DebugBear integration. Manage data, records, and automate workflows. Use when the user wants to interact with DebugBear data.
Diagnostique pourquoi un prompt produit des résultats indésirables et propose des corrections. À utiliser quand le LLM hallucine, ignore des instructions, donne un mauvai — from…
⚡ PRIMARY TOOL for: 'why is X broken', 'find bug source', 'root cause analysis', 'trace error', 'debug issue', 'find where X fails'.
Drive a real debugger with breakpoints, watch expressions, and conditional stops to read live program state at the moment of failure.
Manage evidence freshness by identifying stale decisions and providing governance actions
Decentro integration. Manage data, records, and automate workflows. Use when the user wants to interact with Decentro data.
Use when the user needs to choose, prioritize, or make a go/no-go decision among options. — from general/general-misc
Structure a hard business decision — frame the choice, score options against weighted criteria, run a pre-mortem and stress-test, and produce a recommendation + decision record…
Decision modeling using decision tables, weighted scoring matrices, and decision trees. Structures complex decisions with clear criteria, alternatives evaluation, and out — from…
Decision modeling using decision tables, weighted scoring matrices, and decision trees. Structures complex decisions with clear criteria, alternatives evaluation, and out — from…
面向 AI Agent 的结构化决策支持系统，提供决策框架匹配、认知偏差检测、风险画像学习与强制复盘闭环. 内置 8 类决策框架（决策矩阵、成本效益、前置分析、预演困境、机会成本、二阶思维、奥卡姆剃刀、可逆性评估）， 按"领域×类型"双维度自动匹配最佳框架。扫描 12 类常见认知偏差并标注潜在信号，避免单点误判.
面向 AI Agent 的基础结构化决策支持系统，提供决策框架匹配与认知偏差检测两大核心能力. 内置决策矩阵、成本效益、奥卡姆剃刀、可逆性评估 4 类基础框架，按决策类型自动匹配. 扫描沉没成本、确认偏误、损失厌恶、可得性偏差 4 类常见认知偏差并标注潜在信号. 适用于产品、技术、商业、个人日常权衡场景，帮助用户避免拍脑袋决策与框架错配.
Use after making a material implementation decision, when uncertain about a choice, when requirements or authority are missing, when a fix may be case-specific, or before…
Audits decisions for cognitive biases, runs premortems on plans, and reframes choices to reveal hidden assumptions.
Judge a past decision by its PROCESS, not its outcome — because good decisions lose and bad decisions win, and teams that can't tell the difference learn the wrong lessons.
Bei vorhandenem und ausdrücklich autorisiertem lokalem Entscheidungsprofil: wiederkehrende Entscheidungen aus belegtem Feedback vorhersagen, Konfidenz kalibrieren und Vorhersage,…
طاولة قرار استشارية. تُشخّص المشكلة الحقيقية قبل حلّها، وتفحص الوقائع التي بُني عليها القرار، وتستدعي مؤيداً ومعارضاً معزولين بنيوياً وبتسليح متناظر، وتمنع الرد المُجامل والاعتراض…
Immer einsetzen, sobald mehrere Entscheidungen anstehen oder aufgelaufen sind -- egal ob in einem Thema, Projekt, Dokument oder waehrend einer Session: Inventarisieren, als…
Create or update a Decision Interface Charter for recurring decisions
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict.
Structured decision critic that systematically stress-tests reasoning before commitment surfacing hidden assumptions verifying claims and generating adversarial perspecti — from…
Structured decision critic that systematically stress-tests reasoning before commitment surfacing hidden assumptions verifying claims and generating adversarial perspecti — from…
Use when evaluating the clinical utility of a binary prediction model from a single clinical CSV file by fitting a logistic decision-curve model, plotting decision and…
Document important product decisions. Creates decision logs with rationale, alternatives, and trade-offs.
Use when an architectural choice is made, a library is selected, an approach is committed to, a convention is set, or any "we'll do it this way" moment occurs.
Multi-framework strategic analysis for product decisions. Use when: prioritize features, evaluate trade-offs, strategic decision, impact analysis, pre-mortem, ship or sunset,…
Spawns the decision-scorer agent after architect proposes 2+ variants in an ADR. Produces a weighted scoring table and recommended choice saved to docs/decisions/.
Identify and formalize durable product and technical decisions from agent outputs into long-term memory.
Scan recent notes for decision language and offer to update project Decision Logs
Freeze each tool result ID's replacement fate after it is observed so budget decisions stay deterministic across turns and forks.
Reconstruct the decision actually made in a messy Slack, email, or meeting thread into a proper decision record — commitments named, silent assumptions surfaced, non-decisions…
Triggers for automatically invoking the decision-framework skill before irreversible or high-blast-radius operations.
Thinking frameworks for decisions and problem analysis. Use when evaluating options, root causes, or prioritizing.
Use when choosing between mutually exclusive strategic paths or building a repeatable decision process—constructs Decision Matrices with probability estimates and runs Pre-Mortems.
Structured investigate-iterate-synthesize pipeline (5->5->3->1) that sends parallel agents to explore different facets of a problem, iterates on findings, progressively…
M6.2 用户决策门标准模板。每个 phase 命令产物落盘后，LLM 必须按本 skill 调用 AskUserQuestion 让用户决策"接受/修改/新增/重生成"，未确认前禁止进入下一 phase。
在 DSH 长程任务中为决策层加装五道防偏闸门：原始证据锚、对抗式对齐审计、跨包一致性校验、成本比对、防御自检，防止目标漂移、验收失真与摘要偏差。用于跨会话长任务、多 worker 并行、审计类任务、成本敏感任务的 checkpoint 记录与恢复，以及任何需要"决策层不跑偏"保障的执行场景。
Query and analyze the AI Counsel decision graph to find past deliberations, identify patterns, and debug memory issues
Ask the minimum set of high-value decision questions needed before turning the task into canonical implementation rules.
Record decisions with their context and predictions to enable honest calibration and defeat hindsight bias. Use when making consequential decisions you want to learn from later.
Detect and surface potential decision-making in work items, plans, diffs, docs, or summaries. Use to flag possible decisions neutrally without enforcing process.
Link commits, PRs, tasks, or bugs to a decision. Use when the user invokes /decision-link.
Reconstructs a chronological log of every significant decision made across project email threads — what was decided, who decided it, when, and what alternatives were considered.
Set up the team decision log that ends relitigation — the one-line-per-decision format (what, why, who, when, reopening rule), the capture moments wired into existing rituals, and…
Transforms any decision discussion into a structured Decision Record with context, options considered, rationale, and trigger conditions for revisiting
Capture architectural and implementation decisions with rationale to prevent re-debating. Creates and maintains DECISIONS.md.
Decision rules for Claude Code skills, scripts, MDs, and workflows - project-agnostic patterns
Structured decision-making framework — weigh options, evaluate trade-offs, deliver clear recommendations
Structured approaches to decisions under uncertainty and complexity. Covers expected value, decision trees, multi-criteria decision analysis, System 1 vs System 2 allocation,…
Create, update, or resume a durable multi-session map of unresolved decisions and their dependencies.
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Aide à prendre une décision complexe en structurant les options et critères. À utiliser quand l'utilisateur hésite entre plusieurs choix.
Run meetings that actually decide — the pre-read-then-decide format, the options-on-the-table rule, the decider named before debate starts, and the recorded-or-it-didn't-happen…
Apply the most relevant mental models (First Principles, Inversion, Second-Order Thinking, Occam's Razor, and 16 others) to any problem or decision, surfaces non-obvious insights…
Map and optimize decision moments across Awareness, Consideration, Conversion, and Retention, then attach specific assets, visuals, and automations to each stage.
Map and optimize decision moments across Awareness, Consideration, Conversion, and Retention, then attach specific assets, visuals, and automations to each stage.
Guide stuck or overwhelmed users through targeted branching questions until they reach concrete next steps.
Audits AI-assisted legal, compliance, governance, and institutional decisions before reliance to determine whether the responsible human or institution has enough access to the…
Run a decision past a panel of clashing advisors — an optimist, a pessimist, a numbers person, an ethicist, and future-you — then get a chair's verdict.
Produces a set of surgical edits across all documents affected by an architectural decision, plus a decisions block in STATUS.md that serves as the coherence checkpoint.