$npx -y skills add bo-cao/breaking-coding-chaos --skill bcc-breaking-coding-chaosBCC main skill: dual-loop coding workflow (throughline → plan-spar → clean-cut) or quick status+next. Slash: /bcc-breaking-coding-chaos · chat: bcc:breaking-coding-chaos · "run BCC" · "BCC status" · "what next BCC". Needs a real idea (1:1 implement). Args: goal text, or status. M
| 1 | # bcc-breaking-coding-chaos |
| 2 | |
| 3 | **One main skill + three sub-skills.** This file is the only “big” entry; the three children own deep rules. |
| 4 | |
| 5 | | Sub-skill | Role | |
| 6 | |-----------|------| |
| 7 | | [bcc-throughline](../bcc-throughline/SKILL.md) | Global map: `plans.md` / `progress.md` / `findings.md` only | |
| 8 | | [bcc-plan-spar](../bcc-plan-spar/SKILL.md) | After throughline: single `PLAN.md` align + review | |
| 9 | | [bcc-clean-cut](../bcc-clean-cut/SKILL.md) | After human APPROVE: minimal code + verify + writeback | |
| 10 | |
| 11 | Internal notes (not separate slash skills): [references/SESSION.md](./references/SESSION.md), [references/WRITEBACK.md](./references/WRITEBACK.md). |
| 12 | |
| 13 | **Prerequisite:** a **reasonably concrete idea**. BCC is **1:1 implement + control**, not ideation from zero. |
| 14 | |
| 15 | --- |
| 16 | |
| 17 | ## Shared voice (Mode A and Mode B) |
| 18 | |
| 19 | Talk like a sharp collaborator on **their work** — not a workflow product or ceremony host. |
| 20 | |
| 21 | | Do | Don't | |
| 22 | |----|--------| |
| 23 | | Lead with goal / map / next choice | “先对齐上下文 / BCC 双环说明 / 恢复账本” on cold start | |
| 24 | | Short human gates (confirm hardpoint, APPROVE implement) | Unprompted “还没写代码 / throughline 不写产品代码” lectures | |
| 25 | | Load each child skill and follow **its** voice rules | Dump file-role tables, 5-question grids, skill architecture | |
| 26 | | Keep process quiet; enforce order silently | Sell the next skill every turn | |
| 27 | |
| 28 | Mode A only **chains** the same comfortable steps Mode B uses one-by-one — same tone, same gates, less user typing. |
| 29 | |
| 30 | --- |
| 31 | |
| 32 | ## Two modes (this skill) |
| 33 | |
| 34 | ### Mode A — full chain |
| 35 | |
| 36 | When user says run BCC / full flow / implement this idea end-to-end: |
| 37 | |
| 38 | ```text |
| 39 | 1. bcc-throughline (create/update map — required first; cold start = start the map, not “resume”) |
| 40 | 2. confirm next hardpoint with user (one short question + recommended default) |
| 41 | 3. bcc-plan-spar (grill until clear enough; review budget = rounds if user set it, else plan-spar default) |
| 42 | 4. human APPROVE → write .bcc/session.json (see references/SESSION.md) |
| 43 | 5. bcc-clean-cut (code + verify + mandatory writeback) |
| 44 | 6. if any hardpoint still open → brief status + next hardpoint or stop |
| 45 | if ALL throughline hardpoints complete AND wrap-up not yet offered/closed |
| 46 | → one-shot endeavor wrap-up per bcc-throughline (Gate A+B); else do not re-ask |
| 47 | ``` |
| 48 | |
| 49 | **Thin orchestration only** — open each child’s SKILL.md and follow it (throughline user-voice, plan-spar clear-enough + `rounds`, clean-cut ladder). Do not re-copy grill/review/ladder text here. |
| 50 | |
| 51 | **Args to forward:** if the user passed `rounds=N` / `review=…` on the main skill, pass them into **bcc-plan-spar** for that slice. Grill still has **no** default Q&A quota. |
| 52 | |
| 53 | ### Mode B — user drives |
| 54 | |
| 55 | User calls sub-skills directly. This main skill is optional. Same voice rules as above. |
| 56 | |
| 57 | ### Quick status (built-in — not a separate skill) |
| 58 | |
| 59 | When user only wants “where are we / what next” (or args `status`): |
| 60 | |
| 61 | 1. Read `plans.md`, `progress.md`, `findings.md`, `PLAN.md`, `.bcc/session.json` if present. |
| 62 | 2. Prefer a **short natural** answer (goal · now · next · one why). Optional machine block if useful: |
| 63 | |
| 64 | ```text |
| 65 | BCC status |
| 66 | goal: ... |
| 67 | phase: ... |
| 68 | slice: ... |
| 69 | PLAN: missing|draft|locked|complete |
| 70 | session: ... |
| 71 | next: /bcc-throughline | /bcc-plan-spar | /bcc-clean-cut | ask-user |
| 72 | why: <one sentence> |
| 73 | ``` |
| 74 | |
| 75 | 3. **Stop** — no grill, no code. If they say “do that next”, load that sub-skill. |
| 76 | |
| 77 | | Condition | `next` | |
| 78 | |-----------|--------| |
| 79 | | No `plans.md` / empty goal | `/bcc-throughline` | |
| 80 | | Need align / lock PLAN | `/bcc-plan-spar` (only if throughline OK) | |
| 81 | | PLAN approved for code (session or chat) | `/bcc-clean-cut` | |
| 82 | | All hardpoints `complete` **and** no wrap-up offered/closed yet | one-shot wrap-up (`bcc-throughline` Gate A+B) | |
| 83 | | Wrap-up already offered/closed | do not re-offer (unless user explicitly asks) | |
| 84 | | Unclear | `ask-user` + recommended default | |
| 85 | |
| 86 | --- |
| 87 | |
| 88 | ## Hard workflow rules (remind only) |
| 89 | |
| 90 | 1. **throughline before plan-spar** |
| 91 | 2. **One `PLAN.md`**, updated in place by plan-spar; global progress only in the three throughline files |
| 92 | 3. **Human APPROVE** before clean-cut (session file optional help); **cut freezes PLAN design** (progress 约减 only) |
| 93 | 4. **Writeback** after clean-cut success is mandatory ([WRITEBACK.md](./references/WRITEBACK.md)) |
| 94 | 5. Infer next step from docs + chat; **suggest** to user — no heavy formal state machine |
| 95 | 6. Plan-spar: grill until **clear enough** (no default Q&A rounds); **`rounds`** budgets auto-review only |
| 96 | 7. |