菜单
What limits us — identify bottlenecks, quantify constraints, analyze dependencies, resolve conflicts before experiment execution
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Strategy: Attack an isomorphism claim by demanding an explicit structure-preserving map and trying to break it. Targets any multi-language claim of the form 'X ≅ Y ≅ … across N mathematical languages'. Forces the claim to either earn the word 'isomorphism' or be demoted to 'analogy'. Methods: category theory (functor/natural-iso criteria), model theory, Lakatos monster-barring.
Strategy: Dialectic engine retuned for truth-seeking, not survival. A defender steelmans a claim into its MOST falsifiable form, a critic attacks to refute it, a judge classifies the exchange into BROKEN/CORROBORATED/UNFALSIFIABLE — the judge does NOT pick a winner or score persuasiveness. Methods: Irving debate (repurposed), Toulmin argumentation, Mayo severe testing.
Strategy: Run BEFORE building any validator (sandbox/simulation/benchmark). Builds a non-circularity matrix of theory-claim × validator-assumption to detect when a validator would 'confirm' a theory only because it was built on the theory's own premises. A circular validator's PASS carries zero evidential weight. Methods: Cartwright nomological machines, Winsberg sanctioning-of-simulations, tautology detection.
Strategy: Attack a beautiful unified result on the suspicion that its beauty is the bug. Distinguishes EARNED simplicity (forbids/predicts/subsumes) from DECORATIVE simplicity (re-describes/relabels/accommodates). Directly serves the Occam aesthetic by making it a falsifiable bar, not a vibe. Methods: Sober parsimony-as-evidence, MDL, Meehl risky prediction, accommodation-vs-prediction.
Campaign: Truth-seeking adversarial validation for scientific research artifacts (NOT publication defense). Core question: Where have we fooled ourselves, and is each load-bearing claim even falsifiable? Win-condition is INVERTED from survival/resilience to active refutation. Methods: Popper falsificationism, Lakatos Proofs and Refutations, Mayo severe testing, Platt strong inference.
Strategy: Attack the evidential weight of an 'independent convergence' claim. When N reasoning paths all reach the same conclusion, the confidence boost is real only if the paths were actually independent. Measures shared-prior / shared-blindspot contamination and corrects the over-counted confidence. Methods: Bayesian agreement-as-evidence, correlated-error analysis, jury theorem assumptions.
| name | constraint-analysis |
| description | What limits us — identify bottlenecks, quantify constraints, analyze dependencies, resolve conflicts before experiment execution |
| version | 1.0.0 |
| category | experiment-execution |
| type | campaign |
| strategies | ["bottleneck-identification","resource-constraint","assumption-constraint","dependency-constraint","conflict-resolution"] |
| tactics | ["constraint-tree-building","sensitivity-ranking","constraint-breaking"] |
| dependencies | {"strategies":["assumption-constraint","conflict-resolution","dependency-constraint","experiment-execution-bottleneck-identification","resource-constraint"],"tactics":["constraint-breaking","constraint-tree-building","sensitivity-ranking"],"sops":["constraint-synthesis","context-checkpoint","context-init","experiment-execution-paper-overview","experiment-execution-paper-research","experiment-execution-paper-search","experiment-execution-quality-gate-check","experiment-execution-saturation-detection","experiment-execution-web-research","experiment-execution-web-search"]} |
Before entering this campaign, the following must be true:
| Gate | Condition |
|---|---|
| Research direction exists | North star or research question is crystallized |
| Scope is bounded | Problem space has defined boundaries |
| Resources are enumerable | Can list available compute, data, time, people, budget |
| Stakeholders identified | Know who cares about the outcome |
If any gate fails, return to Campaign 1 (research-direction) or pre-campaign intake.
Produce a comprehensive constraint profile that identifies:
| Situation | Strategy | When to Use |
|---|---|---|
| Unknown bottleneck | bottleneck-identification | System performance is limited but cause unclear |
| Resource uncertainty | resource-constraint | Need to verify feasibility of resource plan |
| Assumption risk | assumption-constraint | Key assumptions untested or fragile |
| Sequencing unclear | dependency-constraint | Task ordering and prerequisites unknown |
| Conflicting demands | conflict-resolution | Two or more constraints oppose each other |
Default execution order: bottleneck-identification → resource-constraint → assumption-constraint → dependency-constraint → conflict-resolution
| Resource | Budget | Escalation |
|---|---|---|
| Subagent calls | ≤15 per strategy | Pause and report partial |
| Wall-clock time | ≤30 min per strategy | Checkpoint and continue |
| Context tokens | ≤80k per strategy | Summarize and spawn fresh |
| Total campaign | ≤5 strategies | Skip if constraint already resolved |
Campaign is complete when:
研究过程经 context-management 落盘，与最终报告分属不同文件：
constraint-analysis，
建立本 campaign 的过程 context 文件。init 幂等——同 Phase 重入返回原文件。constraint-analysis-report 文件落盘（见该 SOP）。Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use |
|---|---|
| assumption-constraint | Which assumptions are most fragile? — Vulnerability ranking + impact assessment of experiment assumptions |
| conflict-resolution | How do constraints conflict with each other? — Evaporating Cloud + assumption challenging + injection to resolve constraint conflicts |
| dependency-constraint | What must be completed first? — Dependency chain analysis + prerequisite graph construction |
| experiment-execution-bottleneck-identification | Where is the system bottleneck? — TOC 5 Focusing Steps + Current Reality Tree to find the binding constraint |
| resource-constraint | Are resources sufficient? — Quantify compute, data, time, human, and financial resource constraints |
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use |
|---|---|
| constraint-breaking | Orchestrate the full constraint-breaking cycle: extract conflict, challenge assumptions, project resolution |
| constraint-tree-building | Build Current Reality Tree from UDEs through causal chains to core conflicts |
| sensitivity-ranking | Rank constraints by sensitivity — which ones most impact the outcome if they shift |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| constraint-synthesis | Synthesize constraint analysis into actionable report with priorities |
| context-checkpoint | Append research process and results to the current Phase's context file. Each append MUST contain >=500 lines of markdown covering both process and results. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. |
| context-init | Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. |
| experiment-execution-paper-overview | Import SOP: paper landscape scan (from literature-engine skill) |
| experiment-execution-paper-research | Import SOP: paper full-text reading (from literature-engine skill) |
| experiment-execution-paper-search | Import SOP: paper AI summary reading (from literature-engine skill) |
| experiment-execution-quality-gate-check | Shared SOP: verify quality gate criteria are met before proceeding |
| experiment-execution-saturation-detection | Shared SOP: detect information saturation — know when to stop searching/analyzing |
| experiment-execution-web-research | Import SOP: deep full-page content analysis (from web-browsing skill) |
| experiment-execution-web-search | Import SOP: quick web scan discovery (from web-browsing skill) |