qmd
Local semantic search engine for markdown knowledge bases using qmd (tobi/qmd). Indexes markdown files with BM25 keyword search, vector embeddings for semantic search, and hybrid reranked queries. Auto-indexes on file edits via Claude Code hooks and refreshes embeddings overnight via launchd. Use when searching project docs, knowledge bases, meeting notes, or any indexed markdown collection.
What this skill does
# qmd - Local Search for Knowledge Bases Search indexed markdown collections using keyword, semantic, or hybrid search. ## When to Use - Searching project documentation or knowledge bases - Finding related files before making changes - Discovering context across many markdown files - Answering questions that span multiple documents ## Quick Start ```bash # Keyword search (fast, BM25) qmd search "your query" --json -n 10 # Find related files qmd search "topic" --files -n 20 # Semantic search (requires embeddings) qmd vsearch "conceptual question" -n 10 # Hybrid search with reranking (best quality, slower) qmd query "natural language question" --json -n 10 # Get full document content qmd get "path/to/file.md" --full ``` ## Search Modes | Mode | Command | Speed | Best For | |------|---------|-------|----------| | Keyword (BM25) | `qmd search` | Fast | Exact terms, known keywords | | Semantic | `qmd vsearch` | Medium | Conceptual queries, synonyms | | Hybrid | `qmd query` | Slow | Complex questions needing both | | File list | `qmd search --files` | Fast | Finding all related files | ## Workflows ### Before answering a question ```bash qmd search "relevant keywords" --json -n 10 ``` Review results, then read specific files for full context. ### After making changes (update cascade) ```bash qmd search "topic you changed" --files -n 20 ``` Review all related files and update any that reference the changed topic. ### Writing content that needs project context ```bash qmd search "positioning voice tone" --json -n 10 qmd search "topic for content" --json -n 10 ``` ## Index Management ```bash # Update text index (fast, ~1 sec) qmd update # Update embeddings (slow, ~3-4 min) qmd embed # Check index health qmd status # List collections qmd collection list ``` ## Setup & Troubleshooting If qmd is not installed or broken, run the doctor script: ```bash bash ~/.claude/skills/qmd/scripts/doctor.sh ``` For full installation and automation setup, see [setup/README.md](setup/README.md). For the complete command reference, see [references/commands.md](references/commands.md). ## Tips - Results below score 0.3 are noise - ignore them - `qmd search` (BM25) is good enough for day-to-day use - Only use `vsearch` when keywords don't match concepts - After changes, always run `--files` query to catch ripple effects - Combine with Read tool: qmd finds files, Read gets full content ## Self-Learning Read [LEARNED.md](LEARNED.md) before using this skill. It contains hard-won lessons about what works and what doesn't. **Update LEARNED.md when you discover:** - A query that returned bad results and what worked instead - Search mode choice that was wrong (e.g. `search` missed something `vsearch` found) - Index issues (stale embeddings, missing files, broken binary) - Installation or automation gotchas - CLAUDE.md patterns that worked or failed for enforcing context-first behavior **Consolidation (keep LEARNED.md under 50 lines):** Before adding a new entry, check the file length. If it's over 50 lines: 1. Merge duplicate/overlapping entries into single proven patterns 2. Remove entries older than 3 months that haven't been reinforced 3. Drop one-off observations that never recurred 4. Move detailed historical context to `LEARNED-archive.md` if worth preserving 5. Keep only entries that would change behavior - if it's obvious, cut it
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.