Results for “branch-by-abstraction”

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

Split an idea or active research path into two or more new research product-path stubs after alignment approval; preserves the source path by default and archives it only when --archive is passed

Crawl a live website, extract its design system, brand surface, and page inventory, and save the snapshot under stardust/current/ for downstream redesign or migration.

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

Design a Concrete-Pictorial-Abstract learning sequence for a mathematical concept using manipulatives. Use when teaching maths through Singapore method or when students struggle with abstraction.

Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.

Detect model stealing, model inversion, and membership inference performed through inference-API abuse by monitoring query patterns, applying output perturbation, and red-teaming your own model's extractability.

Rank a topic's user-flow branches by proof priority (value × risk × frequency) right after user-flow-map, ordering the branches, gating variation breadth, and promoting or pruning flows so state-model and ux-variations grow the tree in proof order — writes only existing flow-tree ordering fields, no schema change.

Spawns parallel reasoning branches under different cognitive frames to explore non-obvious solutions for open-ended design, architecture, naming, and fuzzy debugging problems, then scores, clusters, and deepens the most promising ideas.

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.

Identifies recurring patterns across three or more domains to extract universal principles and apply them to new contexts.

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".

Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.

Traces software supply chain provenance from source to runtime, identifying divergence points in dependency resolution, build, packaging, and release pipelines.

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

Extract Lineage from Fabric Artifacts

Researches a leader's organizational affiliations and fetches logos, producing a JSON record for logo strips and social-proof sections.

Creates digital banners for social, display, hero, and email formats, applying behavioral science principles to maximize attention and conversion.

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。

Distill learnings from a completed repo analysis into reusable knowledge base entries in ~/.copilot/context/. Use after finishing a repo-analysis to make the learnings persistent and searchable.

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.

Patent prior-art and landscape intelligence skill — not generic patent help. Commits to one of five sub-use-cases via forcing intake (novelty search / freedom-to-operate / competitive landscape / acquisition diligence / litigation prior-art) before any search runs. Searches Google Patents, Espacenet, USPTO, and optionally Lens.org for citation-graph signals. Output is an editable Word document (.docx) with verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags where applicable, strategy recommendations, and full audit log. Use when the user asks for patent searching or analysis (e.g., 'prior art search for [invention]', 'freedom to operate analysis for [product]'). Produces search signal, not legal advice — always recommends consulting a patent attorney before filing or licensing decisions. Trademark, copyright, and trade-secret questions are out of scope.

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.

"Anomaly" covers three distinct problems, and a detector built for one is close to

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

Segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks with zero-shot transfer.

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Botany Based Derivation Skill

Off-page playbook (Lesson 10, outreach). Turns a vetted link-prospect list into them-focused outreach drafts that earn links without spamming. Picks the RIGHT people (those who LINKED to or MENTIONED our topic — never "people who tweeted it"), gives each a real "excuse" (fresh-angle / new-proof / ego-bait), keeps to ≤1 follow-up, and never makes a pushy link ask. Drafts only — every outward send is operator-gated. Outreach is a tool, not a strategy.