Results for “problem-reformulation”

Provides a structured methodology for solving nontrivial, ambiguous problems by framing outcomes, selecting evidence, routing specialists, choosing options, and verifying results.

Iteratively improves a compiled LaTeX paper through two rounds of external LLM review, fix implementation, and recompilation.

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.

Convert plans/specs into independently-grabbable vertical slice issues (HITL or AFK classification)

Turn owner feedback about agent behavior into concrete system changes. Use when the owner says something is off, wants the assistant to improve how it operates, asks for a reflection, or wants a durable fix instead of a one-off apology.

Guide teams through MITRE's Problem Framing Canvas to clarify problem statements before jumping to solutions.

Tactical fast path: turn a small problem, bug report, edit request, or narrow refactor into three deliverables — a brief change-spec (docs/specs/), a detailed implementation-ready plan (docs/plans/), and a TODO.md with agent-pickable tasks and milestones. Load when the user describes a tactical problem and wants quick planning artifacts, says "plan this change", "create a TODO", "write a plan for this", "problem to plan", "break this into tasks for agents", "I want to change X — plan it", or when process-decomposer routes here after determining the user needs lightweight planning deliverables. Also triggers on "create tasks from this problem", "make this actionable", or "turn this into a plan agents can execute". For feature-sized work that needs an executable spec + constitution + cross-check gate, route to `spec-driven-development` (or `feature-spec`) instead.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Improves structure without behavior changes, using tests and focused slices; not for features unless behavior change is explicit.

Repairs failed task verification by choosing a strategy: retry with adjustments, decompose into sub-tasks, prune infeasible tasks, or escalate to the user.

Autonomously repairs failed task verification by choosing retry, decompose, prune, or escalate strategies before surfacing to the user.

Review a code file or directory and produce an evidence-backed GitHub or Jira issue proposing bug fixes, performance improvements, modularity improvements, DRY refactors, file splitting, reusable helpers, and architecture-alignment work. Use when a user asks for a code review, technical-debt proposal, refactor proposal, quality audit, bug-risk review, architecture-alignment review, or issue creation. This skill proposes work; it does not modify code.

通用多轮迭代改进：对任意研究制品反复调用 /review → 解析反馈 → 修复 → 更新 wiki，直到达标

Diagnoses a reported bug, error, test failure, or unexpected behavior through a 4-phase root-cause analysis before any code changes.

Clusters a GitHub issue backlog by root cause into plan-master issues, redirects children with a standardized comment, and bundles architectural-fix PRs that close clusters atomically.

Universal transformation λ(ο,K).τ with recursive self-improvement. USE WHEN routing reasoning, validating knowledge graphs, preparing CICM/ANZCA examinations, or when self-improvement of reasoning/architecture/context is required. Routes queries through R0-R3 complexity pipelines, validates topology (η≥target) and governance (KROG), emits per style (Φ), and compounds learnings into knowledge K. Triggers on complexity assessment, multi-step reasoning, examination mode, or /λ invocation.

Transforms vague ideas into structured, actionable concepts through guided divergent and convergent thinking, producing a markdown one-pager.

Review git diffs or file scopes for code reuse, quality, efficiency, and clarity issues, then optionally apply safe, behavior-preserving fixes.

Systematic root-cause analysis for bugs, errors, and unexpected behavior

Master orchestrator to resolve a PR by diagnosing state and delegating to specialized skills.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Orchestrate altering an existing, working feature to new desired behavior by updating tests first, then changing implementation, reviewing, and committing with gated approval.

Diagnose bugs, failing tests, or unexpected behavior by reproducing, isolating, hypothesizing with evidence, and confirming fixes before making changes.

Resolves GitHub issues using isolated worktrees and test-driven development, then delegates PR creation to /github:create-pr so the quality gate and the /github:review-pr loop always run. This skill should be used when the user asks to "resolve an issue", "fix issue

Runs a relentless interview that sharpens a plan or design. Use when the user wants to be grilled on an idea, pressure-test a plan, or refine a design through questioning.

Breaks a plan, spec, or PRD into independently-grabbable issues using tracer-bullet vertical slices, then publishes them to the project issue tracker.

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

Systematic debugging — reproduce, read the error, isolate, hypothesize, fix, verify, document. Use when tracking down a bug, unexpected behavior, or test failure — including phrases like "this doesn't work", "why is this failing", or "help me debug".

Diagnose and repair failing CI for an existing pull request without reopening the implementation pipeline.

Diagnose and fix a bug through a disciplined reproduce, isolate, diagnose, fix, verify loop driven by evidence and one hypothesis at a time — not guesswork.

Audit a repository, vet and prioritize evidence-backed findings, write drift-aware implementation plans, delegate bounded work, and independently verify results. Use when asked to improve, audit, modernize, harden, review, plan fixes for, or systematically reduce risk in a codebase. Use native isolated agents for implementation; use OpenRouter/free only for narrow advisory audit slices under its safety limits.