跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

hedgehog-planning-intake

Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining `04-prd.md` into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different decision at step 5/8. Phase 0 also defines compressed intake, the path a user's explicit "just build it" choice takes on full-stack-app, pwa-app, and authored cores: one batched round of questions in place of the shelf, writing the same archive at the same path so Phase 1, `ux-planner`, and the Re-entry pass all keep their documented source. Also use for the Re-entry pass, which mines new scope into additional intents without re-running the shelf, on any core with a module axis to add an intent to (full-stack-app, pwa-app, authored) — landing-page has none, so its own new-scope path runs through `hedgehog-landing-loop`'s Correction Protocol instead. Invoked by the `planner` age

skyf0xx · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add skyf0xx/hedgehog --skill hedgehog-planning-intake

技能说明


name: hedgehog-planning-intake description: Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different decision at step 5/8. Phase 0 also defines compressed intake, the path a user's explicit "just build it" choice takes on full-stack-app, pwa-app, and authored cores: one batched round of questions in place of the shelf, writing the same archive at the same path so Phase 1, ux-planner, and the Re-entry pass all keep their documented source. Also use for the Re-entry pass, which mines new scope into additional intents without re-running the shelf, on any core with a module axis to add an intent to (full-stack-app, pwa-app, authored) — landing-page has none, so its own new-scope path runs through hedgehog-landing-loop's Correction Protocol instead. Invoked by the planner agent, which decides the path; don't run standalone. landing-page runs this skill's Phase 0 on first run, then mines the same archive through hedgehog-landing-loop's own planning-intake section, that core's counterpart to this skill's Phase 1. An authored core runs this skill's Phase 0, then hedgehog-core-design, then this skill's Phase 1 mining against the designed layer sequence. A brownfield adoption (hedgehog-adopt) never runs this skill's shelf at all — the drivers BMAD elicits are already settled facts of a repo that already exists.

Hedgehog Planning Intake

Turns a person's description of a problem into planning material, by running the vendored BMAD-METHOD planning shelf (Phase 0, shared by every core) and mining its output. On full-stack-app and pwa-app that mining is this skill's own Phase 1, into intent records written via hedgehog intent add; on landing-page it's hedgehog-landing-loop's planning-intake section, into a subject/audience/job statement. This is the mechanics planner calls once its Phase 0 core-selection check has picked a core — the interpretive judgment (which Feature becomes which intent, Confirm & Lock either way) belongs to planner; this skill (Phase 0, and Phase 1 on full-stack-app and pwa-app) and hedgehog-landing-loop (landing-page's own mining) are the fixed procedures that judgment runs inside.

That shelf run is a first run, once per project. When new scope enters play later on a core with a module axis (full-stack-app, pwa-app, authored), planner runs the Re-entry pass at the end of this file instead: it reads the existing archive as context and elicits only what's new, adding intents to a graph that keeps everything already built. Landing-page has no module axis for this pass to add an intent to; its own new-scope path runs through hedgehog-landing-loop's Correction Protocol post-build entry instead — see that skill, not this one.

Phase 0 — BMAD elicitation (every core, first run only)

Phase 0 and Phase 1 below are the first run — a project whose build graph holds no intents yet. When the graph already holds intents, run the Re-entry pass at the end of this file instead; the shelf does not run twice on one project.

Run Phase 0 in the session already talking to the user, never as a detached subagent — every skill below can drop into Facilitator or Creative Partner mode, a live multi-turn conversation a subagent has no channel to hold (planner.md states the same constraint). Applies regardless of which core invoked this Phase — hedgehog-landing-loop runs it in full too.

Check uv is on PATH before anything else — every skill in the shelf below shells out to it (uv run {bmad-root}/scripts/*.py) for its memlog, customization resolution, and research tooling, so its absence mid-shelf strands a run partway through rather than failing at the one point where the whole shelf is still skippable. Run uv --version; if it fails (not found, or exits non-zero), stop before running any BMAD skill and tell the user plainly: uv is required by the vendored BMAD planning shelf and isn't on PATH — install it (https://docs.astral.sh/uv/getting-started/installation/) and re-run. Don't fall back to a reduced or headless shelf run on this failure; that's a silent behavior change of exactly the kind this check exists to prevent.

State the BMAD attribution, then run the vendored shelf in full sequence — on a first run there is no per-project skip logic and no reduced default set:

  1. bmad-forge-idea (vendor-skills/BMAD/core-skills/bmad-forge-idea) — pressure-test the idea through persona-driven interrogation before diverging on it; strengthens, rejects, or clarifies it, optionally writing forged-idea.md as input to the skills below.
  2. bmad-brainstorming (vendor-skills/BMAD/core-skills/bmad-brainstorming) — diverge on the idea before locking anything.
  3. bmad-product-brief (vendor-skills/BMAD/bmm-skills/plan/bmad-product-brief) — the product brief.
  4. bmad-prfaq (vendor-skills/BMAD/bmm-skills/plan/bmad-prfaq) — vets the idea press-release-style.
  5. bmad-prd (vendor-skills/BMAD/bmm-skills/plan/bmad-prd) — the PRD, including its Glossary (entities, relationships, cardinality).
  6. bmad-ux (vendor-skills/BMAD/bmm-skills/plan/bmad-ux) — the UX spec, DESIGN.md + EXPERIENCE.md.
  7. bmad-deep-recon (vendor-skills/BMAD/core-skills/bmad-deep-recon) — market/competitive/user-voice research.

Any skill may itself invoke bmad-advanced-elicitation (vendor-skills/BMAD/core-skills/bmad-advanced-elicitation) at its own pause points — that's expected, let it run.

Write each skill's output to .hedgehog/BMAD/, per the fixed layout:

.hedgehog/BMAD/
  00-manifest.md        # attribution + pinned version + date + which skills ran
  01-brainstorming.md
  02-brief.md
  03-prfaq.md
  04-prd.md
  05-ux-spec/
    DESIGN.md
    EXPERIENCE.md
  06-res
阅读完整来源 ↗