菜单
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
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
Use when one Claude session or process must message, hand off work to, or coordinate with another independent Claude session on the same machine, or dispatch a task to another session and track its acknowledgement or completion. Also use when native SendMessage cannot reach the target session (it is team-scoped and cannot reach one it did not spawn), or when told to coordinate over claude-bus.
Use when building or extending a Google Slides deck programmatically (Slides API or a Workspace CLI like gws), when new slides must automatically inherit a consistent background/font/layout, when a diagonal line/connector/arrowhead renders wrong, when building flowcharts or other diagrams via the API, when asked about Morph or slide/object animation via the API, when you need a custom slide layout/master and the Slides API alone can't create one, when a replaceAllText edit seems to vanish or hit zero occurrences unexpectedly, or when auditing an existing deck for leftover unstyled or inconsistent elements
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Use when searching a codebase to answer "where does X happen", "what is related to Y", or to map an unfamiliar area, especially when the semble MCP server is available. Also use when grep is returning too much noise or you do not know the exact symbol to grep for. Skip for: known-symbol lookups, error-string searches, or one-shot reads where the file path is already known.
Communication mode that is brief by default, signal when it matters — keeps human mental model in sync with agent
| name | to-prd |
| description | Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context. |
This skill takes the current conversation context and codebase understanding and produces a PRD. Do NOT interview the user — just synthesize what you already know.
Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the PRD, and respect any ADRs in the area you're touching.
Sketch out the seams at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can.
Check with the user that these seams match their expectations.
ready-for-agent triage label - no need for additional triage.The problem that the user is facing, from the user's perspective.
The solution to the problem, from the user's perspective.
A LONG, numbered list of user stories. Each user story should be in the format of:
This list of user stories should be extremely extensive and cover all aspects of the feature.
A list of implementation decisions that were made. This can include:
Do NOT include specific file paths or code snippets. They may end up being outdated very quickly.
Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.
A list of testing decisions that were made. Include:
A description of the things that are out of scope for this PRD.
Any further notes about the feature.