get-bb/bb/prompt-library
- community
Checking that the SKILL.md file is still in the repository.
Search prompt history and manage starred reusable prompts in BB.
Install
npx vskill@latest install get-bb/bb/prompt-librarySKILL.md
Prompt library
Open + → Prompts… or press Ctrl+R in a composer. Search matches saved titles, starred prompt bodies, and recent history. Select Thread, Project, or All; the scope is remembered per composer kind on this device. The new-thread composer offers Project and All. Arrow keys select, Tab switches scope, Enter inserts, and Escape closes. Desktop shows a full Markdown preview beside the list; narrow layouts open the preview when a row is tapped, with Back and Insert.
Click the star or press Cmd/Ctrl+S to star or unstar the selected prompt. Star current draft saves the draft. Starred prompts keep text and mentions, deduplicate by text, persist across reloads, and sort by most recent use. Use Add title beside Starred and Insert in the preview footer, or click an existing title above the preview, to name or rename it. Titles are optional, trimmed, and limited to 120 characters. Save an empty title to clear it; Escape cancels an edit. Titles appear above the body preview and are never inserted into the composer. Renaming preserves the prompt ID and usage history. Starring an already-saved body keeps its existing title. History attachments are retained when restoring into an empty composer. Starred prompts omit attachments. A nonempty composer receives text and mentions at the kept cursor. Inserting never sends a message.
The server warms the history index when the plugin starts, fetching the newest 100 entries first and then older pages in the background. The picker returns saved prompts and available history immediately, including in a fresh browser. It updates while history loads and labels incomplete searches “Searching older prompts…”. Concurrent requests share one refresh; successful refreshes are reused for two seconds in the picker. Later refreshes fetch only newer prompts. On a history failure, available prompts remain usable and Retry resumes loading. Each query word, ignoring case, must match a single word of the prompt: exactly, as its start, with one typo (words of four or more letters), inside it, or as an abbreviation that starts at its first letter (tmln finds timeline). Letters are never matched across words. Results include up to 20 starred and 30 recent prompts in scope. Without a query, starred prompts come first, then recent ones. A query returns one ranked list: exact title matches first, then prompts that start with the query, then by match type in that order, then starred prompts and prompts of the composer's kind (prompts that started a thread in the new-thread composer, follow-ups in a thread composer), then by relevance (rarer words, repeated words, and shorter prompts score higher) decayed by age with a seven-day half-life; a starred prompt's age counts from its last use. A starred prompt appears once, as its starred row. History contains user prompts; core records them without agent-only input. Prompts stay searchable until the server restarts, even if their thread is deleted.
CLI and SDK
bb prompts search [query...] [--project ID | --thread ID] [--composer new-thread|follow-up] [--partial] [--json];--composerdefaults tofollow-upbb prompts list [--json]bb prompts star <text...> [--title "Title"] [--json]bb prompts title <id> <title...> [--json]orbb prompts title <id> --clear [--json]bb prompts unstar <id> [--json]
Use bb.sdk.plugins.callRpc({ pluginId: "bb--prompt-library", method, input }): search takes { query, scope: "thread" | "project" | "global", projectId, threadId, composer: "new-thread" | "follow-up" } with nullable IDs. It also accepts waitForHistory (default true) and refreshHistory (default true). Set waitForHistory: false to return available results immediately. Poll with refreshHistory: false while loading is true to observe the in-progress work without starting another refresh. Use refreshHistory: true to refresh or retry a failed background load. It returns { prompts, loading, historyError }, where historyError is null or a failure message. CLI search waits for complete results by default; --partial returns the same progressive snapshot. Each row has kind: "starred" | "recent"; star takes { prompt: { text, mentions }, title? }; setTitle takes { id, title } (use null to clear) and returns { id, title }. Search returns title and highlighted titleSnippet on starred rows; CLI list and star JSON also include title. unstar and markUsed take { id }.
The bundled plugin is disabled by default. Enable it in Settings → Plugins or with bb plugin enable bb--prompt-library. Its Search prompts shortcut is rebindable in Keyboard Settings. Plugins can page through the same core history with bb.sdk.experimental_promptHistory.list({ cursor, limit }).
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/prompt-library/skills/prompt-library/SKILL.md
Popularity
- Repository stars
- 4,602
- Repository forks
- 700
- 7-day trend score
- 5
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/get-bb/bb/prompt-library)