e.g., references/output-format.md, references/capability-types.md) and link to them from the main skill.
Add explicit validation/error-handling steps within the workflow phases, e.g., 'If npx skills find returns no results, broaden search terms by trying synonyms before proceeding to skill creation' and 'After npx skills add, verify installation succeeded by checking the skill is accessible.'
Replace placeholder-heavy YAML blocks with one fully concrete end-to-end example that shows the complete flow from user request to execution plan, rather than multiple partial examples with template variables.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. The Universal Capability Types table, task decomposition principles (atomicity, independence, etc.), and the elaborate output format templates are things Claude already knows. The skill template section explains generic SKILL.md structure that doesn't need to be here. Much of this could be reduced to 1/4 the size. | 1 / 3 |
Actionability | The skill provides concrete CLI commands like 'npx skills find' and 'npx skills add', and includes structured YAML examples. However, much of the content is template/placeholder-heavy (e.g., '{skill-name}', '{capability_type}') rather than truly executable. The decomposition examples are illustrative but not copy-paste ready workflows. | 2 / 3 |
Workflow Clarity | The 6-phase workflow is clearly sequenced and the phases are logically ordered. However, validation checkpoints are weak — the execution plan mentions verification as a list item but there are no explicit feedback loops for error recovery (e.g., what happens if skill search fails, if skill installation fails, or if a created skill doesn't work). The 'verify before proceeding' best practice is mentioned but not integrated into the workflow steps. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with everything inline. The capability taxonomy table, skill template, output format template, and multiple full examples could all be split into separate reference files. There are no references to external files for detailed content — everything is crammed into one document. | 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
45f9fac
- 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.