sync-seed

Étoiles0

Forks0

Mis à jour17 juillet 2026 à 14:40

Keep seed.md (the repository DNA) in sync with the actual repo state. Use when: ending a growth tick; after adding content or structure; whenever the seed's inventories may have drifted from reality. Concept-agnostic. Regenerates seed.md sections 1–7 from the live repo; never touches the Evolution Log (section 8).

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Source

bamr87

bamr87/1987

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	sync-seed
description	Keep seed.md (the repository DNA) in sync with the actual repo state. Use when: ending a growth tick; after adding content or structure; whenever the seed's inventories may have drifted from reality. Concept-agnostic. Regenerates seed.md sections 1–7 from the live repo; never touches the Evolution Log (section 8).
argument-hint	No arguments. Run after content/structure changes to refresh the DNA.

Sync Seed

seed.md is the repository's DNA and rebuild blueprint. This skill regenerates its generated sections (1–7) so they always reflect the real repo. The Evolution Log (section 8) is append-only and must never be regenerated or reordered here.

Procedure

Step 1 — Read current state

Read seed.md (preserve section 8 verbatim).
Scan .github/ (skills, prompts, agents, instructions), README.md, ROADMAP.md, and all category folders / generated artifacts.

Step 2 — Regenerate sections 1–7

Rewrite each section to match reality:

Concept Definition — keep the existing concept block unless the concept genuinely changed (changing it is a deliberate retarget, not a sync). Do not invent changes.
Identity & Mission — keep aligned with concept.subject.
Architecture — regenerate the inventory table from the actual files present in .github/ (one row per file, with its purpose). Add/remove rows as files change.
Content Inventory — current taxonomy, README table row count, and the list of dedicated topic files that exist.
Structure Inventory — which generated artifacts exist (category indices, TIMELINE.md, index.md/TOC, cross-refs) vs. not-yet-generated.
Growth Loop — keep current (only change if the loop itself changed).
Rebuild Procedure — keep current.

Step 3 — Preserve the Evolution Log

Leave section 8 exactly as-is. Appending to it is the job of the encode-seed prompt, not this skill.

Step 4 — Confirm

Report which sections changed and a one-line diff summary (e.g. "Architecture: +1 file; Content: 13→15 rows").

Notes

Idempotent: if nothing changed in the repo, sections 1–7 should come out identical (no diff).
This skill is descriptive, not creative — it mirrors what exists; it does not add content or plan work (that's add-topic / plan-roadmap).

Plus depuis ce dépôt

même dépôt

add-topic

bamr87/1987

Add one or more topics to this knowledge-base repository. Use when: adding a new item (event, person, work, discovery, etc.) within the repo concept; unsure whether a topic deserves a knowledge-table row or a full dedicated article; bulk-adding multiple topics at once; auto-discovering coverage gaps across the concept's categories. Concept-agnostic — reads subject/taxonomy from seed.md. Orchestrates research, format selection, file creation, README linking, and session logging.

2026-07-170

build-structure

bamr87/1987

Generate and refresh the structural artifacts of this knowledge base — category index pages, a timeline, a master index/TOC, and cross-reference links. Use when: new topic files were added and indices need updating; building out repository structure beyond flat content; running a structure item from the roadmap. Concept-agnostic and idempotent — derives everything from the concept and existing content; only rewrites generated regions.

2026-07-170

plan-roadmap

bamr87/1987

Decide what this knowledge base should grow next and update ROADMAP.md. Use when: starting a growth tick and need to choose the next 1–3 items; the backlog is low and needs refilling; reconciling completed work into Done. Concept-agnostic — reads the concept and current state from seed.md and the repo. Reads/writes ROADMAP.md only.

2026-07-170

publish-session

bamr87/1987

Publish the current working session for this repository. Use when: finishing a session and ready to commit and push changes; wanting to log session work to seed.md before committing; pushing new topics, articles, README updates, or instruction changes to GitHub. Concept-agnostic. Runs encode-seed → git status review → commit → push in one orchestrated flow.

2026-07-170

research

bamr87/1987

Research a topic within this repository's concept and return structured findings. Use when: looking up items (events, people, works, discoveries, etc.) within the concept; crawling authoritative sources; verifying facts and attribution; gathering facts before deciding whether to create a knowledge-table row or a dedicated file. Concept-agnostic — reads subject/scope/source_strategy from seed.md. Does NOT write files on its own — use add-topic for that.

2026-07-170

build-structure

bamr87/1987

Generate and refresh the structural artifacts of this knowledge base — category index pages, a timeline, a master index/TOC, and cross-reference links. Use when new topic files were added and indices need updating, when building repository structure beyond flat content, or when running a structure item from the roadmap. Concept-agnostic and idempotent — derives everything from the concept and existing content; only rewrites generated regions.

2026-07-160

name	sync-seed
description	Keep seed.md (the repository DNA) in sync with the actual repo state. Use when: ending a growth tick; after adding content or structure; whenever the seed's inventories may have drifted from reality. Concept-agnostic. Regenerates seed.md sections 1–7 from the live repo; never touches the Evolution Log (section 8).
argument-hint	No arguments. Run after content/structure changes to refresh the DNA.

Sync Seed

Procedure

Step 1 — Read current state

Read seed.md (preserve section 8 verbatim).
Scan .github/ (skills, prompts, agents, instructions), README.md, ROADMAP.md, and all category folders / generated artifacts.

Step 2 — Regenerate sections 1–7

Rewrite each section to match reality:

Concept Definition — keep the existing concept block unless the concept genuinely changed (changing it is a deliberate retarget, not a sync). Do not invent changes.
Identity & Mission — keep aligned with concept.subject.
Architecture — regenerate the inventory table from the actual files present in .github/ (one row per file, with its purpose). Add/remove rows as files change.
Content Inventory — current taxonomy, README table row count, and the list of dedicated topic files that exist.
Structure Inventory — which generated artifacts exist (category indices, TIMELINE.md, index.md/TOC, cross-refs) vs. not-yet-generated.
Growth Loop — keep current (only change if the loop itself changed).
Rebuild Procedure — keep current.

Step 3 — Preserve the Evolution Log

Leave section 8 exactly as-is. Appending to it is the job of the encode-seed prompt, not this skill.

Step 4 — Confirm

Report which sections changed and a one-line diff summary (e.g. "Architecture: +1 file; Content: 13→15 rows").

Notes

Idempotent: if nothing changed in the repo, sections 1–7 should come out identical (no diff).
This skill is descriptive, not creative — it mirrors what exists; it does not add content or plan work (that's add-topic / plan-roadmap).