菜单
Decomposes natural language queries into targeted searches across Readwise Reader documents, highlights, and tags. Use when the user searches their reading library, asks what they saved about a topic, or wants to find specific highlights.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Opt the current project into down-tier model delegation by installing a standalone .claude/rules/model-delegation.md rule, optionally with pre-shaped .claude/agents/ definitions (fast-executor, task-coder) and an optional agent-state feedback layer. The rule tells Claude to route well-specified data and coding tasks to a cheaper model in a subagent, keeping judgment-heavy work in the main loop. Use when the user says "set up model routing", "set up model delegation", "use cheaper models for subagents", "delegate to a lower-power model", or wants to remove or update that rule.
Pre-share scan for leaked secrets and privacy-sensitive content. Wraps simonw/scan-for-secrets for literal matching (with JSON/URL/HTML/backslash/unicode escape variants) and composes a ripgrep regex pass for shape-based leaks (other users' home paths, emails, IPv4, MAC, JWTs, API keys). Use when user says "scan for secrets", "check for leaked credentials", "pre-share scan", "redact home paths", "PII scan", "strip my username from transcripts", "scan logs before publishing", "check before sharing", "audit before commit", "find leaked API keys", "scan agent transcript".
Convert JavaScript and TypeScript projects to use bun instead of npm/yarn/pnpm. Use when user asks to "migrate from npm to bun", "convert to bun", "switch package managers", "replace npm", or "use bun instead". Includes conversion tables and lock file migration. Core conventions auto-loaded via SessionStart hook; invoke /dev-conventions:bun-tooling for full reference.
Audit project dependencies for known vulnerabilities using uv audit (Python) and bun audit (JS/TS). Use when user says "audit dependencies", "check for vulnerabilities", "security audit", "check deps", "are my packages safe", "CVE check", "dependency security", "vulnerability scan". Invoke with /dev-conventions:dep-audit.
Documentation conventions: last-updated dates, lowercase filenames, internal/ subfolder for non-shared docs, session logs, and documenting the "why". Use when creating or updating documentation, READMEs, or design docs. Invoke with /dev-conventions:doc-conventions. Triggers on "write docs", "update README", "document this", "add a design doc", "session log".
Detailed Python/uv conversion reference. Core conventions auto-loaded via SessionStart hook; invoke /dev-conventions:python-tooling for full conversion tables. Use when you need the complete uv command mapping, version pinning strategy, or lock file workflow.
| name | library-search |
| description | Decomposes natural language queries into targeted searches across Readwise Reader documents, highlights, and tags. Use when the user searches their reading library, asks what they saved about a topic, or wants to find specific highlights. |
| metadata | {"author":"Fred Bliss","version":"1.0.0","last_verified":"2026-04-02"} |
The search intelligence behind Readwise Reader queries. Transforms a natural language question into targeted searches across your reading library and produces ranked, relevant results.
Turn this:
"What articles have I saved about distributed systems that I highlighted?"
Into targeted searches:
Documents: search_library("distributed systems", limit=30)
Highlights: search_highlights("distributed systems", limit=20)
Tags: get_documents_by_tag("distributed-systems")
Then synthesize into a prioritized knowledge brief.
| Query Type | Example | Strategy |
|---|---|---|
| Topic search | "articles about X" | Broad document search + highlight search |
| Recall | "that article I saved about X" | Search titles and summaries, prioritize recent saves |
| Highlight retrieval | "my notes on X" | Prioritize highlight search, include annotations |
| Tag browse | "everything tagged X" | Tag-based document lookup |
| Status query | "what's in my inbox" | Location-filtered document list |
| Cross-reference | "X related to Y" | Multiple searches, intersect results |
From the query, extract:
For each query type, determine which tools to call and in what order:
Topic search:
search_library(query, category?, limit=30) -- broad document searchsearch_highlights(query, limit=20) -- parallel highlight searchRecall search:
search_library(query, limit=20) -- focus on titlesTag browse:
list_tags() -- find matching tag keysget_documents_by_tag(tag) -- fetch tagged documents| Factor | Weight | Description |
|---|---|---|
| Highlight count | 0.3 | Documents you highlighted are more valuable |
| Recency | 0.25 | More recently saved/updated items rank higher |
| Title/summary match | 0.25 | Direct keyword match in title or summary |
| Reading progress | 0.1 | Partially read items may be more relevant than unread |
| Tag match | 0.1 | Exact tag match boosts relevance |
For knowledge retrieval:
Highlighted + annotated documents > Highlighted documents > Read documents > Saved but unread
When initial search returns too few results: