decompose-research-goal
SkillDev toolsLets your agent break a research goal into a tree of smaller testable sub-goals with dependencies and feasibility notes.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the decompose-research-goal skill
About this skill
Turn a research direction into an AND/OR goal DAG with testable leaves, dependency structure, and feasibility annotations.
What this skill tells your AI
The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/decompose-research-goal/SKILL.md and read by ahel’s review.
Purpose
Turn a research direction into an AND/OR goal DAG with testable leaves, dependencies, and feasibility annotations.
Input contract
required: [research_direction, constraints]
optional: [actor_profile, obstacle_report, timeline, north_star]
constraints: [goal wording, constraints, and source context must be explicit]
Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
- You MUST load skill
formulate-top-goalto formalize the top goal and desired effect. - You MUST load skill
decompose-and-or-goalto recursively construct AND/OR branches and executable leaves. - You MUST load skill
validate-goal-treeto check leaf specificity, testability, coverage, and dependency consistency. - You MUST load skill
assess-goal-feasibilityto annotate feasibility and alternatives. - You MUST load skill
map-dependenciesto map the goal dependencies. You MUST load skillcrystallize-north-starto compress the result into a North Star.
Deviation: Omit feasibility annotations when no actor, resource, or timeline constraints are supplied; mark the tree provisional rather than inventing constraints. Re-run only the affected branch after a decision changes its parent goal.
Output contract
produces: [goal_tree_dag, executable_leaves, dependency_map, feasibility_annotations, research_north_star]
delta_fields: [findings, hypothesis_updates, decisions, uncertainties, open_questions]
Thresholds and quality gates
- Every leaf must be testable or executable and trace to a parent goal.
- AND/OR semantics must be explicit; unresolved feasibility remains an uncertainty.
- Completion requires coverage of the declared top goal, not a fixed leaf count.
Failure and counterexamples
Reject trees with circular dependencies, vague leaves, or branches that cannot be tied to the declared direction. Do not treat a polished sentence as evidence that decomposition is complete.
Provenance map
resolved: goal-decompositionresolved: north-star-crystallization-formulate-top-goalresolved: north-star-crystallization-and-or-decomposeresolved: north-star-crystallization-validate-leavesresolved: north-star-crystallization-feasibility-checkresolved: north-star-crystallization-ask-decomposition-validation
Preserved source criteria ledger
| source | source line | kind | source criterion |
|---|---|---|---|
| none retained | - | - | No source numeric/textual criterion retained after normalization. |
Context checkpoint / Delta notes
Append the goal DAG, leaf validation, feasibility annotations, dependency changes, and unresolved validation questions.
Signals
- GitHub stars
- 501
- Forks
- 41
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
decompose-research-goal- Source
- github.com/yogsoth-ai/de-anthropocentric-research-engine