From paper-distill
Provides QMD CLI command reference, collection handles, retrieval recipes, and index refresh guidance for querying and maintaining Markdown vaults in Paper Distill setups.
npx claudepluginhub hamondyan/paper-distillThis skill uses the workspace's default tool permissions.
QMD CLI is the primary read/index path for this vault. Business MCP tools write Markdown; QMD queries, fetches, and keeps indexes in sync. This skill gives you a fast command index and points at deeper recipes under [references/](references) when a specific scenario needs more detail.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Executes ctx7 CLI to fetch up-to-date library documentation, manage AI coding skills (install/search/generate/remove/suggest), and configure Context7 MCP. Useful for current API refs, skill handling, or agent setup.
Generates production-ready Python code for Dataverse SDK with error handling, singleton clients, retry logic, OData optimizations, logging, and type hints.
Share bugs, ideas, or general feedback.
QMD CLI is the primary read/index path for this vault. Business MCP tools write Markdown; QMD queries, fetches, and keeps indexes in sync. This skill gives you a fast command index and points at deeper recipes under references/ when a specific scenario needs more detail.
The authoritative source for syntax is qmd --help at runtime, with docs/qmd-cli.md providing the Paper Distill mapping.
| Command | Use it when |
|---|---|
qmd query <text> | Default retrieval. Hybrid search with auto expansion and reranking. |
qmd get <path>[:line] [-l N] | You already know the file or want a specific slice. |
qmd status | Check index and collection health before assuming reads are current. |
qmd update | Catch the index up to Markdown after a round of business writes. |
qmd embed -f | Force-refresh embeddings when semantic retrieval must reflect new writes immediately. |
| `qmd collection list | show |
| `qmd context list | add` |
qmd ls [collection[/subpath]] | List indexed files by collection or path prefix. |
Repo collection handles:
canon-papers → wiki/paperscanon-concepts → wiki/conceptsinsights-conversations → insights/conversationsinsights-ideas → insights/ideasraw-evidence → raw/evidenceqmd query "<topic>" without -c; then narrow with -c canon-papers or -c canon-concepts once you see where the evidence lives.qmd get wiki/papers/<slug>.md; add :line -l N for a slice.qmd update. If the user needs semantic (vector) results to reflect the new page right now, follow with qmd embed -f.qmd status, then qmd collection list / qmd collection show <name>.See references/query-recipes.md for lexical vs semantic vs filtered search, references/maintenance.md for post-write refresh decisions, and references/common-pitfalls.md for the mistakes that waste the most time.
qmd query when the user asks a question and you do not already know the file.qmd get when the search results point at one decisive page you need to quote or inspect closely.qmd status before debugging retrieval health, collection drift, or "why can't qmd see this page?" questions.qmd update after a batch of business writes; reserve qmd embed -f for moments when semantic retrieval has to be current immediately.qmd --help.This skill is a reference surface for agents that are already holding another task. It does not invoke MCP tools on its own. When another skill (paper-intake, paper-distillation, knowledge-workbench, idea-workbench) needs QMD syntax, route here instead of duplicating command details in each SKILL.md.
For command details not covered here, prefer runtime qmd --help over memory.