memory-usage
Use when you need to query SiftCoder's persistent project memory across sessions. Provides MCP tools mem_search, mem_get, mem_timeline, mem_why, mem_drain. Triggers when the user asks "what did we decide about X", "why is X this way", "find prior discussion of X", "show me the history of Y".
What this skill does
# Using SiftCoder Memory
SiftCoder runs a per-workspace memory daemon that captures tool observations, summarises them with a local or remote LLM, and exposes a queryable store with provenance.
## Available MCP tools
- `mem_search(query, k=10)` — hybrid BM25+vector retrieval, RRF fused, Ebbinghaus-decayed. Returns top-k summaries with timestamps and provenance hints.
- `mem_get(id)` — fetch full summary by id.
- `mem_timeline(id, before=5, after=5)` — chronological neighbours.
- `mem_why(id)` — BFS the provenance graph from a node and return the cause chain (`causes`, `derives_from`, `calls`, `imports`, `contradicts`, …).
- `mem_drain(batch=16)` — force a small drain pass (rarely needed; consolidator runs automatically).
## When to use which tool
| Intent | Tool |
|---|---|
| "Has this been discussed before?" | `mem_search` |
| "Show me that decision in full" | `mem_get` (after search) |
| "What happened around the time of X?" | `mem_timeline` |
| "Why did we end up with this code?" | `mem_why` |
| "I just made big changes, capture them now" | `mem_drain` |
## Patterns
**Always search before assuming.** If the user references prior work, run `mem_search` first. A hit is cheaper and more accurate than re-deriving from current files.
**Verify before acting on memory.** Memory is a snapshot of what was true when written. If it names a file/symbol/flag, grep or read first to confirm it still exists.
**Prefer `mem_why` over `git log` for non-obvious code.** `git log` shows the commit; `mem_why` shows the conversation that led to it.
**`mem_symbol_search` is recall, not live precision.** It finds symbols you have touched (regex-extracted, with provenance) — great for "where have I been." For live go-to-definition / find-all-references across a multi-language codebase, prefer Claude Code's code-intelligence (LSP) plugin. See `docs/foundations/large-codebases.md`.
**Don't dump raw mem_search results to the user.** Pick the 1–3 relevant ones, paraphrase, cite ids.
## Anti-patterns
- Do not use memory as the source of truth for ephemeral session state (tasks, todos, in-progress work). Use TodoWrite/TaskCreate for those.
- Do not write to memory directly — capture flows through hooks. If you want something pinned, surface it to the user and let them confirm.
## Quick examples
```
mem_search({ query: "auth middleware decision", k: 5 })
mem_get({ id: "summary:142" })
mem_why({ id: "summary:142" })
mem_timeline({ id: "summary:142", before: 3, after: 3 })
```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.