一键在 Manus 中运行任何 Skill

recursive-spine-migrate

星标1

分支0

更新时间2026年7月7日 01:49

Use when converting a repo's existing prose work-ledgers (status files, queue tables, gap/debt registers, follow-up files, deferral tails) into GitHub issues and milestones under the recursive-spine convention. Dry-run by default — inventories and proposes, writes nothing. Live mode files issues with back-links and produces a retirement checklist; never deletes history, never migrates closed work.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

slopstopper

slopstopper/recursive-spine

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

recursive-spine: migrate

Default mode is DRY-RUN. Live mode only when the user explicitly says so, and only after they have reviewed a dry-run report.

Dry-run mode

Inventory. Find every prose artifact holding live work state: status files, playbook queue tables, gap/debt registers, follow-up files, "outstanding" sections, TODO tails in docs. Ask the user to confirm the list and name anything missed. Read each one fully.
Classify every row as one of: open work item / open gap / open debt / open deferral / closed-or-shipped (NOT migrated — git and archives remain the record for the past) / not-work-state (method text that stays).
Propose the mapping as a table: source (file + section) → proposed issue title, labels, milestone (existing or proposed-new with its narrative description), and the back-link line that will go in the issue body. Sliced in-flight work maps to a milestone with slice issues.
Honest denominator. End the report with: files read in full, files skipped (and why), rows classified vs. rows total per file. Never imply a complete sweep you didn't do.
Write the report to a file the user names (default migrate-dry-run.md in the repo's plan/docs area) and STOP. Writes to GitHub in dry-run mode are a violation of this skill.

Live mode

Preconditions: dry-run report reviewed by the user; repo already stamped by recursive-spine-bootstrap (labels exist).

File each approved mapping row via gh issue create / gh api for milestones. Every issue body starts with Migrated from: <file>#<section> (<commit-ish>). Nothing is filed without a back-link.
Every dry-run row must land as: filed issue (record the number in the mapping table) OR an explicit won't-file decision with a one-line reason. No silent drops — the completed table goes in the migration PR description.
Produce a retirement checklist for the prose artifacts (archive location, terminal-header text pointing at the replacement queries, deletion step) — but DO NOT execute retirement; that belongs to the repo's own cutover plan with its owner checkpoint.
Never delete or rewrite source documents. Never file issues for closed/shipped rows. Never touch runtime code.

同仓库更多 Skills

同仓库

recursive-spine-scaffold

slopstopper/recursive-spine

Use when a repo has (or is getting) the tracking stamp and needs the rest of its spine — interviews for and stamps up to six parts, each optional: a rules codex with a moments map, an ADR directory, a CI gate skeleton, a session-memory convention, a constraints file with its sha-pinned drift gate, and the loop workflow. Frames + the builder's answers + proven pollen from their hives; nothing invented ships. Offers recursive-spine-bootstrap first when tracking is missing; records every answer, including declines, in the dialect note.

2026-07-221

recursive-spine-digest

slopstopper/recursive-spine

Use when sweeping all recursive-spine-conforming repos for tracking health — aging deferrals (oldest first), stalled milestones, in-flight by lane, assigned-but-untouched issues, and debts named in closing comments but never filed, plus seedling pollen that never transplanted (hive repos). Reports honest denominators; includes the recursive-spine repo itself in every sweep.

2026-07-171

recursive-spine-handover

slopstopper/recursive-spine

Use when closing a unit of work — an issue is about to close, a PR is about to merge, or a session is ending with its work complete. Assembles the closing record as a comment on the issue: debts filed before the close (principle 4), the pollen question asked, state pointers captured, the down-tier offer made. Previews the comment before posting; degrades loudly when gh or the constraints file is missing.

2026-07-151

recursive-spine-method

slopstopper/recursive-spine

Use when a builder wants to learn or be reminded of the recursive-spine tracking convention — where work state lives (GitHub issues+milestones, never prose ledgers), the five principles, the module system, and how to design a repo's dialect. Pure knowledge; takes no actions.

2026-07-151

recursive-spine-nudge

slopstopper/recursive-spine

Use after a recursive-spine-digest sweep to select and deliver system-initiated nudges — 0–3 conversation-starters pushed to the owner about what is unblocked, aging, stalled, or newly connected. Every nudge ends in a question; the skill proposes conversations, never executes work.

2026-07-151

recursive-spine-bootstrap

slopstopper/recursive-spine

Use when installing the recursive-spine tracking convention onto a repo — interviews for modules and dialect, then stamps labels, issue/PR templates, a CLAUDE.md/AGENTS.md tracking section, and cross-project board membership. Idempotent; degrades loudly on missing gh scopes; offers (never forces) plumb-line and tokenomics wiring.

2026-07-111

name

recursive-spine-migrate

description

recursive-spine: migrate

Default mode is DRY-RUN. Live mode only when the user explicitly says so, and only after they have reviewed a dry-run report.

Dry-run mode

Inventory. Find every prose artifact holding live work state: status files, playbook queue tables, gap/debt registers, follow-up files, "outstanding" sections, TODO tails in docs. Ask the user to confirm the list and name anything missed. Read each one fully.
Classify every row as one of: open work item / open gap / open debt / open deferral / closed-or-shipped (NOT migrated — git and archives remain the record for the past) / not-work-state (method text that stays).
Propose the mapping as a table: source (file + section) → proposed issue title, labels, milestone (existing or proposed-new with its narrative description), and the back-link line that will go in the issue body. Sliced in-flight work maps to a milestone with slice issues.
Honest denominator. End the report with: files read in full, files skipped (and why), rows classified vs. rows total per file. Never imply a complete sweep you didn't do.
Write the report to a file the user names (default migrate-dry-run.md in the repo's plan/docs area) and STOP. Writes to GitHub in dry-run mode are a violation of this skill.

Live mode

Preconditions: dry-run report reviewed by the user; repo already stamped by recursive-spine-bootstrap (labels exist).

File each approved mapping row via gh issue create / gh api for milestones. Every issue body starts with Migrated from: <file>#<section> (<commit-ish>). Nothing is filed without a back-link.
Every dry-run row must land as: filed issue (record the number in the mapping table) OR an explicit won't-file decision with a one-line reason. No silent drops — the completed table goes in the migration PR description.
Produce a retirement checklist for the prose artifacts (archive location, terminal-header text pointing at the replacement queries, deletion step) — but DO NOT execute retirement; that belongs to the repo's own cutover plan with its owner checkpoint.
Never delete or rewrite source documents. Never file issues for closed/shipped rows. Never touch runtime code.