بنقرة واحدة
lcm-memory
Lossless context management — search and store persistent memory across sessions
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Lossless context management — search and store persistent memory across sessions
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Lossless context management — search and store persistent memory across sessions
Use when deciding which lcm MCP tool to call — lcm_search, lcm_grep, lcm_expand, lcm_describe, lcm_store, lcm_doctor, or lcm_stats — or when an lcm tool returns an error.
Use when the user says 'cut a release', 'release vX.Y.Z', 'publish a new version', or 'bump the version'. Covers the full release flow: version bump → PR to main → CI → merge → publish → develop sync.
This skill should be used when the user asks to "run lcm dogfood", "self-test lcm", "validate lcm build", "test lcm hooks", "check lcm mcp tools", or mentions lcm QA, regression testing, or pre-release validation. Runs a comprehensive 39-check self-test across all CLI commands, hooks, MCP tools, and resilience.
You MUST use this before any work to recall project memory, and after implementing to store decisions. Lossless-claude (lcm) provides persistent cross-session memory via CLI commands.
Run the E2E validation checklist against a real lcm installation. Tests daemon, hooks, import, compact, promote, retrieval, and resilience. Pass a flow name for a subset (import, compact, promote, curate, retrieval, hooks, doctor, cleanup), or omit for the full suite.
| name | lcm-memory |
| description | Lossless context management — search and store persistent memory across sessions |
Before responding to code tasks, check memory first. Code task? →
lcm searchFIRST. Completed work? →lcm storeBEFORE done.
You have access to a persistent memory system that survives across conversations.
Code task received → lcm search FIRST → Work → lcm store → Done
Non-code task → Just respond normally
Retrieve relevant context before starting work.
lcm search "How is authentication implemented?"
Regex pattern search for precise matches.
lcm grep "createDaemon|startMcpServer" --mode regex
Inspect a specific node returned by search or grep.
lcm describe sum_abc123def456
Recover lower-level detail from a summary node.
lcm expand sum_abc123def456 --depth 2
Persist important knowledge after completing work.
lcm store "Auth middleware uses JWT with 24h expiry. See src/middleware/auth.ts"
Show token savings and compression ratios.
lcm stats
| Task Type | Search? | Store? |
|---|---|---|
| Add/create/implement feature | MUST | MUST |
| Fix/debug/resolve bug | MUST | MUST |
| Refactor/optimize/move code | MUST | MUST |
| Write/add tests | MUST | MUST |
| "How does X work?" (codebase) | MUST | Only if insights |
| General concept question | NO | NO |
| Meta task (run tests, build) | NO | NO |
| Git task (commit, PR, push) | NO | NO |
lcm is not found: run npm install -g @lossless-claude/lcmlcm daemon start --detachlcm doctor