Agent skill · Workflow & Productivity

bcc-throughline

BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.

cao bo 13★ · 1 repos on radarProfile →
claude-codecursorcodexMIT
Install
npx skills add bo-cao/breaking-coding-chaos --skill bcc-throughline --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 4
SKILL.md size: 9 KB
Bundled scripts: none
Path: skills/bcc-throughline/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 13
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# bcc-throughline **Job:** keep a durable **endeavor map** so the human can see progress and re-order work — goal, phases, hardpoints, what changed. **Files (project root only):** `plans.md` · `progress.md` · `findings.md` Templates: [templates/](./templates/). Coding checklists live in root `PLAN.md` (other skills) — not here. **Internal only:** disk = durable context; chat = RAM. Session file: [SESSION.md](../bcc-breaking-coding-chaos/references/SESSION.md). Writeback rules: [WRITEBACK.md](../bcc-breaking-coding-chaos/references/WRITEBACK.md). Do **not** narrate these metaphors or protocol names to the user unless they ask how BCC works. --- ## User voice (required — comfort first) Talk like a sharp collaborator mapping the project — **not** like a workflow product or a gatekeeper. | Do | Don't | |----|--------| | Lead with **their goal / map / options** | Lead with “先恢复上下文 / 对齐账本 / BCC 流程” | | Short: goal → map (or delta) → 1–2 next choices | Dump file-role tables, 5-question grids, skill lecture | | Suggest **only** map-level things (order, balance, drop/merge hardpoints) | Remind “还没写代码 / Throughline 不写产品代码 / 不进 plan-spar” unprompted | | On cold start: act like **starting** |

What's inside
Steps it walks through
  1. User voice (required — comfort first)
  2. Branch: cold start vs resume
  3. Cold start flow
  4. Resume / “where are we” flow
  5. Endeavor wrap-up (strict — rare)
  6. Gate A — Map fully complete (required)
  7. Gate B — Offer at most once (required)
  8. When to evaluate the gates
  9. Ask (only if Gate A + Gate B pass)
  10. If user wants global verification
  11. If user skips
  12. Explicit user ask later
  13. What you may suggest
  14. Agent ops (silent)
Ships with 3 files
  • templates/findings.md
  • templates/plans.md
  • templates/progress.md
More from breaking-coding-chaos
All skills →
About this skill
What does the bcc-throughline skill do?

BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.

How do I install it?

Run `npx skills add bo-cao/breaking-coding-chaos --skill bcc-throughline --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From bo-cao/breaking-coding-chaos, a repository with 13 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going