Menü
Cognitive protocol that converts unknown unknowns into known unknowns. Invoke for large/ambiguous goals, or when user asks for honest breakdown, decomposition, or avoiding empty plans.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | decomposer |
| description | Cognitive protocol that converts unknown unknowns into known unknowns. Invoke for large/ambiguous goals, or when user asks for honest breakdown, decomposition, or avoiding empty plans. |
This is the TRAE-specific adapter for the Decomposer protocol. The universal skill definition is at ../../SKILL.md. The full protocol is at ../../PROTOCOL.md.
Before executing the five steps, establish two things:
Use the detection tree in ../../references/COGNITIVE_POSITIONS.md to determine the user's dominant position. Ask the questions if the answer is not obvious from context.
Use the trigger phrase detection in ../../references/OUTPUT_CONTEXTS.md. For TRAE conversations, the default context is "TRAE Conversation" — Markdown dialogue within the conversation flow.
The five-step protocol is defined in ../../PROTOCOL.md. Execute it faithfully. The TRAE-specific considerations are:
../../references/ANTI_SHELL_CHECKLIST.md. If any fails, return to the corresponding step.| File | Purpose |
|---|---|
../../PROTOCOL.md | Full five-step protocol definition |
../../SKILL.md | Universal skill definition |
../../references/COGNITIVE_POSITIONS.md | Position detection (includes MIT Scholar) |
../../references/OUTPUT_CONTEXTS.md | Context rendering rules |
../../references/ANTI_SHELL_CHECKLIST.md | Self-check checklist |
../../references/SCALE_GUIDE.md | Scale adaptation guide |
../../references/COMMON_PITFALLS.md | Common execution errors |
../../VALIDATION.md | Empirical validation roadmap |
../../TUTORIAL.md | Beginner tutorial |
../../references/PROBE_TOOLKIT.md | Probe toolkit for finding unknown unknowns |
../../references/FALSIFIABILITY_WHITEPAPER_TEMPLATE.md | Falsifiability Whitepaper fill-in template |
../../references/ERROR_BUDGET_SPEC_TEMPLATE.md | Error Budget Specification fill-in template |
../../references/ZERO_CODE_VALIDATION_TEMPLATE.md | Zero-code validation template |
../../references/SEVEN_DAY_TEST_CHAIN_TEMPLATE.md | 7-day lethal test chain template |
../../references/DECISION_CARDS_WORKSHEET.md | Three decision cards worksheet |
../../references/QUICK_REFERENCE_CARD.md | Single-page protocol cheat sheet |
This skill should be used when a user provides a vague, abstract, or "hollow" vision, goal, or idea and wants it turned into a concrete, actionable implementation path with verifiable acceptance criteria. It also triggers on mentions of "愿景回溯" (the Chinese term for vision retrospective), "vision retrospective", or requests to critique/refine a vision into executable steps. It contrasts with vision-driven development by tracing claims backward to evidence anchors rather than forwarding from assumptions.
Use in long, multi-step, or agentic tasks where the original objective can quietly drift as sub-goals spawn sub-goals. Forces periodic re-grounding against the literal original goal. Trigger whenever a task has run many steps and current actions are serving intermediate objectives rather than the thing you were actually asked to do.
Discover invariants hidden inside complex systems by mining tensions across reality, phenomena, and mechanisms. Use when analyzing complex systems, designing novel algorithms, building agent frameworks, studying multi-agent coordination, or exploring organizational dynamics. Not for simple optimization tasks or known-solution problems.
Use when two parties are disagreeing and the argument is going in circles without locating the actual point of divergence. Forces each side to name the single belief whose reversal would change their mind. Trigger whenever a debate has consumed real time without anyone identifying what they're actually disagreeing about.
Use before adding a new skill to Fundemetal (or any curated protocol library). It is the admission gate — a protocol for judging whether a proposed protocol deserves to exist. Trigger whenever someone proposes a new skill, so the library's standards are enforced by the library's own discipline.
Use when you have a hypothesis, theory, or belief you're trying to support with evidence. Forces you to hunt for what would kill it, not just what confirms it. Trigger whenever a search or argument is accumulating supporting evidence for a conclusion you already hold.