Results for “what-if”

Friendly docflow readiness check: one status, one reason, and the exact next command. Use when asked if docflow is set up, ready, or "what do I do next".

Discover what bundled skills exist in this mimir install and what each one does. Use when you're not sure if a capability is already covered by a skill ("can I X?", "is there a skill for Y?", "what skills do I have?"). Reads SKILL.md frontmatter from each skill directory and surfaces names + descriptions.

Use this skill when managing post-SAP follow-up testing for a driver. Covers the testing cadence, recordkeeping, what happens if a test is missed, and how to transition the schedule to a new employer.

Map symbol dependencies, callers, and blast radius before editing code. Load when the user asks what depends on a symbol, what breaks if they change something, blast radius of a change, reverse dependencies, or which tests cover a function. Also triggers on "who calls this", "impact of changing", "dependency map", "what uses this", "find callers", or before any non-trivial edit when safe-change is not yet active. Pairs with codebase-understanding for broad architecture; this skill is symbol-scoped and edit-gated.

Clarify requirements before implementing by asking targeted questions when a request has multiple plausible interpretations or key details are unclear.

Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition, method (A/B, holdout, switchback, quasi-experiment, MAB), MDE/duration plan, peek policy, validity threats, and pre-committed decision rule. Platform-agnostic. Load when the user has a candidate experiment and needs to spec it before launch, or says "spec this experiment", "write the test plan", "design this A/B test", "what's the hypothesis", "how big a sample do we need", "how long should we run this", "define the metrics for this test", or when the experimentation orchestrator routes here.

Stop. That last message did not land — re-pitch it. Use when the user says "wait what", "I don't follow", "explain that again", or similar confusion signals.

Compare, cross-review, and merge competing plans from multiple agents into one executable direction with a clear handoff.

Iterate on a pull request until actionable CI checks pass and high/medium review feedback is addressed, stopping at human approval, draft, or merge gates.

First-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusions from verified premises. Bilingual: auto-detects Chinese or English.

胡一菲（情景喜剧虚构）认知与表达框架（压缩蒸馏）：公寓女王、武力梗喜剧化、嘴硬心软 触发：爱情公寓 等。虚构；忌暴力模仿

Package a customer escalation for engineering, product, or leadership as a decision-ready handoff — impact, timeline, facts vs. hypotheses, and a specific ask with an owner.

Guides dose escalation for obesity pharmacotherapy based on efficacy and tolerability while staying within approved upper dose limits. Triggers include clinician questions like "How should I titrate naltrexone/bupropion if the starting dose is tolerated?" or "What is the maximum liraglutide dose I can use?"

Build a compact, validation-gated implementation plan for multi-step, risky, or ambiguous work — typically when phases need explicit checkpoints, the change touches multiple files/services, or the user wants alignment before execution. Output goes to `.claude/plans/<topic>.md` (or `.agents/plans/`) with goal, in/out-of-scope, phased steps, validation per phase, and replanning triggers. Skip for trivial single-file fixes, bug investigations (use `tracer`), or open-ended exploration (use `explore`). Pair with `ship` once the plan ends and merge work begins.

Write the executable feature specification — the WHAT and WHY artifact that agents and reviewers treat as source of truth. Owns both /specify and /clarify modes. Load when the user asks to write a feature spec, write a specification, write an executable spec, define functional requirements, capture acceptance criteria as Given/When/Then, or when the spec-driven-development orchestrator routes here. Also triggers on "feature spec", "executable spec", "/specify", "/clarify", "write the spec for this feature", "specification for", "spec-driven", "machine-readable spec". Output: docs/specs/YYYY-MM-DD-<slug>-feature-spec.md. Hard gate: cannot Approve while [NEEDS CLARIFICATION] markers remain.

Council

Update or correct an existing skill file based on judge feedback or improved understanding.

Close a work session without losing what just happened. Write a handoff brief that captures progress, the decisions you made, the unfinished items and their next steps, and the details that would evaporate overnight, then it asks whether to commit or save it, never automatically. Trigger on "wrap up this session", "write a handoff", "close out for the day", "hand this off", "what did we get done", or the end of any working session you might have to resume later.

Give a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a user-supplied approach set. Use for a solo POV, a mid-session second opinion, a named-peer cross-check, any request to consult other models or reconcile their opinions, an `oracle` panel, or a correction-cost-gated proactive cross-check offer. Not for findings review (use ce-doc-review), neutral explainers, or generating options (use ce-ideate or ce-brainstorm).

Challenge decisions, surface counter-arguments, flag assumptions. Trigger: 'should I', 'is this right', 'critique', 'poke holes', 'second opinion', 'devil's advocate'. Auto-fired by ijfw-intent-router.

当面对新任务或目标，因过度思考“如何开始”或“需要多久”而陷入拖延、焦虑，迟迟无法行动时

Structured workflow to reproduce, diagnose, plan, fix, verify, and record a bug fix, requiring a deterministic reproduction before diagnosis and minimal changes only.

当需要将生活或工作中的复杂情境转化为可管理、可执行的系统时，或当感到迷茫、缺乏动力、陷入社会比较时，调用此模型来重新构建认知和行动框架

Discovers connected MATLAB-supported hardware devices, searches by capability, and checks required support packages and add-ons. Use when the user asks what hardware is connected, finds a device that supports a capability (e.g., CAN, analog input), or checks if required support packages or add-ons are installed.

Break a stuck or complex problem into the smallest sub-question that, if answered, unlocks the next step — then answer it and repeat until the path forward is clear. Load when a problem feels genuinely stuck, when reasoning keeps circling, or when deep-thinking diagnoses a Socratic frame. Also triggers on "I keep going in circles", "what is the real question here", "help me reason through this step by step", "unstick my thinking", "recursive questioning", "what is the root question". Based on the recursive Socratic questioning method (EMNLP 2023) which outperforms CoT and Tree-of-Thought on complex reasoning tasks.

Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with structured-planning and debug-and-fix. Does not replace root-cause debugging — adds plan-level path selection.

Self-contained code review checklist — formatting, type safety, duplication, readable conditions, logic-out-of-UI, test coverage, comment quality. Adapts to whatever tooling the project actually has (skips Prettier/TypeScript/test-runner checks if unconfigured). Use before merging, after completing a feature, or any time you want a second pass on code quality. In Claude Code, prefer the official `code-review` skill or `pr-review-toolkit`/`feature-dev` code-reviewer agents instead — both are real, installed, and go deeper than this checklist. This copy exists for Codex/Cursor portability, where those agents aren't available.

Approach an app, tool, codebase, website, or product as a genuine first-time user with zero insider context — try it out using only the information provided, get confused where a real newcomer would, and surface the "obvious" questions that people who built or use the thing daily can no longer see. Use this whenever the user wants a first-time-user test, a fresh perspective, a naive walkthrough, a cold read of their README/onboarding/docs/UI, or says things like "pretend you've never seen this", "would a new user get this?", "test my app like a beginner", "what would confuse someone new?", or "give me fresh eyes on this". Also use it when someone wants to find gaps in onboarding, docs, or first-run experience — even if they don't say "fresh eyes" explicitly.