ワンクリックでManusで任意のスキルを実行

sync-adapters

スター90

フォーク39

更新日2026年7月15日 22:56

Regenerate the per-vendor skill adapters from the committed agent-skills/ layer. Run after authoring or editing a skill, or after a clone or pull, so Claude, Gemini, Cursor, Kiro, GitHub Copilot, and Google Antigravity each get a current native adapter.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

Accenture

Accenture/mercury

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

関連職種SOC

SOC 職業分類に基づく

ソフトウェア開発者コンピュータ・数学職·SOC 15-1252

ファイルエクスプローラー

4 ファイル

SKILL.md

readonly

name	sync-adapters
description	Regenerate the per-vendor skill adapters from the committed agent-skills/ layer. Run after authoring or editing a skill, or after a clone or pull, so Claude, Gemini, Cursor, Kiro, GitHub Copilot, and Google Antigravity each get a current native adapter.
provenance	agent-memory-builtin

⚠️ Tool-managed skill provided by agent-memory (provenance: agent-memory-builtin). Don't edit it in place — fork under a new name, or upstream a fix to the agent-memory project (see SKILLS.md).

This skill is the sync skill adapters operation. It is a runnable script — do not hunt for an npm command, MCP tool, or hand-write the adapter files. Run one of these from the repo root (output is byte-identical across all three; bash needs no runtime install — prefer it, especially in a non-Node project):

bash agent-skills/sync-adapters/scripts/sync-adapters.sh
# no bash? (e.g. native Windows) — use whichever runtime you have:
node agent-skills/sync-adapters/scripts/sync-adapters.mjs
python3 agent-skills/sync-adapters/scripts/sync-adapters.py

For each agent-skills/<name>/SKILL.md it (re)writes all six vendor adapters — .claude/skills/<name>/SKILL.md, .gemini/commands/<name>.toml, .cursor/rules/<name>.mdc, .kiro/skills/<name>/SKILL.md, .github/skills/<name>/SKILL.md, .agents/skills/<name>/SKILL.md — and prunes orphaned adapters it previously generated (identified by their pointer signature; never touches hand-authored vendor files). The .agents/skills/ adapter is the Agent Skills standard dir read by Google Antigravity (agy, the Gemini CLI successor) — Antigravity ignores .gemini/commands, so this is what makes /<name> work there.

It is idempotent and writes only the gitignored adapter dirs — never agent-skills/, never a committed file. Pass --dry-run to preview. The neutral agent-skills/<name>/SKILL.md is always the source of truth; the adapters are thin regenerated pointers (do not commit them).

After syncing, reload your runtime if it loads adapters at startup (e.g. GitHub Copilot CLI: /restart or a skills rescan) for a new /<name> to become available this session.

このリポジトリの他の Skills

同じリポジトリ

apply-critique

Accenture/mercury

Apply a fresh-context reviewer's critique to the current work through a bounded, validated, human-gated loop. Use after a second-opinion review returns a critique — parse it, plan a few scoped fixes, run the build/tests and memory-lint, then summarize what was applied versus rejected and why.

2026-07-1590

archive-fact

Accenture/mercury

Safely move a decayed fact or completed thread from continuity.md into the archive — the mechanical half of a memory review, done deterministically. Use during the REVIEW.md ritual (step 4) or whenever a specific fact must be archived, instead of hand-editing continuity.md (which has truncated the file twice). The agent decides what to archive; this performs the move safely.

2026-07-1590

harvest-knowledge

Accenture/mercury

Re-scan the repo's human-authored documentation (docs trees, ADRs, decision logs, design specs, roadmaps, kanban) and fold newly-durable facts into the shared memory/ layer — additively, on demand. Use when docs have grown or changed since enable, or to backfill a repo enabled before the curious harvest existed. Distills into neutral memory; never overwrites curated facts.

2026-07-1590

memory-lint

Accenture/mercury

Deterministic integrity check for the agent-memory layer. Use after a memory review, before committing memory/ changes, or in CI to catch decay miscounts — facts archived while still referenced, an id in both continuity and the archive, tier or supersession drift. The agent judges meaning; the script does the counting.

2026-07-1590

refresh-metadata

Accenture/mercury

Recompute continuity.md fact footers (last_used, uses, tier) from the session reference log — REVIEW.md steps 2–3, done deterministically. Use during a review, or whenever memory-lint reports [stale-metadata], instead of updating footers by hand. Pure arithmetic from the references; it never decides what to archive.

2026-07-1590

second-opinion

Accenture/mercury

Generate a fresh-context review snapshot of the current task for a clean-memory AI reviewer (any vendor or a clean session). Use at a milestone that looks complete, or when blocked, uncertain, or facing a risky change, to get an independent second opinion before proceeding; shows a security advisory before exporting any state.

2026-07-1590

name	sync-adapters
description	Regenerate the per-vendor skill adapters from the committed agent-skills/ layer. Run after authoring or editing a skill, or after a clone or pull, so Claude, Gemini, Cursor, Kiro, GitHub Copilot, and Google Antigravity each get a current native adapter.
provenance	agent-memory-builtin

⚠️ Tool-managed skill provided by agent-memory (provenance: agent-memory-builtin). Don't edit it in place — fork under a new name, or upstream a fix to the agent-memory project (see SKILLS.md).

bash agent-skills/sync-adapters/scripts/sync-adapters.sh
# no bash? (e.g. native Windows) — use whichever runtime you have:
node agent-skills/sync-adapters/scripts/sync-adapters.mjs
python3 agent-skills/sync-adapters/scripts/sync-adapters.py

After syncing, reload your runtime if it loads adapters at startup (e.g. GitHub Copilot CLI: /restart or a skills rescan) for a new /<name> to become available this session.