跳到正文
cccskills
免费在 GitHub 公开

map-flows

Use when asked to map or analyze flows, pipelines, processes, or sequences of events in this repo — e.g. "mapa el flujo", "flow", "pipeline", "ciclo de vida", "trace the request", "how does the build/release flow work", "diagrama del flujo". Maps data flows, request lifecycles, CI/CD pipelines, and state transitions with verified file:line evidence. Distinct from analyze-code (which maps code structure); this skill maps movement over time.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Flow Mapper

You trace and diagram how things move through a system: data, requests, processes, CI/CD pipelines, and state. Every step in the flow is grounded in a real file or command — a flow map is only as good as its evidence.

Steps

  1. Identify the flow — is it data flow, a request lifecycle, a CI/CD pipeline, a state machine, or a build/release process? Ask if ambiguous, otherwise infer from the request and proceed.

  2. Find the entrypoint(s) mechanically — for a request/data flow: the listener, handler, or function that receives input. For a pipeline: the trigger (GitHub Actions: on: in .github/workflows/*.yml; web: the page that boots the JS; Go: main()). Read the entrypoint fully.

  3. Trace step by step — follow each hop from source to sink:

    • What invokes the next step (function call, event, HTTP request, message, workflow step, cron)?
    • What data is passed, transformed, or dropped at each hop?
    • Where does it branch, retry, or fail?
    • Where does it end (response, file, DB, deployment, terminal state)? For each hop record file:line evidence.
  4. Check the flows you cannot trace by reading — commands that prove behavior: run the pipeline dry (shellcheck, go vet, build), grep for the entrypoint callers, trace where a symbol/step is referenced. Note anything you had to infer rather than verify.

  5. Include failure paths — every flow has error paths; map what happens on each failure (retry, abort, fallback, silent). A flow map without failure paths is a fairy tale.

  6. Diagram and report — produce a step-by-step map. Use a text sequence (and offer Mermaid on request). Keep it precise, not decorative.

Output format

  1. Flow type and scope — what was mapped and from where to where.
  2. The map — numbered steps, each with: action, responsible component/file (file:line), data in -> data out, and trigger.
  3. Branches and failure paths — every conditional/error path with its outcome.
  4. Hot spots — steps that are fragile, slow, or risky (blocking I/O, fixed ports, no timeout, no retry, || exit 1 chains).
  5. Verified — commands run and results; anything inferred marked as such.
  6. Improvements (only if requested or glaring) — concrete, ordered.

Rules: evidence at every hop; distinguish verified from inferred; map the real flow, not the intended one.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when asked to analyze a file, a directory, or the whole codebase to understand structure, architecture, dependencies, complexity, duplication, dead code, or technical debt — e.g. "analyze this", "análisis total", "explain this codebase", "mapa del código", "how does X work", "technical debt". Produces a complete, structured picture with verified commands, not guesses. Distinct from review-* skills (which judge quality); this skill explains and maps.

中文简介正在准备中。当前显示原文说明。

sazardev/networking-with-go592026年8月8日 更新

Use when asked to audit or harden security in this repo — e.g. "security audit", "auditoría de seguridad", "revisa la seguridad", "is this secure", "hardening", "vulnerabilities". Audits code, config, workflows, and secrets exposure. Covers injection, secrets, TLS, untrusted input, dependency risk, and CI supply-chain hygiene. Runs when the user asks about security, not just for code reviews.

中文简介正在准备中。当前显示原文说明。

sazardev/networking-with-go592026年8月8日 更新

Use when reviewing the structure, ordering, coherence, and narrative flow of the book as a whole or across chapters. Checks chapter sequencing against the ID scheme, cross-references and forward hooks between chapters, README/index link integrity, exercise-to-chapter pairing, duplicate or contradictory content, and progression of difficulty. Best paired with a full-docs review rather than a single-chapter proofread.

中文简介正在准备中。当前显示原文说明。

sazardev/networking-with-go592026年8月8日 更新

Use when writing, expanding, rewriting, or drafting any chapter (.mdx) or Go exercise for this book. Encodes the authorial voice, the mdx-pdf-format rules, the ID/naming scheme, the zero-emoji rule, chapter/exercise pairing, and the "theory first, then code" pedagogy so new or edited content reads like the rest of the book and keeps the PDF compiling.

中文简介正在准备中。当前显示原文说明。

sazardev/networking-with-go592026年8月8日 更新

Use when brainstorming, evaluating ideas, designing architectures, writing technical plans, or choosing between approaches — e.g. "give me ideas", "ideas para", "diseña la arquitectura", "how should I structure this", "compare approaches", "plan". Turns vague ideas into concrete, prioritized, buildable designs with explicit tradeoffs. Use before writing code, not after.

中文简介正在准备中。当前显示原文说明。

sazardev/networking-with-go592026年8月8日 更新

Use when proofreading, copy-editing, or verifying English in any docs/**/*.mdx chapter or code comment in this repo. Catches grammar, punctuation, spelling, syntax, article/tense/agreement errors, wordiness, tone drift, and style inconsistencies, and rewrites text in the book's confident second-person voice without changing meaning or breaking the mdx/PDF format rules.

中文简介正在准备中。当前显示原文说明。

sazardev/networking-with-go592026年8月8日 更新

查看 sazardev 的全部技能

报告此技能的问题