claude-mem

Build a queryable code-structure graph for a codebase using graphify (AST + optional semantic extraction), then file the result into the claude-mem wiki at wiki/code/. Trigger phrases - graphify this codebase, build the code graph, ingest the code, /graphify-ingest, refresh the graph.

Incrementally rebuild the code-structure graph after a feature is implemented. Detects changed files, re-extracts only those, merges into existing graph.json, preserves community labels via Jaccard matching, refreshes wiki/code/. One-shot - run after each feature, before commit. Trigger phrases - refresh the graph, update the code graph, /graphify-update, rebuild after this feature, graph update.

Autonomous plan-driven research loop. Takes a topic, decomposes it into research questions in a persisted plan artifact, dispatches research subagents per question, synthesizes findings, and files everything into the wiki as structured pages. Resumable: an interrupted session leaves the plan in the vault and the next run continues it. Based on Karpathy's autoresearch pattern plus OpenManus PlanningFlow patterns: program.md configures objectives and budgets, statuses live in the plan note. Triggers on: "/autoresearch", "autoresearch", "research [topic]", "deep dive into [topic]", "investigate [topic]", "find everything about [topic]", "research and file", "go research", "build a wiki on", "resume research".

Ingest sources into the Obsidian wiki vault. Reads a source, extracts entities and concepts, creates or updates wiki pages, cross-references, and logs the operation. Supports files, URLs, and batch mode. Triggers on: ingest, process this source, add this to the wiki, read and file this, batch ingest, ingest all of these, ingest this url.

Export the wiki's canonical BA / project deliverables to formal Office documents (.docx / .xlsx) and diagrams (PlantUML), written to .raw/exports/, by reusing the ba-suite skills. Optionally push to a tracker (ClickUp / Jira) over MCP. The wiki stays the source of truth; Office files are a generated view. For Mode ADLC and Mode C vaults. Triggers on: "/ba-export", "ba export", "export to docs", "export the BRD", "export the backlog", "generate the requirements doc", "export test cases", "export BA deliverables", "export to clickup", "export to jira", "produce office docs".

Plain-language explanation of one node in the project's graphify code graph: source file, type, community membership, and all incoming/outgoing edges with relations and confidence tags. Cheap (no LLM cost — direct graph lookup). Use for "what is X", "explain this function", "show me what touches Y" when Y is a single named symbol. Triggers on: "/graphify-explain", "explain node", "what is X (in the graph)", "describe node", "neighbors of", "what touches X", "show me X's connections" (when about code).

Find the shortest path between two named nodes in the project's graphify code graph. Returns the hop sequence with edge relations and confidence tags. Cheap (no LLM cost — NetworkX shortest path on the existing graph). Use for "how does A reach B", "trace the dependency chain from X to Y", "what connects A and B". Triggers on: "/graphify-path", "shortest path between", "how does X reach Y", "trace path from", "dependency chain from A to B", "path A to B" (when about code).

Free-form code-structural query against the project's graphify code graph. BFS (default) or DFS traversal from term-matched start nodes, returning relevant subgraph as node + edge listings with source file pointers and community tags. Cheap (no LLM cost — pure graph traversal). Use for "what's connected to X", "what touches Y", "explore the auth area", or any open-ended code-structural exploration when a graphify graph exists for the project. Triggers on: "/graphify-query", "graph query", "query the graph", "explore the graph", "what's connected to", "what touches", "what's in the X area" (when about code).

Create and edit Obsidian Bases (.base files): Obsidian's native database layer for dynamic tables, card views, list views, filters, formulas, and summaries over vault notes. Triggers on: create a base, add a base file, obsidian bases, base view, filter notes, formula, database view, dynamic table, task tracker base, reading list base.

Write correct Obsidian Flavored Markdown: wikilinks, embeds, callouts, properties, tags, highlights, math, and canvas syntax. Reference this when creating or editing any wiki page. Triggers on: write obsidian note, obsidian syntax, wikilink, callout, embed, obsidian markdown, wikilink format, callout syntax, embed syntax, obsidian formatting, how to write obsidian markdown.

Build or refresh AGENTS.md for a project. Combines mechanical extraction (build/test/lint commands, configs) via the mechanical-scanner subagent with a short structured tribal-knowledge interview. Output is AGENTS.md-spec compatible so it works across Codex, Cursor, Copilot, Aider, and Claude Code. Designed for brownfield repos where new code should match existing conventions. Trigger phrases: /project-profile, set up agents.md, build project profile, init project context, create AGENTS.md, scan project conventions, brownfield setup.

Save the current conversation, answer, or insight into the Obsidian wiki vault as a structured note. Analyzes the chat, determines the right note type, creates frontmatter, files it in the correct wiki folder, and updates index, log, and hot cache. Triggers on: "save this", "save that answer", "/save", "file this", "save to wiki", "save this session", "file this conversation", "keep this", "save this analysis", "add this to the wiki".

In-session guided help for claude-mem. Answers questions about requirements (host tools, Python, Obsidian), the workflow (which skill when, end-to-end flows), troubleshooting (common errors and fixes), and terminology (glossary of claude-mem concepts). Reference docs hold canonical content; this skill routes the user's question to the right one and synthesizes a focused chat answer. Triggers on: "/wiki-faq", "how do I get started", "I'm new", "where do I start", "first time setup", "what is claude-mem", "what's the workflow", "explain the workflow", "what are the requirements", "what do I need", "why is X broken", "graphify isn't working", "hot cache not loading", "skills not appearing", "edge drop", "labels.json mismatch", "what is hot cache", "what is .raw", "what is a vault", "explain mode B", "explain mode ADLC", "what are concerns", "what is wrap-up", "agentic mode", "what is graphify", "wiki-faq", "claude-mem faq".

Health check the Obsidian wiki vault. Finds orphan pages, dead wikilinks, stale claims, missing cross-references, frontmatter gaps, empty sections, AND graph-layer drift (label/title mismatches, stale labels.json, orphan community pages, graph staleness vs source files). Creates or updates Dataview dashboards. Generates canvas maps. Triggers on: "lint", "health check", "clean up wiki", "check the wiki", "wiki maintenance", "find orphans", "wiki audit", "lint the graph".

Answer questions using the Obsidian wiki vault and (when present) the graphify code graph. Reads hot cache first, routes code-structural questions to graphify-out/graph.json via graphify CLI, narrative questions to wiki pages. Synthesizes answers with citations. Files good answers back as wiki pages. Supports quick, standard, and deep modes, and auto-scales to large / ADLC vaults with grep-first + bounded-recursion reads (RLM-style). Triggers on: what do you know about, query:, what is, explain, summarize, find in wiki, search the wiki, based on the wiki, wiki query quick, wiki query deep, what calls X, where is X defined, how does A connect to B.

Obsidian knowledge companion for coding agents. Sets up a persistent wiki vault, scaffolds structure from a one-sentence description, and routes to specialized sub-skills. Use for setup, scaffolding, cross-project referencing, and hot cache management. Triggers on: "set up wiki", "scaffold vault", "create knowledge base", "/wiki", "wiki setup", "obsidian vault", "knowledge base", "second brain setup", "running notetaker", "persistent memory", "llm wiki".

Session wrap-up sync for ADLC (Agentic Development Life Cycle) vaults. Before ending a session, checks git changes across the vault and co-located code repos, injects updates into the relevant code wikis, reflects shipped features / resolved gaps / new requirements into the product wiki, then refreshes hot.md and appends log.md. Uses context already loaded in the session, no full re-scan. Triggers on: "wrap up the session", "end session", "wrap up", "session end", "session wrap-up", "sync before exit", "/wrap-up".

Gate 0 governance advisor that sits above the shift-left engineering workflow: it decides whether a tool or vendor is approved for a use case before any building starts. Runs use-case intake and an approval registry, vendor lifecycle governance with re-review triggers, buy-vs-build evaluation with a TCO artifact, per-use-case compliance scoping, and asset tracking with shelfware detection, then reports a portfolio status. Hands an approved intake down to shift-left Gate 1 with trace IDs. Triggers on: "should we use vendor X", "is this tool approved", "buy vs build", "we're paying for X and not using it", "compliance class for this use case", "vendor is shutting down", "vendor got acquired", "which tool should we standardize on", "why are we still paying for X", "do we still need X", "consolidate our tools", "rationalize our tool stack", "vendor viability", "shelfware", "governance status", "/product-management-layer".