reflect-skills-from-me…
This skill should be used when the user asks to "reflect on skills from memory", "audit marketplace skills against memory",…
This skill should be used when the user asks to "create PRD", "write product requirements document", or mentions "PRD", "product requirements document".
$ npx -y skills add FradSer/dotclaude --skill create-prd --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/create-prdContext preview
The summary Claude sees to decide when to auto-load this skill.
This skill should be used when the user asks to "create PRD", "write product requirements document", or mentions "PRD", "product requirements document".
name: create-prd description: This skill should be used when the user asks to "create PRD", "write product requirements document", or mentions "PRD", "product requirements document". user-invocable: true argument-hint: "--md | --lark [--folder-token TOKEN_OR_URL | --wiki-node TOKEN_OR_URL | --wiki-space ID_OR_URL]" allowed-tools: ["Read", "Write", "AskUserQuestion", "Glob", "Bash(lark-cli:*)", "Skill"]
Follow the phases below to transform product ideas into a complete PRD document. All PRD content is written in Chinese (the target audience is Chinese-speaking teams).
Determine output mode from `$ARGUMENTS`:
| Argument | Mode | Output | |----------|------|--------| | `--md` (default) | Local Markdown | Save as `.md` file to project directory | | `--lark` | Feishu Cloud Doc | Create via `lark-cli` using Lark rich-text features |
`--lark` mode accepts optional location arguments (mutually exclusive), supporting token or Feishu URL:
Pass URL directly to `lark-cli` — no manual token extraction needed. Defaults to user's personal space root when no location specified.
Check for existing design or requirements documents:
1. Search for `docs/`, `prd/` directories or user-specified files 2. If found, extract key information (problem statement, target users, core features) as pre-filled content 3. If nothing found, skip this phase
Ask the user which PRD type they need:
Follow the interview questions in `references/prd-interview-questions.md`, one question at a time. Wait for the answer before continuing.
If Phase 0 found pre-filled content, show it to the user for confirmation and skip covered questions.
1. **Select template**:
2. **Fill content**: Use gathered information for each section, following `references/prd-best-practices.md` writing principles
3. **AI Agent consumability**:
4. **Quality requirements**:
5. **Format**:
Run validation per `references/prd-validation-checklist.md` — completeness, SMART goals, content quality, BDD acceptance criteria.
Save file after validation:
Create Feishu document after validation:
1. **CRITICAL** — Confirm standalone `lark` plugin (`lark@frad-dotclaude`) is installed; follow its `lark-shared` skill for authentication 2. Follow the lark plugin's `lark-doc` skill for document creation guidance 3. Refer to `lark-doc-create.md` for full `docs +create` parameters and Lark-flavored Markdown syntax 4. Convert PRD content to Lark-flavored Markdown (see Feishu enhancements section) 5. Create document:
lark-cli docs +create --title "PRD-[ProductName]-[YYYYMMDD]" \
[--folder-token TOKEN_OR_URL | --wiki-node TOKEN_OR_URL | --wiki-space ID_OR_URL] \
--markdown "<lark-flavored-markdown>"6. For longer PRDs, split: `docs +create` for first half, then `docs +update --mode append` for remaining sections 7. If `board_tokens` are present:
8. Report the document URL
After saving, suggest follow-up options:
**CRITICAL** — In `--lark` mode, use Lark-flavored Markdown syntax to leverage Feishu's rich-text capabilities.
| PRD Section | Feishu Feature | Description | |---|---|---| | Project metadata (version/date/owner) | `<lark-table>` | Enhanced table with header row | | Key risks/assumptions/dependencies | `<callout>` | Color-coded: risk=red, assumption=blue, dependency=yellow | | Core goals / success metrics | `<callout emoji="..." background-color="light-green">` | Highlight key OKRs | | Priority comparison (P0/P1/P2) | `<grid cols="3">` | Three-column side-by-side layout | | User journey / business process | `<whiteboard type="blank">` | Flowchart, filled via lark-whiteboard | | System architecture | `<whiteboard type="blank">` | Architecture diagram, filled via lark-whiteboard | | Milestones / timel
A curated collection of 22 plugins for Claude Code, providing specialized agents, skills, and automation tools for development and productivity workflows.
This skill should be used when the user asks to "reflect on skills from memory", "audit marketplace skills against memory",…
Use acpx as a headless ACP CLI for agent-to-agent communication, always inside an isolated SubAgent. Use when running coding…
Delegates a self-contained task to a Google Gemini Managed Agent (Antigravity) running in a remote sandbox with code execution,…
Runs a deep-research query on Google Gemini's deep-research managed agent and returns a cited report. This skill should be used…
This skill should be used when the user asks to "understand a codebase", "get code context", "research a library", "explore a…
Execute this when the user requests code context for a repository, library, or any natural-language code/technology question…