stage-flow-status

Reports read-only status of manuscript sections, claims, evidence, and build with one next action.

2|Updated Aug 3, 2026
One-click install
npx skills add https://github.com/wanghao9610/STAGE --skill stage-flow-status-wanghao9610
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stage-flow-status
Source: https://github.com/wanghao9610/STAGE/tree/main/.qwen/skills/stage-flow-status
Command: npx skills add https://github.com/wanghao9610/STAGE --skill stage-flow-status-wanghao9610

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Academic writing projects spread progress across outlines, claim ledgers, evidence manifests, review cycles, and build outputs, making it hard to know where the paper stands or what to do next. This Skill reads all of those artifacts in one pass and produces a single honest status report with exactly one recommended next action. ## Core Features & Use Cases - Whole-flow status board: Tallies per-section, per-figure, and per-table states from the outline, claim coverage by ledger status, evidence freshness against upstream stamps, reference counts, and review-cycle state. - Deterministic signals: Runs read-only script modes (import.sh --diff for evidence drift, lint.sh --no-build for the build gate) and reports missing data as "unknown" rather than guessing. - One prioritized next action: Applies a fixed priority order (story, outline, evidence, drafting, audits, review, packaging) to name exactly one follow-up command, with red lint gates outranking everything. - Use Case: After a week of drafting, run the status check to see that two sections are still skeletons, three claims are unsourced, and the evidence has drifted — and receive the single command to run next. ## Quick Start Ask the assistant to run /stage-flow-status to show where the paper currently stands and what to work on next.

Frequently Asked Questions about stage-flow-status

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check the status of my paper writing workflow?

Run /stage-flow-status with no arguments to get a full report covering cycle state, outline board, claim coverage, evidence freshness, and build status. Pass a section number, slug, or title to narrow the outline and claim detail to one section.

How does the skill decide what to work on next?

It applies a fixed priority order: adoption, story, outline, evidence drift, open promises, unfinished rows, unsourced claims, stale audits, missing review, then packaging. A failing lint gate outranks the entire list and routes to the owner lint names.

Does stage-flow-status modify any files in the repository?

No, it is strictly read-only. It never creates, edits, or deletes files and never commits; its two script invocations (import.sh --diff and lint.sh --no-build) also run in read-only modes.

What happens when evidence or build data is missing?

Missing fields are reported as "unknown" rather than guessed. With no evidence source configured, import.sh reports it has nothing to check; with no finished build, the report states the paper has not been built instead of failing lint.

Can I scope the status report to a single manuscript section?

Yes, pass a section argument resolved by number, file slug, or title against notes/outline.md. The scan itself stays project-wide, and scoping is applied to the outline board and claim detail in the report.