本文へ移動
cccskills
無料GitHub で公開

fec-alchemy

Use when absorbing ideas, capabilities, workflows, architecture, quality systems, ecosystem extensions, or engineering practices from any reference system into the current project through original, project-native redesign rather than copying.

インストール方法を見る

含まれるファイル(6)

  • SKILL.md5.5 KB
  • assets/absorption-plan-template.md888 B
  • assets/intake-template.md1.6 KB
  • assets/review-checklist.md1.3 KB
  • references/methodology.md5.0 KB
  • references/originality-and-licensing.md2.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Integration of project absorption and originality

Purpose

Convert excellent ideas, capabilities, and engineering practices from one or more reference systems into improvements in the current project that are original, maintainable, and consistent with the target project style.

Suitable for absorbing, borrowing, benchmarking, migrating or integrating another code base, product, framework, library, service, CLI, plug-in, documentation system, AI/Agent tool chain, architecture or engineering workflow. This Skill should not be used for general bug fixes, individual API usage issues, or direct file format conversions, unless the user explicitly requests project-level ingestion or adaptation.

Procedure

  1. Clarify goals and reference systems:
  • Treat the current repository as the target system and its architecture, naming, testing, release model and maintenance boundaries as the source of truth.
  • Treat external repositories, uploaded packages, documentation, examples, product descriptions or running experiences as reference systems that only provide evidence and inspiration.
  • Identify the scope of absorption: product capabilities, architectural patterns, domain models, interface protocols, data flow, runtime behavior, development experience, quality system, delivery process, documentation knowledge or ecological expansion.
  • When there is a lot of information, you can use assets/intake-template.md to create a brief list.
  1. Establish a target project baseline:
  • First read the target project README, package metadata, directory structure, configuration, existing entries, extension points, test commands and release notes.
  • Find out that the target project already has similar capabilities and determine whether they should be enhanced, merged, replaced, split, documented or added.
  1. Scan reference items:
  • Prioritize reading README, package metadata, source code layout, project form related directories, key modules, tests, examples and release notes.
  • Record observations as capabilities, intentions, patterns, and trade-offs, not as a checklist of documents to copy.
  1. Refining candidate capabilities:
  • For each candidate, describe the problem it solves, user value, suitability, dependencies, risks, verifiability and relationship to the current status of the target project.
  • For candidates whose licenses and sources are unclear or whose implementation is highly bound to reference projects, only refine ideas and do not reuse expressions.
  1. Map to target architecture:
  • Redesign using native naming, module boundaries, dependency strategies, coding conventions and testing methods of the target project.
  • Avoid creating parallel systems that compete with existing modules; avoid blindly introducing dependencies just because the reference project uses them.
  • Non-trivial changes can use assets/absorption-plan-template.md.
  1. Original realization or plan:
  • Write new code or new documentation without copying non-trivial code, prompt words, configurations or documentation expressions from the reference project.
  • Unify the boundaries of responsibilities and remove duplicate instructions when absorbing ecological extensions, prompt words, commands, plug-ins, automations, agents or rules.
  • Large tasks are delivered in vertical thin slices first, and rejected or delayed candidates are recorded.
  1. Verification and reporting:
  • Run the most relevant type checks, lints, tests, builds, documentation checks or skill checks.
  • If it cannot be verified, clearly state the cause of the blockage, the scope of the risk and the information that requires user confirmation.
  • Use assets/review-checklist.md for manual review when necessary.

Constraints

  • Don't turn absorb tasks into mechanized diff merging.
  • Does not copy the naming scheme, file structure, or implementation details of the reference project in its entirety.
  • Do not reuse verbatim non-trivial code, documentation, hints, or configurations from reference projects when the license or user intent is unclear.
  • Do not compromise security, privacy, permission boundaries, testing, maintainability, or target project product direction to match the reference project.
  • Do not claim originality unless the output can explain why the target design is different, why it is suitable for the target project, and how to verify it.
  • Don't cram long reference material into the main description; large assignments read references/methodology.md, licenses and original risks read references/originality-and-licensing.md.

Expected Output

Analysis task output:

  • Absorption candidates
  • Recommended target design
  • Realize the plan
  • Description of risks and licenses
  • Verification Checklist

Implementation class task output:

  • Changes completed
  • Instructions for originalization
  • Verification results
  • Remaining work

In warehouse-level tasks, if the host tool supports file editing, the project's local plan document should be created or updated.

Detailed reference

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when reviewing or improving frontend accessibility, semantic structure, keyboard support, focus management, ARIA labels, screen reader behavior, WCAG 2.2 issues, touch accessibility, or assistive-technology regressions; Chinese triggers include accessibility, accessibility, a11y, WCAG, screen reader.

日本語の概要は準備中です。原文の説明を表示しています。

bovinphang/frontend-craft222026年9月26日 更新

用于审查或改进前端无障碍、语义结构、键盘支持、焦点管理、ARIA 标签、屏幕阅读器行为、WCAG 2.2 问题、触控无障碍或辅助技术回归;中文触发词包括 无障碍、accessibility、a11y、WCAG、屏幕阅读器。

日本語の概要は準備中です。原文の説明を表示しています。

bovinphang/frontend-craft222026年9月26日 更新

用于从参考系统中吸收想法、能力、工作流、架构、质量体系、生态扩展或工程实践,并通过原创的项目内重设计转化为当前项目能力,而不是复制原实现。

日本語の概要は準備中です。原文の説明を表示しています。

bovinphang/frontend-craft222026年9月26日 更新

Use when designing, implementing, or reviewing frontend-to-backend API integration, typed API clients, REST/tRPC/OpenAPI client choices, auth refresh, API error mapping, upload flows, SSE/WebSocket/polling choices, CORS-facing frontend behavior, or cross-boundary loading/error states. Do not use for backend-only service architecture or TanStack Query cache policy alone; Chinese triggers include API integration, front-end and back-end joint debugging, typed API client, Interface error handling, SSE, WebSocket.

日本語の概要は準備中です。原文の説明を表示しています。

bovinphang/frontend-craft222026年9月26日 更新

用于设计、实现或审查前后端 API 集成、类型化 API client、REST/tRPC/OpenAPI 客户端选型、认证刷新、API 错误映射、上传流程、SSE/WebSocket/轮询选择、CORS 相关前端行为或跨边界 loading/error 状态。不要用于纯后端服务架构或仅 TanStack Query 缓存策略;中文触发词包括 API 集成、前后端联调、typed API client、接口错误处理、SSE、WebSocket。

日本語の概要は準備中です。原文の説明を表示しています。

bovinphang/frontend-craft222026年9月26日 更新

Use when frontend work needs to communicate data, action, state, permission, validation, or business-rule needs to backend teams without dictating endpoint design, field names, database shape, or implementation details; Chinese triggers include front-end and back-end requirements handover, back-end requirements, API requirements clarification, data requirements description.

日本語の概要は準備中です。原文の説明を表示しています。

bovinphang/frontend-craft222026年9月26日 更新

bovinphang のスキルをすべて見る

このスキルの問題を報告する