gongyijie85
- 132 skills
- 0 followers
- 1 day ago last updated
- ▌ Prototype · gongyijie85构建一个 throwaway（一次性）原型来回答设计问题。当用户想验证某个 state model（状态模型）或逻辑是否合理，或想探索 UI 应该长什么样时使用。
- ▌
- ▌ Wayfinder · gongyijie85把一个巨大的工作块(超过单个 agent 会话所能承载)规划为 issue tracker 上的一张共享决策 ticket 地图,并逐个解决这些 tickets,直到通往目的地的路线清晰可见。
- ▌ To Tickets · gongyijie85把一个 plan、spec 或当前对话拆分为一组 tracer-bullet ticket,每个 ticket 声明其 blocking edges,并发布到已配置的 tracker——本地以文本记录 edges(每个 ticket 一个文件),真实 tracker 则使用原生 blocking 链接。
- ▌ Code Review · gongyijie85沿两个轴审查自某个固定点(fixed point,commit、分支、tag 或 merge-base)以来的变更 — Standards(代码是否符合本仓库文档化的 coding standards?)和 Spec(代码是否实现了原始 issue/spec 所要求的内容?)。两个审查在并行 sub-agents 中运行,并排报告结果。当用户想审查一个分支、一个 PR、进行中的变更,或说 "review since X" 时使用。
- ▌ Codebase Design · gongyijie85设计 deep modules(深模块)的共享词汇。当用户想要设计或改进模块的 interface、寻找 deepening(加深)机会、决定 seam 放在哪里、让代码更可测试或更易被 AI 导航,或当其他 skill 需要 deep-module 词汇时使用。
- ▌ Diagnosing Bugs · gongyijie85针对棘手的 bug 和性能 regression 的诊断回路。当用户说 "diagnose"/"debug this",或报告某样东西 broken/throwing/failing/slow 时使用。
- ▌ Domain Modeling · gongyijie85构建并打磨项目的 domain model(领域模型)。当讨论 codebase 术语、编写或编辑 CONTEXT.md,或记录或编辑 ADR 时使用。
- ▌
- ▌
- ▌ Setup Matt Pocock Skills · gongyijie85为工程类 skills 配置本仓库——设置它的 issue tracker、triage 标签词汇与领域文档布局。在首次使用其他工程类 skills 之前运行一次。
- ▌
- ▌ Improve Codebase Architecture · gongyijie85扫描代码库寻找 deepening（加深）机会，将其呈现为可视化 HTML 报告，然后对你选中的那一项进行 grilling（拷问）式深入探讨。
- ▌ Repo Scan · gongyijie85Bootstrap pointer that installs the external repo-scan skill from a pinned, reviewable commit. Use when repo-scan must be installed before running its cross-stack source-code asset audit; this ECC pointer does not perform the audit itself.
- ▌ Ito Compute · gongyijie85 bundleQuery live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô compute status, validate GPU nodes, revoke Itô access, or rent or purchase GPU compute and needs the supported boundary explained.
- ▌ Configure Ecc · gongyijie85Guide ECC installation, update, or reconfiguration from inside Claude Code, Codex, or Kimi while respecting each harness's real plugin, scope, and hook capabilities.
- ▌ Delivery Gate · gongyijie85Stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits. Use when Claude should be mechanically blocked from declaring work finished before quality checks and learning capture actually pass.
- ▌ Django Security · gongyijie85Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations. Use when reviewing Django authentication, authorization, input handling, or deployment settings.
- ▌ Docker Patterns · gongyijie85Docker and Docker Compose patterns for local development, hardened CLI installer harnesses, container security, networking, volumes, and multi-service orchestration. Use when creating or reviewing Dockerfiles and Compose services, testing installers across Linux distributions, or planning accurate native macOS and Windows validation.
- ▌ Golang Patterns · gongyijie85Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications. Use when writing or reviewing Go code and idiomatic structure or conventions are in question.
- ▌ Prisma Patterns · gongyijie85Prisma ORM patterns for TypeScript backends — schema design, query optimization, transactions, pagination, and critical traps like updateMany returning count not records, $transaction timeouts, migrate dev resetting the DB, @updatedAt skipped on bulk writes, and serverless connection exhaustion. Use when writing a Prisma schema or query, or debugging transactions, migrations, or serverless connection limits.
- ▌ Backend Patterns · gongyijie85Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when building or reviewing Node.js, Express, or Next.js API routes and their data access.
- ▌ Coding Standards · gongyijie85Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns. Use when reviewing code quality or naming with no framework-specific skill that applies.
- ▌ Prompt Optimizer · gongyijie85Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
- ▌ Tasteforge Video · gongyijie85Use for file-driven multimodal image, video, and 3D-asset discovery; taste interviews; distill or apply workflows; style-pack validation; editable EDL/FCPXML export; provenance audits; and offline planning that must fail closed before provider generation.
- ▌ Gan Style Harness · gongyijie85GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper. Use when a feature should be built autonomously through generator and evaluator iteration until it clears a quality bar.
- ▌ Loop Design Check · gongyijie85Design a goal-oriented agent loop, and review it for the ways loops go wrong — spinning and burning tokens, Goodhart-gaming the verifier, or running a wrong answer to completion. Two actions: (1) WRITE a loop — gate whether to build it, define a machine-decidable goal, pick the loop type, pick a skeleton; (2) REVIEW a loop — run it past five failure modes plus decidability, boundaries, fallback, judge independence, and keep-judgment-with-the-human red lines. Use when designing an autonomous agent loop, or when you already have one and worry it will spin, cheat, or run a wrong answer to the end. Complements the mechanism-layer loop skills (autonomous-loops, continuous-agent-loop) by covering the judgment layer they don't. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent a runaway loop, goal-oriented loop, decidable goal, plan/build/judge.
- ▌ Verification Loop · gongyijie85A comprehensive verification system for Claude Code sessions. Use when verifying a Claude Code session's work before claiming it is complete.
- ▌ Nasiko Control Plane · gongyijie85 bundleInstall, detect, and operate the optional Nasiko agent control plane through ECC with pinned artifacts, explicit consent, and telemetry and secrets boundaries.
- ▌ Quarkus Verification · gongyijie85Verification loop for Quarkus projects: build, static analysis, tests with coverage, security scans, native compilation, and diff review before release or PR.
- ▌ AI Regression Testing · gongyijie85Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.
- ▌ Cost Aware LLM Pipeline · gongyijie85Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. Use when LLM spend needs to come down, or when routing tasks across model tiers and budgets.