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
Evaluation results
90%
54%Automating the Customer Onboarding Workflow
Task decomposition report format
Trigger mechanism identified
100%
100%
YAML subtask format
0%
100%
Capability taxonomy used
0%
100%
Search commands shown
0%
100%
Built-in capabilities excluded from search
12%
100%
Capability mapping YAML
0%
25%
Skills install command format
0%
100%
Execution plan prerequisites
80%
100%
Execution plan steps
50%
100%
Execution plan verification
62%
100%
Report section headers
100%
100%
Subtasks table
50%
62%
Skills to create section
0%
80%
Atomicity principle applied
100%
100%
Without context: $0.2207 · 1m 44s · 9 turns · 14 in / 5,230 out tokens
With context: $0.6882 · 2m 39s · 27 turns · 3,959 in / 9,009 out tokens
89%
47%Building a Telegram Alert Skill for Infrastructure Monitoring
New skill creation structure and template
SKILL.md frontmatter present
0%
100%
Third-person description
0%
62%
When to Use section
0%
100%
Prerequisites section
0%
100%
Usage section with Basic Usage
0%
100%
Advanced Usage subsection
0%
100%
Configuration section
100%
100%
Examples section
62%
100%
Troubleshooting section
100%
100%
Skill directory structure
100%
100%
General-purpose design
75%
100%
User confirmation acknowledged
0%
0%
Skill title heading
100%
100%
Without context: $0.6154 · 2m 15s · 26 turns · 1,704 in / 9,339 out tokens
With context: $0.4207 · 1m 42s · 20 turns · 843 in / 5,874 out tokens
91%
56%Research Paper Discovery and Knowledge Base Pipeline
Gap analysis and execution plan generation
content_generation as built-in
0%
100%
Execution plan YAML keys
11%
100%
Install command format
0%
44%
Execution steps fields
33%
100%
Verification section present
0%
100%
Skills search performed
0%
100%
Error/fallback strategies
100%
55%
Prerequisites field populated
0%
100%
skills_to_install field
0%
100%
Gap analysis documented
100%
100%
Single responsibility steps
100%
100%
Scheduling identified
100%
100%
Without context: $0.4146 · 2m 31s · 17 turns · 21 in / 8,474 out tokens
With context: $0.4934 · 2m 20s · 18 turns · 133 in / 7,413 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Unknown
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.