ahepi/deepreason/decision-mapping
Claude Code and agent skill by ahepi/deepreason
- community
Checking that the SKILL.md file is still in the repository.
Typing an open-item queue - which items are decisions, which are riders, which are notes - without shrinking it (FR-22). Use for any "what is actually on the desk" document. The source cycle's first map understated its queue by more than half.
Install
npx vskill@latest install ahepi/deepreason/decision-mappingSKILL.md
Decision Mapping (new in 0.5, from FR-22)
<!-- PROMPT-CORE-BEGIN --> A queue map is DERIVED: the pins are the record, and where the map and a pin disagree, the pin wins. The map's characteristic failure is making the queue look smaller than it is; every rule here exists because that happened.
- THE RIDER TEST: an item rides on a root only if EVERY answer to the
root determines it. "It arises only once the pin is admitted" is a DIFFERENT, weaker edge - name it as such. An item no answer determines is independent, however related it feels.
- THREE TIERS, not two: ADMISSION (is this route accepted at all - and
this tier sits ABOVE shape: refuse admission and the shape question is never asked), SHAPE (given admission, which form), FREEZE-TIME WORK (follows admission; determined by no answer; it is scheduled, not cleared, by any decision).
- ELIMINATIONS are the map's strongest claims - that a question ceases
to exist. Verify one per OPTION of the root, not just the favoured option; a question that survives under any option is not eliminated.
- SHARED-CAUSE claims name the shared FACT and the test that measures
it on each side. Two obstacles with different facts (a missing join is not a cardinality ceiling) are two questions; fusing them is how a reversal gets re-imported after its source refused it.
- One counting rule per table, stated. Counting one row's notes as
cleared items while another row has none is how an ordering gets flattered. Every total recomputed, never remembered (FR-26).
- ORDERINGS are preferences unless derived. Give the criteria, show
which order each criterion yields, and name the chooser. Demoting an item a source ranks first requires an argument, not a table cell.
- The map ships a STALENESS GUARD on its inventory (every source item
classified exactly once; no invented items) and states the guard's limit: inventory is checkable, classification is not - adversarial review is what checks classification, and the map records what that review removed (a map is only as trustworthy as its known failures). <!-- PROMPT-CORE-END -->
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingtools/treadle0.5/skills/decision-mapping/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ahepi/deepreason/decision-mapping)