From cman
Searches and summarizes past Claude Code sessions, plans, and memory across all projects. Handles recaps by time period, keyword searches, and provides resume commands. (Deprecated: use /remember)
npx claudepluginhub laiso/cman --plugin cmanThis skill is limited to using the following tools:
> **Deprecation:** Prefer **`/remember`** ([remember skill](../remember/SKILL.md)). The **`cm-search`** skill name will be removed in a future release.
Searches past Claude Code work across all projects via /remember [keywords] or queries about sessions, recaps, and prior outputs.
Searches Claude Code conversation history in Scribe DB (SQLite FTS5) or JSONL files to recall past discussions, decisions, code snippets, and context from prior sessions.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Share bugs, ideas, or general feedback.
Deprecation: Prefer
/remember(remember skill). Thecm-searchskill name will be removed in a future release.
Search and summarize past Claude Code sessions, plans, and memory across all projects. The remember skill delegates here for the full instructions.
If $ARGUMENTS is non-empty (e.g. /remember FOO BAR), join the tokens into the search keyword and follow the Search flow. Do not ask the user to repeat the query.
First, gather data by calling these tools in parallel:
mcp__plugin_cman_cman__list_sessions with limit=200mcp__plugin_cman_cman__list_plansmcp__plugin_cman_cman__list_memoryThen use the results to generate output. This skill searches across ALL projects by default. Determine what the user needs from context:
/remember)$ARGUMENTS when providedmcp__plugin_cman_cman__search_sessions with the keyword
include_memory=true when the user may have stored relevant notesexclude_subagents=true to skip sub-agent noise (default for targeted searches)search_sessions calls with alternate forms (e.g. English and Japanese: Scan / スキャン, or DynamoDB / dynamo) and merge the resultsAlways include claude --resume <id> for sessions the user might want to continue.
Rephrase raw prompts into brief work descriptions (e.g., "@README.md" → "README editing").