一键在 Manus 中运行任何 Skill

mnemos-briefing

星标3

分支1

更新时间2026年4月28日 07:18

Build per-cwd project memory briefing by combining 3 layers (Identity + cwd Sessions + 1-hop wikilink expansion), then synthesizing an evolution-aware narrative (400-600 words). Invoked by SessionStart hook (non-interactive via claude --print) with the current cwd as argument. Output goes to stdout; wrapper writes it to <vault>/.mnemos-briefings/<cwd-slug>.md.

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

mnemos-dev

mnemos-dev/mnemos

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Mnemos briefing skill v2 (3-layer)

You will be given a single argument: an absolute cwd path. Your job is to read the canonical prompt at prompt.md (sibling file in this skill folder) and execute it exactly.

Process:

Read <skill-folder>/prompt.md for the full 3-layer synthesis prompt.
Execute Step 1 (Identity) → Step 2 (Cwd) → Step 3 (Cross-context) → Step 4 (Budget) → Step 5 (Synthesize).
Write briefing markdown body to stdout. No frontmatter.

Token budget: Hard cap 15K input. Output 400-600 words (~1K tokens).

Cost: This skill uses Claude Code subscription quota (claude --print), not ANTHROPIC_API_KEY. Typical cost: 1 LLM call per session-start.

同仓库更多 Skills

同仓库

mnemos-identity-refresh

mnemos-dev/mnemos

Update <vault>/_identity/L0-identity.md by reading existing identity + new Sessions since last refresh. Synthesizes delta into updated profile, marks revised preferences explicitly, preserves identity-relevant decisions. Invoked from SessionEnd worker subprocess (non-interactive via claude --print) — no arguments needed beyond vault discovery.

2026-04-283

mnemos-recall

mnemos-dev/mnemos

Cross-context recall from the Mnemos memory palace. User invokes /mnemos-recall <query> to ask a free-text question; skill searches the palace via MCP, reads top drawers, and synthesizes a narrative answer with wikilink citations. In-session only (no subprocess). Use when cwd-based auto-briefing doesn't cover the query (e.g. working in cwd A but asking about work done in cwd B).

2026-04-273

mnemos-refine-transcripts

mnemos-dev/mnemos

Refines Claude Code JSONL transcripts (~/.claude/projects/) into high-signal Sessions/<YYYY-MM-DD>-<slug>.md notes in the Mnemos vault. Triggers: "/mnemos-refine-transcripts", "refine transcripts", "summarize JSONLs and write to Sessions", "process raw logs", "import Claude Code history to vault", "process unprocessed transcripts". Does NOT call the mnemos API, does NOT call any LLM API — work is done by Claude in this session.

2026-04-273

name	mnemos-briefing
description	Build per-cwd project memory briefing by combining 3 layers (Identity + cwd Sessions + 1-hop wikilink expansion), then synthesizing an evolution-aware narrative (400-600 words). Invoked by SessionStart hook (non-interactive via claude --print) with the current cwd as argument. Output goes to stdout; wrapper writes it to <vault>/.mnemos-briefings/<cwd-slug>.md.

Mnemos briefing skill v2 (3-layer)

You will be given a single argument: an absolute cwd path. Your job is to read the canonical prompt at prompt.md (sibling file in this skill folder) and execute it exactly.

Process:

Read <skill-folder>/prompt.md for the full 3-layer synthesis prompt.
Execute Step 1 (Identity) → Step 2 (Cwd) → Step 3 (Cross-context) → Step 4 (Budget) → Step 5 (Synthesize).
Write briefing markdown body to stdout. No frontmatter.

Token budget: Hard cap 15K input. Output 400-600 words (~1K tokens).

Cost: This skill uses Claude Code subscription quota (claude --print), not ANTHROPIC_API_KEY. Typical cost: 1 LLM call per session-start.