跳到正文
cccskills
免费在 GitHub 公开

roadmap

Use when a project has to be declared above its pieces of work, from nothing or from the boards, plans and prototypes already made, when a slot has landed or the picture has changed and the roadmap must be redrawn, or when someone asks where the project stands. Produces and keeps the roadmap (iterations of deliverable slots, each slot's state derived from what exists for it) and the foundation reference (the technology decisions). Not for designing a slot (brainstorm), planning it (write-plan) or building it (execute-plan).

中文简介正在准备中。当前显示原文说明。

Ovich/swarmstorm星标 13(GitHub 13 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(3)

  • SKILL.md6.0 KB
  • references/documents.md2.3 KB
  • scripts/domains.mjs3.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Roadmap

The roadmap is the one document above the pieces of work: what is delivered in what order, what exists for each piece, what must be decided before the next one starts.

  • A slot is something the customer can use or a system that can be deployed. Nothing smaller: a screen, a service, a migration, a board are pieces of work under a slot.
  • A slot is done when the feature is delivered and working, never when its last plan finished.
  • An iteration groups the slots delivered together.
  • The first iteration of a project from scratch is usually one slot, the foundation: the smallest deployable system the features build on, reachable at the product's own domain, its first piece of work the repository itself, created at the provider the foundation names with its conventions file, before any code.
  • No big design up front. The next iteration has its slots named precisely; later iterations carry a title, the outcome and at most a rough list. A slot is split into its pieces of work, or a new piece opened for a brainstorm, when the work reaches it.

The two documents

  • YYYY-MM-DD-<project>.roadmap.md, kind roadmap, dated at declaration and kept for the life of the project.
  • foundation.reference.md, kind reference, undated, never retiring: the technology decisions, one row each; tags project and roadmap.
  • Their contents and rows: references/documents.md, read before drafting or redrawing either.
  • Both are registered and served via the aiview skill in the product's group, the one its product-level boards and prototypes share, created and titled after the product when none exists, the roadmap started when the declaration began.
  • Documents in the project's folder that are not the product's are linked apart, as not its slots.

Slots and their state

  • Every document of a slot carries the slot's slug as a tag, whatever group it sits in.
  • The state is derived from what the tag finds, never typed: empty (nothing), in design (a board, or a plan not yet approved), drawn (prototypes), planned (an approved plan), in progress (a plan's tracker has a ▶), landed (the person confirmed the feature delivered and working, with the evidence: a URL, a deployment, a customer).
  • In the tracker only in progress is ▶ and only landed is ✅; in design, drawn and planned stay ⬜ with the state written in the slot row.
  • At declaration the draft derives each state from the reading, and the tags are applied when the interview confirms which slot a document serves.
  • A board serves a slot, or the roadmap itself when the idea is product-level, and its tag says which.
  • The roadmap resolves its own decisions through the interview skill, never through a board of its own, and keeps the exchange in its interview log: the question with its options and recommendation, then the answer as given.

Declare

  1. Read everything that exists for the project: its documents in aiview, its code and conventions file, any register the person names.
  2. Name what is missing: slots no document covers (accounts and login, billing, the foundation itself are the usual absences), foundation rows no decision covers, dependencies between slots that nothing states.
  3. Draft both documents whole, a recommendation in every open place with its reason, register and serve them, tell the person the URLs, and hand them over as something to correct.
  4. Interview on the draft. The tree: the order of iterations, which slot each existing piece belongs to, the foundation rows the first slot needs. Rows a later slot needs stay open with that slot named. Every answer lands in the documents as it is given. For the name and domain rows, run scripts/domains.mjs <name>... --tld <the TLDs the product needs> on the person's suggestions before asking; each option carries its domains as available, registered or unknown, and a name whose domain is taken is never the recommended one.
  5. Close. The state node names the first slot and its next step. Say so in chat.

Redraw

Run when a slot lands, a plan finishes, a board opens for a slot, or the person says the picture changed.

  • Derive every state again. Mark landed only with the person's evidence.
  • Split the slot the work has reached into its pieces of work, each a group.
  • Ask the foundation rows the next slot needs and refuse to start it while one is open.
  • Deviate from the earlier drawing when the last slot taught something, and write what changed and why in the redraw log.
  • Retire the landed slot's groups as the aiview contract asks.

Status

Read-only, in chat: the iteration, the slot in progress, what blocks, the foundation rows still open for the slot ahead, the pieces of work the next slot still lacks.

The diagram

The roadmap opens on its tracker, drawn to the tracker protocol of the write-plan skill (its references/tracker.md, the Slots section): one subgraph per iteration, one node per slot with the glyph of its derived state, dependency edges, the state node with the iteration, the slot in progress, next, blocked and the open rows. The coarse iterations share one subgraph, "later", their order carried by the edges alone. Parse it after every edit with aiview mermaid-check.

Red flags

ThoughtReality
"The stack can be decided when the first plan is written"Then it is decided in one plan, and the second slot inherits it without seeing it. Rows close in the foundation, before the slot.

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

aiview

免费

Use whenever a document is produced for the user to read and react to while it evolves: a brainstorm board, a plan, a design language, a prototype, a PR analysis, a review report, a live PDF. Also when a document must be registered, opened, listed, moved or retired, or a prototype's bindings checked. Not for code, tests or configuration, or any file nobody opens in a browser.

中文简介正在准备中。当前显示原文说明。

Ovich/swarmstorm132026年10月29日 更新

Use when a person wants to think an idea through and keep the discussion: a feature, a tool choice, an architecture question, before a plan or without one, with the agent through an interview. Produces a board in aiview holding the decisions, the diagrams and what was investigated. Not for a swarm of seats working it (brainswarm), not for an implementation plan and not for bug fixes.

中文简介正在准备中。当前显示原文说明。

Ovich/swarmstorm132026年10月29日 更新

Use when a person wants a swarm of role seats to work a topic on the swarm board under a chosen protocol: a brainstorm (ideas before any judgment), a debate (questions argued to decisions, a skeptic endorsing) or an editorial (one text drafted, read by seats standing for its readers, revised), a protocol or template the project keeps as a `protocol-<name>` skill (or an older `brainswarm-<name>` one), or a custom protocol recommended for the person's intent, or a seat's brief names a brainswarm protocol. Produces the run's record in aiview, written by the orchestrator alone. Not for one person thinking aloud with the agent (brainstorm, interview) and not for a plan's slices (execute-plan).

中文简介正在准备中。当前显示原文说明。

Ovich/swarmstorm132026年10月29日 更新

cold-read

免费

Use when dispatched to cold-read a plan, as an agent that was not in the conversation that wrote it, to say whether it can be carried out from the document alone. Produces what the reader would build, its questions, and a verdict, ready or not ready, repeated as the writer fixes the plan. Not for judging the design (interview, pr-review), not for the mechanical checks (aiview plan check, tracker check), and not for writing the plan (write-plan).

中文简介正在准备中。当前显示原文说明。

Ovich/swarmstorm132026年10月29日 更新

Use when code is hard to follow and is to be audited or reworked: long if/else or switch chains, cascades of type checks or parse attempts, kind fields compared to strings, flag parameters, deep nesting, a function hard to read. Also for complexity guardrails, or one long conditional function pasted. Produces a ranked audit of families, one family reworked behind characterization tests, or the guardrails.

中文简介正在准备中。当前显示原文说明。

Ovich/swarmstorm132026年10月29日 更新

Use when a page is wanted to work on something with the person during development, fed the project's real data (comparing model answers, walking an agent call by call, measuring an output against its template), when such a workbench has to change, be reworked or its feed broke, or mid-session when turns went into aligning with the person on how to do a kind of work that recurs and real project data could show it. Produces the page in aiview, kind `workbench`, and the project's `workbench-<bench>` skill with its feed and operating steps. Not for designing a product screen (design-prototype) or verifying user stories (verification-skill-create).

中文简介正在准备中。当前显示原文说明。

Ovich/swarmstorm132026年10月29日 更新

查看 Ovich 的全部技能

报告此技能的问题