automate-me
Turn recurring working preferences in scoped agent sessions into a small, portable skill or project rule. Use when someone asks to capture how they work or update their personal mode.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- automate-me
- metadata
- { "author": "Brenden Bishop", "attribution": "../../ATTRIBUTION.md" }
- description
- Turn recurring working preferences in scoped agent sessions into a small, portable skill or project rule. Use when someone asks to capture how they work or update their personal mode.
- disable-model-invocation
- false
02 资源文件 1
- 参考文档agents/openai.yaml42 B
03 SKILL.md 正文
Automate me
Turn repeated corrections and preferences into something an agent can follow. Start with the user's stated preferences. Ask which project and time window to inspect before reading other sessions. Use the bundled session reader to list and selectively read Codex, Claude Code, Cursor, Grok, and available Amp sessions. Local readers constrain results to the selected project. Amp's thread list cannot yet prove a project or time match, so confirm selected thread IDs before opening them and pass --allow-unverified-amp when reading. Report missing providers rather than claiming a complete history.
Look for patterns across sessions, not one-off requests. Show the proposed rules and the evidence for each. Choose the smallest durable home: an existing project instruction for project behavior, a task skill for a repeated procedure, or personal memory for a stable personal preference. Don't create a new -mode skill when a short addition to an existing one suffices. Do not copy raw transcripts into the repository or generated skill.
When personal memory is the destination, read the installed memory policy and obtain approval for the exact change before writing. For a project skill, use the host's skill authoring capability or BStack's authoring playbook. Put portable skill files under .agents/skills, then use BStack setup to bind selected hosts. Keep the resulting skill short, test discovery in the selected host, and present the draft before landing it.
The output is a proposed change with its destination and evidence. Reading sessions does not itself authorize publishing or writing personal memory.
04 同仓库更多 Skills
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
unslop
Cut AI tells from any writing. Must always apply.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.