hjemmesidekongen/task-decomposer
plugins/smedjen/skills/task-decomposer/SKILL.md
Decomposes task descriptions into ordered subtask lists with complexity estimates, file scope, dependency chains, and 5-factor risk scores. Handles ambiguity by requesting clarification when task scope is insufficiently defined.
testing
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai task-decomposerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 5:30 PM38.6s2 files scanned
SKILL.md
- name:
- task-decomposer
- description:
- >
- user_invocable:
- false
- interactive:
- false
- model_tier:
- senior
- depends_on:
- []
- reads:
- []
- type:
- data_validation
- - name:
- scope_coverage
- verify:
- Union of subtask file_scopes covers all files implied by the original task
- fail_action:
- Add missing subtasks for uncovered files
- on_fail:
- Decomposition incomplete — fix flagged issues before dispatch
- on_pass:
- Decomposition valid — ready for tier-assignment
- origin:
- smedjen
- inspired_by:
- superpowers-main/skills/writing-plans/SKILL.md + executing-plans/SKILL.md
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- Built for smedjen orchestration pipeline with risk scoring and dependency tracking
Task Decomposer
Breaks a task into an ordered list of subtasks suitable for parallel or sequential agent dispatch.
Core Algorithm
- Parse the input task description and any referenced files.
- Identify logical units of work — each unit should be independently testable.
- For each subtask, determine: complexity (S/M/L/XL), file scope, dependencies on other subtasks, and a 5-factor risk score.
- Order subtasks by dependency graph (topological sort).
- Write the decomposed output to
.ai/tasks/decomposed/<task-id>.yml.
Ambiguity Gate
If the task description scores above 3.5 on the ambiguity factor, halt and request clarification. Do not guess at scope — unclear tasks produce bad subtask graphs.
Questions to ask:
- What files or modules are in scope?
- What is the expected end state?
- Are there constraints (performance, backwards compat, etc.)?
Complexity Sizing
| Size | Rough scope | Typical files | |------|------------|---------------| | S | Single function or config change | 1-2 | | M | Feature within one module | 3-5 | | L | Cross-module change | 5-10 | | XL | Architectural change | 10+ |
Risk Score
Each subtask gets a 5-factor risk vector: [scope, reversibility, ambiguity, impact, dependencies], each 1-5. Feeds into tier-assignment downstream.
Rules
- Max 12 subtasks per decomposition. If more are needed, split the parent task first.
- Each subtask must have at least one file in its scope.
- Dependencies must reference subtask IDs within the same decomposition.
- If a subtask has no dependencies, mark it as
parallel_eligible: true. Seereferences/process.mdfor detailed algorithm, schemas, and examples.
Related Skills
hjemmesidekongen/brand-strategy
development
VerifiedTrustedCommunity
Creates a brand from scratch through market research and interactive sparring. Runs competitive research via Perplexity, then guides the user through positioning, audience, voice, values, and content pillars. Produces the full brand guideline set at .ai/brand/{name}/. Use when building a new brand, defining brand strategy for a product, or when /våbenskjold:create is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-loader
testing
VerifiedTrustedCommunity
Loads brand guidelines from .ai/brand/{name}/ and makes them available to the current context. Progressive disclosure: L1 confirms brand exists, L2 loads summary, L3 loads specific files on demand. Use when a downstream skill or user needs brand context, or when /våbenskjold:apply is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-evolve
documentation
VerifiedTrustedCommunity
Guided reinvention of an existing brand guideline. Loads current brand from .ai/brand/{name}/, identifies what to keep vs change, and walks the user through targeted evolution. Preserves brand equity while updating positioning, voice, or values. Use when refreshing a brand or when /våbenskjold:evolve is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-audit
development
VerifiedTrustedCommunity
Codifies an existing brand from materials, samples, and references. Analyzes provided content to extract voice patterns, values, and positioning. Produces the same guideline format as brand-strategy. Use when a brand already exists but isn't documented, or when /våbenskjold:audit is invoked.
SKILL.mdUpdated Apr 5, 2026