数据与 AI技能

Debug "API returns data that doesn't exist in database" when multiple Kubernetes clusters exist (production, staging, POC). Use when: (1) REST API returns records that direct database queries can't find, (2) Data counts match approximately but specific records don't overlap, (3) kubectl context points to a different cluster than the one serving the public domain, (4) ClickHouse/Postgres queries return stale or different data than the API, (5) "completely different datasets" despite same table names and schemas. Root cause: querying the wrong cluster's database.

中文简介正在准备中。当前显示原文说明。

Fix macOS app hard crashes (EXC_CRASH / SIGKILL) caused by accessing TCC-protected APIs without the matching Info.plist usage description key. Use when: (1) App crashes immediately when touching Photos, Contacts, Calendar, Reminders, Location, Microphone, Camera, Screen Recording, etc., (2) Crash report shows `Exception: EXC_CRASH (SIGKILL)` with `Termination namespace: TCC`, (3) Crash stack includes `TCC.__TCC_CRASHING_DUE_TO_PRIVACY_VIOLATION__`, (4) Termination details contain "This app has crashed because it attempted to access privacy-sensitive data without a usage description", (5) Flutter macOS publish / gallery-save flow crashes on Gal.putVideo, PHPhotoLibrary, CNContactStore, etc. Critical distinction: macOS does NOT return a deny error — it SIGKILLs the process. This skill also covers the NSPhotoLibraryUsageDescription vs NSPhotoLibraryAddUsageDescription distinction that trips many apps.

中文简介正在准备中。当前显示原文说明。

Fix silent data loss when mutating Nostr replaceable events (Kind 0 profile, Kind 3 contact/follow list, Kind 10002 relay list, etc.) in client apps. Use when: (1) Following someone wipes the user's entire follow list, (2) Updating profile metadata loses existing fields, (3) Fresh browser session or mobile login causes data loss on first action, (4) Replaceable event mutation uses stale or null cached state. Root cause: Nostr replaceable events are full-replace (no partial update), so publishing based on stale/unloaded cache overwrites the canonical version. Applies to any Nostr client using React, Flutter, or similar reactive frameworks where query state may not be loaded when a mutation fires.

中文简介正在准备中。当前显示原文说明。

Fix Flutter PageView "snap back" or scroll position reset issues on provider/state rebuilds. Use when: (1) PageView scrolls then snaps back to previous page after state update, (2) Scroll position resets when Riverpod/Provider rebuilds, (3) Feed scrolls back to top on data refresh, (4) PageView loses position after orientation change or widget rebuild.

中文简介正在准备中。当前显示原文说明。

Optimize slow PostgreSQL inserts in Python using psycopg2. Use when: (1) Row-by-row inserts are taking too long over network, (2) executemany() isn't providing speedup, (3) Migrating large datasets to PostgreSQL, (4) Network latency making individual INSERT statements impractical. The key is using execute_values() from psycopg2.extras instead of executemany() or individual execute() calls.

中文简介正在准备中。当前显示原文说明。

Select appropriate Ollama models for processing sensitive but legal content. Use when: (1) llama3.2 or deepseek-r1 refuses to process content with "I cannot assist" responses, (2) Local LLM returns generic safety disclaimers instead of following instructions, (3) Need to process adult content, sex work data, or other legal-but-sensitive material through a local LLM. Also covers using /api/chat vs /api/generate for system prompt support, and structuring prompts for consistent format compliance.

中文简介正在准备中。当前显示原文说明。

Fix Gorse 0.5.x recommendation engine silently disabled or degraded due to config incompatibility with 0.4. Use when: (1) Gorse 0.5 recommendations are poor/empty despite having data, (2) collaborative filtering appears disabled even though [recommend.collaborative] section exists, (3) migrating Gorse config from 0.4 to 0.5, (4) old config keys like [recommend.popular], [recommend.neighbors], [recommend.online], [recommend.offline] are being used with Gorse 0.5. Critical: type="mf" must be explicitly set in [recommend.collaborative] or CF is silently disabled (default "none").

中文简介正在准备中。当前显示原文说明。

Fix psycopg2 "IndexError: tuple index out of range" when using LIKE with parameterized queries. Use when: (1) cursor.execute() fails with IndexError on a query containing LIKE '%pattern%', (2) SQL LIKE wildcards conflict with psycopg2 %s parameter placeholders, (3) Query works in psql but fails in Python. The % character has dual meaning: SQL LIKE wildcard AND psycopg2's parameter substitution marker.

中文简介正在准备中。当前显示原文说明。

Art direction for any content — reads text, PDF, Word, HTML, PPT, then proposes 2-3 creative directions with photography style, mood, and visual language. After selection, generates AI image prompts and visual briefs section-by-section. Use when the user shares content and needs visual direction, image sourcing, or creative direction for any material.

中文简介正在准备中。当前显示原文说明。

Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts. Generates 4 interconnected docs — SPECIFICATION.md, IMPLEMENTATION.md, TASKS.md, BRANDING.md — plus a self-contained PROMPT.md for autonomous execution by any coding agent. Includes interactive tech stack selection, design pattern recommendations, and architecture decisions with trade-off analysis. Trigger when user wants to: plan a project, create specs, architect a system, break work into tasks, choose a tech stack, get design pattern advice, generate a coding agent prompt, or do documentation-first development. Phrases: "plan my project", "spec this out", "architect", "help me plan", "what stack should I use", "generate a prompt", "break this into tasks", "project docs", "I want to build X".

中文简介正在准备中。当前显示原文说明。

Render Obsidian-style weighted graph views from book JSON, keyword indexes, TOCs, card data, or node-link data. Use when the user asks for Obsidian graph view, graph view png, weighted graph, keyword graph, directory-keyword graph, spherical graph visualization, or high-weight nodes centered with clear Chinese labels.

中文简介正在准备中。当前显示原文说明。

Create companion Codex workflows from book chapters, reader exercises, prompts, field notes, and teaching material. Use when Codex needs to turn a chapter excerpt, 書籍練習, AI 提示詞, worksheet, or author note into a reusable Skill-style workflow, GitHub-shareable companion artifact, or book link resource for readers.

中文简介正在准备中。当前显示原文说明。

Generate systematic refinement steps from high-level specifications to concrete implementations in Isabelle/HOL or Coq, preserving correctness obligations at each step. Use when working with formal verification, program refinement, proof development, or when translating abstract specifications into executable code while maintaining formal guarantees. Supports data refinement (abstract types → concrete structures), algorithmic refinement (specifications → algorithms), and stepwise refinement with proof obligations.

中文简介正在准备中。当前显示原文说明。

Automatically extract abstract finite-state models in SMV/NuSMV format from source code (C/C++, Java, Python) for formal model checking. Use when users need to: (1) Generate SMV models from program code for verification, (2) Extract state-transition models from protocol implementations, (3) Analyze control flow and data flow to construct formal models, (4) Create models for checking safety and liveness properties, (5) Convert imperative code to declarative state machines. Particularly effective for protocol implementations, concurrent systems, and control logic with clear state transitions.

中文简介正在准备中。当前显示原文说明。

Identify bug-introducing commits using semantic analysis that extends traditional SZZ algorithm. Distinguishes semantic changes from refactorings or code movements using control-flow and data-flow similarity analysis. Use when analyzing bug-fix commits to trace back to bug-introducing changes, investigating software evolution, conducting empirical studies on defect prediction, or reducing false positives in bug localization. Supports git repositories and provides explanations for why commits are identified as bug-introducing.

中文简介正在准备中。当前显示原文说明。

Generate formal specifications (definitions, predicates, invariants, pre/post-conditions) in Isabelle/HOL or Coq from informal requirements, source code, pseudocode, or mathematical descriptions. Use when users need to: (1) Formalize algorithms or data structures, (2) Create function specifications with contracts, (3) Generate predicates and properties for verification, (4) Translate informal requirements into formal logic, (5) Specify invariants for loops or data structures, or (6) Create formal definitions for mathematical concepts. Supports both Isabelle/HOL and Coq equally.

中文简介正在准备中。当前显示原文说明。

Generate complete, production-ready functions and classes from formal specifications, design descriptions, type signatures, or natural language requirements. Use this skill when implementing APIs from specifications, creating data structures from schemas, building classes from UML diagrams, generating code from contracts, or translating design documents into code. Supports multiple programming languages and follows language-specific best practices.

中文简介正在准备中。当前显示原文说明。

Automatically generates change logs from git commits, patches, and pull requests. Use when preparing software releases, creating version summaries, or maintaining CHANGELOG.md files. Analyzes commit messages (including conventional commits), diff/patch files, and PR data to produce categorized Markdown change logs organized by type (Features, Bug Fixes, Breaking Changes, etc.). Ideal for release notes, version updates, and automated changelog maintenance.

中文简介正在准备中。当前显示原文说明。

Identifies and analyzes conflicts in software requirements including logical contradictions, technical incompatibilities, resource constraints, timeline issues, data conflicts, and stakeholder priority mismatches. Use when reviewing requirement sets, specifications, user stories, or project plans to detect conflicts that could block implementation or cause rework. Provides detailed conflict analysis with resolution strategies and impact assessment.

中文简介正在准备中。当前显示原文说明。

Performs abstract interpretation over source code to infer possible program states, variable ranges, and data properties without executing the program. Reports potential runtime errors including out-of-bounds accesses, null dereferences, type inconsistencies, division by zero, and integer overflows. Use when analyzing code for potential runtime errors, performing static analysis, checking safety properties, or verifying program behavior without execution.

中文简介正在准备中。当前显示原文说明。

Full-stack autonomous math modeling agent for CUMCM (全国大学生数学建模竞赛). Reads the problem statement and data, iterates through research → coding → verification → LaTeX writing, and produces a publication-quality PDF paper. Use when the user provides a CUMCM problem and wants end-to-end automated modeling, coding, and paper generation.

中文简介正在准备中。当前显示原文说明。

Monthly social media performance review for SMBs. Analyses post-level and account-level data from Instagram, LinkedIn, Facebook, or TikTok. Identifies what worked, what didn't, and why. Produces a client-ready report and specific recommendations that feed back into the content calendar. Accepts CSV exports, screenshots, or manual data input.

中文简介正在准备中。当前显示原文说明。

Pixel Path turns any two places (optionally via waypoints) into a pixel-art fly-through of the real road. It routes the trip, bakes the real buildings, land cover, landmarks, hills and horizon from OpenStreetMap and elevation data, generates scenery art with RetroDiffusion at a chosen level of detail (sparse, moderate or detailed; estimated up front, quoted exactly for free, budget-capped; free placeholder art also works), builds a page where you zoom along the route and scroll to go faster or slower, and runs a self-check that screenshots the result. Use when someone asks for a "pixel path", a "pixel road trip", to "drive" or "fly" from X to Y in pixel art, or a retro first-person view along a real route.

中文简介正在准备中。当前显示原文说明。

Analyze Excel/CSV files with DuckDB SQL via bash.

中文简介正在准备中。当前显示原文说明。