把本会话增量固化进 .ai_state。长任务收尾、context 将满或关键决策后触发。
Scanned 9/5/2026
Install to Claude Code
npx -y skills add WenJunDuan/Rlues --skill athena-checkpoint --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Athena Checkpoint?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wenjunduan-athena-checkpoint-10e01767)More formats (shields.io, HTML) on the badges page.
---
name: athena-checkpoint
description: 把本会话增量固化进 .ai_state。长任务收尾、context 将满或关键决策后触发。
---
# /athena-checkpoint — 会话记忆固化 (v9.9.6)
Memory contract: **Tier1 working memory** only supplies the current-turn delta; **Tier2 persistent memory** receives authoritative state; **_index.md retrieval router** keeps stage/next_action/current sprint, authoritative pointers, route_history≤10 and current-state log≤10. Detailed history belongs in `session-log.md`; hooks are fallback only.
## 痛点 (你的反馈)
每次会话要结束, 你都得手动描述一堆 "现在做到哪、下次接着干啥", 让 Athena 存进 .ai_state.
本 skill 把这个动作做成一键: **agent 自己回顾本会话、提炼增量、落进工程**, 你只需确认。
## 触发
- **手动**: 用户说 `/athena-checkpoint` / "存一下进展" / "记录到 ai_state" / "收尾"
- **建议时机** (主 agent 可主动提醒, 但不自动执行): 会话结束前 · 长任务阶段切换 · 重要决策后 · context 快满时
## 不做
- ❌ 不自动频繁 checkpoint (token 浪费; 手动或建议, 不强制)
- ❌ 不替代 compact hook (hook 是兜底保险)
- ❌ 不写 compound (那是跨 sprint 沉淀; checkpoint 是本会话状态)
- ❌ 不总结整个项目史 (只本会话增量; 项目史看 git log + sprints/)
## 详细 playbook
完整工作流、模板、schema 与联动细节见 `references/playbook.md` —— 按需 Read, 不进热路径。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.