메뉴
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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| 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 (seeSKILLS.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.
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.
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.
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.
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.
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.
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.