Results for “branch-by-abstraction”

Create a git branch following Sentry naming conventions, automatically deriving the branch type and description from current work context.

Apply the Von Restorff Effect to make the most important element visually distinct from its surroundings, improving attention and recall.

Auto-extract reusable patterns from the current session into skills or memory

Safely create, adopt, publish, or clean up an issue-backed non-primary Git branch without force-pushing or absorbing ambiguous work

Extract a bounded part of the invoking codebase into a new GitHub repository with private and public-OSS readiness gates

Composite skill — one-pass cleanup of stale local branches, dead worktrees, merged branches, and abandoned remote PR branches. Chains `git fetch --prune` → `clean_gone` (kill [gone] branches) → worktree prune + offer-to-remove dead worktrees → list-and-delete branches merged to main and release → delete remote PR branches whose PRs merged >7 days ago. Use instead of running `clean_gone` alone — that only catches half the rot. Daily-friction composite; fires on "clean up branches", "branch hygiene", "stale worktrees", and on session start when local branch count > 30.

Find a single insight that eliminates multiple components by recognizing when seemingly different systems share a common underlying pattern.

Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract insights", "mine this", "process this".

Deletes local git branches whose upstream is gone, removing attached worktrees first.

Extract Lineage from Fabric Artifacts

从 PAPER_PLAN 起草 LaTeX 论文：逐 section 从 wiki 取材撰写 + 生成 figures/tables + BibTeX 验证 + de-AI polish

Scores any US stock ticker through Warren Buffett's four-lens framework (business simplicity, moat, management, valuation) and returns a weighted HOLDABLE/WATCHABLE/AVOID verdict.

当用户提出短篇短剧、动画短片、微电影、剧情视频、AI视频、影视化短片、动态漫、宣传片、预告片等**单集 5-10 分钟以内**的短篇制作需求，或包含"做个短剧"、"拍个微电影"、"弄个动画短片"、"写个短剧剧本"、"画个分镜"、"搞个人设/场景资产"、"出个关键帧"、"写图生视频提示词/Seedance提示词"等表达时调用。适用于需要按"规划-剧本-分镜-资产-关键帧-视频生成"推进完整视频生产流程的短篇场景。**不承接几十集连续短剧、长篇商用短剧、连续剧、连续番剧的完整制作**；如遇此类需求，明确声明本 skill 边界并建议用户使用专门的长篇短剧工具或分批下单。

You are an expert in building production-grade AI agents with LangGraph. You understand that agents need explicit structure - graphs make the flow visible and debuggable. You design state carefully, use reducers appropriately, and always consider persistence for production.

Analyzing session replays, extracting persona-based behavioral patterns, and storytelling UX issues. Reads the 'why' from real user operation logs. Works with Field/Echo for persona validation.

Multi-project signal isolation with cascading recipe resolution

Botany Based Derivation Skill

Algebra Based Derivation Skill

Root reference for litigation practice spanning civil, criminal, and administrative proceedings. Provides sub-area taxonomy, core principles, and routing guidance. Use when classifying litigation work, routing to a sub-practice skill, or applying general litigation standards.

Extract a learned skill from the current conversation

Understand through recursive decomposition and modular reconstruction of simple operations to reproduce emergent complexity. Use this skill whenever reasoning is required. Framework for [[#parse|parsing]], [[#branch|branching]], [[#reduce|reducing]], [[#ground|grounding]] and [[#emit|emitting]]. Employs metacognitive reasoning epistemology, leveraging first principles through recursive decomposition[^1]. Self-referential and scale-invariant.

JS Bridge Pattern

Deconstruct vague business concepts into atomic-level clarity using Wittgenstein's language philosophy and Austrian economics.

Reduction is a trade, not an improvement.

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

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

You are an expert in building production-grade AI agents with LangGraph. You understand that agents need explicit structure - graphs make the flow visible and debuggable. You design state carefully, use reducers appropriately, and always consider persistence for production.