search-documents | paperless | ClaudePluginHub

Skill

search-documents

Search documents in Paperless-ngx. Use when the user wants to find documents, says "search paperless", "find documents about X", "show similar to doc ID N", or asks for document autocomplete suggestions.

Install

$

npx claudepluginhub cameri/claude-skills --plugin paperless

Tool Access

This skill is limited to using the following tools:

ReadWriteBash(http *)Bash(python3 *)

Preview

<objective>

SKILL.md

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

139.0k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

bmad-help

Analyzes BMad project state from catalog CSV, configs, artifacts, and query to recommend next skills or answer questions. Useful for help requests, 'what next', or starting BMad.

bmad-pro-skills

43.8k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitMar 24, 2026

Actions

View Source View Plugin View on GitHub View README

<objective> Searches Paperless-ngx documents using full-text search, similarity matching, or autocomplete. Dispatches to the appropriate API endpoint based on argument format and displays results using shared formatting references. </objective>

<quick_start>

/paperless:search-documents <query text>
/paperless:search-documents more_like=<document id>
/paperless:search-documents autocomplete=<partial term>

</quick_start>

<setup> Read `<base_dir>/../../references/auth.md` for credential loading. Read `<base_dir>/../../references/id-cache.md` for metadata cache instructions. </setup> <workflow> Parse `$ARGUMENTS` for mode:

Full-text search — query=<text> or bare text:

http --ignore-stdin -b \
  GET "${PAPERLESS_URL%/}/api/documents/" \
  "Authorization:Token $TOKEN" \
  "Accept:application/json; version=6" \
  query=="$QUERY"

Display results per <base_dir>/../../references/search-results.md.

Similarity search — more_like=<id>:

http --ignore-stdin -b \
  GET "${PAPERLESS_URL%/}/api/documents/" \
  "Authorization:Token $TOKEN" \
  "Accept:application/json; version=6" \
  more_like=="$ID"

Display results per <base_dir>/../../references/search-results.md, sorted by rank.

Autocomplete — autocomplete=<term> or complete=<term>:

http --ignore-stdin -b \
  GET "${PAPERLESS_URL%/}/api/search/autocomplete/" \
  "Authorization:Token $TOKEN" \
  term=="$TERM" \
  limit==10

Display returned suggestions as a plain list.

No arguments — show usage hint:

Usage:
  /paperless:search-documents <query text>
  /paperless:search-documents query=<text>
  /paperless:search-documents more_like=<document id>
  /paperless:search-documents autocomplete=<partial term>

</workflow> <notes> - `query==` and `more_like==` use httpie's double-`==` syntax for URL query params. - `search_hit` may be absent for non-search responses; handle gracefully. </notes>

<success_criteria>

Correct API endpoint called based on argument mode
Results displayed using format from search-results.md
Autocomplete returns a plain list of suggestions
Missing arguments show the usage hint </success_criteria>