一键在 Manus 中运行任何 Skill

server

星标0

分支0

更新时间2026年7月15日 16:31

This skill should be used when the user asks to "start the memory server", "open the memory browser", "visualize my memory", "stop the tm server", "is the memory server running", or invokes /tm:server [start|stop|status]. Manages a local read-only HTTP browser for the whole store - global and project memory, paginated lists, keyword search - at http://127.0.0.1:<port>/. Starting is confirmed with the port and store path; stop and status act on a clear ask.

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

Lucklyric

Lucklyric/turing-mem

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

tm — server (local memory browser)

A read-only single-page browser for the whole store: scopes in a sidebar (global + every project with counts), paginated note/log/archive lists, MEMORY.md one tab away, keyword search across every file, rendered markdown with clickable wikilinks. Runs on http://127.0.0.1:<port>/ — loopback only, GET only; it can never write memory, so every write gate stays where it belongs (in the skills). Any session can manage it: state lives in ${XDG_CONFIG_HOME:-$HOME/.config}/turing-mem/server.json, never inside the store.

Guard (run first, always)

Run ${CLAUDE_PLUGIN_ROOT}/scripts/tm-guard.sh "$PWD" and read its KEY=VALUE output. The server needs only a resolvable store: if TM_STATUS is NEED_INIT/NEED_ADOPT, stop and follow the repair flows in <MEMORY_DIR>/references/bootstrap.md (plugin copy at ${CLAUDE_PLUGIN_ROOT}/references/bootstrap.md if the store does not exist yet). NEED_MIGRATE/READ_ONLY do not block — the browser is read-only by construction. PROJECT_EXISTS=false does not block either; the browser shows the whole store.

Steps

Interpret $ARGUMENTS: start [port], stop, status, or empty (treat as status, then offer start if stopped).

status — run ${CLAUDE_PLUGIN_ROOT}/scripts/tm-server.sh status and report the KEY=VALUE block in one or two lines (running: URL + store; stopped: say so and offer start).
start — suggestions first, then one confirm:
1. Proposed port: the user's argument, else 8765. If tm-server.sh start later reports the port busy, suggest the next ones (8766, 8767) rather than failing dry.
2. Confirm via AskUserQuestion — "start the memory browser on http://127.0.0.1:/ for <MEMORY_DIR>?" (start / different port / cancel). Loopback-only and read-only are worth one clause in the description.
3. Run ${CLAUDE_PLUGIN_ROOT}/scripts/tm-server.sh start <port> and relay the URL. Mention the browser UI basics once: sidebar scopes, / to search, MEMORY tab.
stop — on a clear ask, run ${CLAUDE_PLUGIN_ROOT}/scripts/tm-server.sh stop and confirm it reported SERVER=STOPPED. No confirmation gate: stopping is trivially reversible and loses nothing.

The server reads the store live from disk — new checkpoints and notes appear on refresh; there is nothing to restart after memory writes.

Codex fallback

Same scripts, installed at ~/.agents/skills/scripts/; run tm-server.sh directly and confirm the start in plain text ("start on port 8765? yes/no").

同仓库更多 Skills

同仓库

checkup

Lucklyric/turing-mem

This skill should be used when the user asks to "run a memory checkup", "check up on my memory", "take care of my memory", "tidy up memory", "do whatever memory needs", "what should memory do next", or invokes /tm:checkup. Auto triage across the whole turing-mem surface - one status read, then a priority ladder picks the single best next action (repair, link, doc refresh, consolidate, checkpoint, commit reminder) and dispatches the matching verb. When the project is unresolved it searches the store for candidate folders and presents concrete choices. Every action goes through that verb's own confirm gates; nothing is decided silently.

2026-07-130

init

Lucklyric/turing-mem

This skill should be used when the user asks to "set up turing-mem", "initialize the memory store", "init tm", "repair the memory store", accepts an offer to set up after a guard reports a non-OK status, or invokes /tm:init. Creates config.json and the memory dir, adopts an existing store, scaffolds the current project folder, and walks the bootstrap repair flow. Every significant step is confirmed with the user before acting — nothing is created without explicit approval.

2026-07-130

link

Lucklyric/turing-mem

This skill should be used when the user asks to "link this folder/project to a memory project", "map this directory to project X", "pin this repo to existing memory", accepts a KEY_MISMATCH repair, or invokes /tm:link [id|path]. Forces the current directory to map to an existing turing-mem project folder by writing project_overrides in config.json — cross-host linking for no-remote projects. The mapping is always confirmed before writing.

2026-07-130

rename

Lucklyric/turing-mem

This skill should be used when the user asks to "rename the project memory folder", "change the memory folder name", "rename project X in memory", "give this project's memory a different name", or invokes /tm:rename [new-name]. Renames a project's store folder prefix — the -8hex identity suffix is always preserved, so resolution keeps working from every clone and host. Updates the global index row and any config overrides pointing at the folder. The rename is always confirmed before anything moves.

2026-07-080

status

Lucklyric/turing-mem

This skill should be used when the user asks to "check turing-mem status", "tm status", "memory status", "is my memory store healthy", "tm health", or invokes /tm:status. Read-only health report — config, store version, project resolution, note and checkpoint counts, consolidation state — with the matching repair verb for anything unhealthy.

2026-07-080

consolidate

Lucklyric/turing-mem

This skill should be used when the user asks to "consolidate memory", "merge the log checkpoints", "run consolidation", invokes /tm:consolidate, or accepts the SessionStart nudge reporting unconsolidated log checkpoints. Dispatches the tm-archivist agent to merge project log/ checkpoints into durable notes and MEMORY.md, refresh the index, and prune consolidated logs.

2026-07-070

name	server
description	This skill should be used when the user asks to "start the memory server", "open the memory browser", "visualize my memory", "stop the tm server", "is the memory server running", or invokes /tm:server [start\|stop\|status]. Manages a local read-only HTTP browser for the whole store - global and project memory, paginated lists, keyword search - at http://127.0.0.1:<port>/. Starting is confirmed with the port and store path; stop and status act on a clear ask.
argument-hint	[start [port] \| stop \| status]

tm — server (local memory browser)

Guard (run first, always)

Steps

Interpret $ARGUMENTS: start [port], stop, status, or empty (treat as status, then offer start if stopped).

status — run ${CLAUDE_PLUGIN_ROOT}/scripts/tm-server.sh status and report the KEY=VALUE block in one or two lines (running: URL + store; stopped: say so and offer start).
start — suggestions first, then one confirm:
1. Proposed port: the user's argument, else 8765. If tm-server.sh start later reports the port busy, suggest the next ones (8766, 8767) rather than failing dry.
2. Confirm via AskUserQuestion — "start the memory browser on http://127.0.0.1:/ for <MEMORY_DIR>?" (start / different port / cancel). Loopback-only and read-only are worth one clause in the description.
3. Run ${CLAUDE_PLUGIN_ROOT}/scripts/tm-server.sh start <port> and relay the URL. Mention the browser UI basics once: sidebar scopes, / to search, MEMORY tab.
stop — on a clear ask, run ${CLAUDE_PLUGIN_ROOT}/scripts/tm-server.sh stop and confirm it reported SERVER=STOPPED. No confirmation gate: stopping is trivially reversible and loses nothing.

The server reads the store live from disk — new checkpoints and notes appear on refresh; there is nothing to restart after memory writes.

Codex fallback

Same scripts, installed at ~/.agents/skills/scripts/; run tm-server.sh directly and confirm the start in plain text ("start on port 8765? yes/no").