automate-me
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via Pi skill authoring + unslop, optionally pulling fresh evidence from recent transcripts.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- automate-me
- description
- Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via Pi skill authoring + unslop, optionally pulling fresh evidence from recent transcripts.
- disable-model-invocation
- true
03 SKILL.md 正文
Automate me
A guided flow for turning the user's working conventions into a skill agents will follow. The output is one -mode skill tailored to them (e.g. jay-mode, priya-mode).
This skill orchestrates three others: an inline mining pass (see step 1), Pi skill authoring (authoring), and the unslop skill (prose discipline). Pi skill authoring here means Pi's skills documentation (docs/skills.md in the installed Pi package) plus the skill-authoring playbook, ../poteto-mode/playbooks/authoring-a-skill.md. It sequences them; it doesn't replace them.
Flow
0. Check for an existing skill
Look recursively for .pi/skills/**/*-mode/SKILL.md and ~/.pi/agent/skills/*-mode/SKILL.md matching the user's handle. Mode skills can live in a personal category directory (.pi/skills/<handle>/), not only at the top level. If one exists, confirm intent by asking in your reply and ending the turn (unless they already said "update my skill" or similar):
- Update the existing skill (default for repeat runs)
- Start fresh (rare; ask why before doing it)
Update mode changes the rest of the flow:
- Step 1 mines only history since the skill was last edited (
git log -1 --format=%cI <path>). - Step 2 asks what's changed or missing, not what to capture from zero.
- Step 4 edits the existing file in place. Preserve sections the user hasn't contradicted; revise ones with new evidence; add new sections only for genuinely new rules.
1. Mine their history
Locate prior Pi sessions for the current working directory before fanning out, with the per-cwd session directory rule in ../poteto-mode/playbooks/session-pickup.md. Read only that one directory. Before grepping, reading or delegating an earlier session file, read only its first line, the session header, and check that its cwd is exactly this working directory: a session directory's encoded name can collide with another project's, and a directory can be shared. Skip any session whose header names another directory, or has none, without reading further. A child brief lists only the files that passed and tells the child to repeat this check before it greps or reads one. Never glob all of ~/.pi/agent/sessions/, because that crosses project boundaries and may read unrelated private chats.
Survey recent agent conversations within that scope for recurring patterns. Launch one bare investigator child per slice of history (e.g. last 2-4 weeks, split into 3 slices so each has enough material), as independent subagent calls in one turn per ../poteto-mode/references/fan-out.md, with model: "task:recon". Each slice mining child reads only the session files the parent lists in its task, after repeating the header check on each, looks for the signals below, and returns a short structured list of patterns it saw with evidence pointers. Default signals worth hunting:
- Response preferences (length, tone, format, "dumb it down" corrections)
- Delegation habits (subagents, models, specialized workflows, parallelism)
- Verification posture (what "done" means; unit tests vs live repro; reviewers)
- Code and prose discipline (style, principles cited, lint/format tools)
- Process conventions (worktrees, commits, PRs, review/merge tooling)
- Meta preferences (fixing skills mid-task, proposing new ones)
Cross-check across slices before elevating a signal. Patterns seen in 2+ slices are high-confidence; lone signals are weak and usually get dropped.
2. Ask the user directly
Mining misses intent that has not come up yet. Ask one or two concise questions in your reply, each with 4-6 numbered options, then one optional free-form follow-up, and end the turn for the answers. Do not block on questions that an experiment or repository evidence can answer.
Don't dump 20 questions. Two structured rounds plus one open question is usually enough.
3. Cluster findings
Group the combined signals into sections. Common ones (use only what applies):
- Response style: length, tone, format.
- Autonomy: how much to do without asking; MCP tool use.
- Understand first: which skills to reach for when scoping or investigating a change.
- Subagents: default, parallelism, model-to-task, specialized workflows.
- Prose / code discipline: principles, lint tools, style guides.
- Review and verify: repro posture, verification skills, live-testing tools.
- Process: git worktrees, commits, PRs, review/merge tooling.
- Skills: skill-authoring habits, fix-the-skill-first, proposing new skills.
The poteto-mode skill shows the shape. Read it for granularity. Don't copy its content; the user's rules are not the same as poteto-mode's.
4. Draft the skill
Author the skill with Pi skill authoring. Placement:
- Path: preserve an existing mode skill's category. For a new mode, use
.pi/skills/<handle>/<handle>-mode/SKILL.mdwhen the repo has an established personal category for that handle; otherwise default to.pi/skills/<handle>-mode/SKILL.mdin the project. Writing inside the project's.pi/skills/needs no permission. A personal skill at~/.pi/agent/skills/<handle>-mode/changes the user's Pi configuration, so write there only after the user explicitly confirms that path. - Handle: the user's first name or chosen identifier.
- Frontmatter
description: trigger on their name +/<handle>-mode+ "work in their style", not on generic keywords like "write code" or "review PR". - Frontmatter formatting: follow Pi's skills documentation. The
nameis lowercase letters, digits and single hyphens, at most 64 characters, and thedescriptionis at most 1024 characters. Keepdescriptionas one YAML scalar; quote it or usedescription: >-with indented continuation lines when punctuation or wrapping requires it. - Frontmatter
disable-model-invocation: trueby default. Mode skills are heavy and opinionated; they should only apply when the user explicitly invokes them (by name or slash command), not auto-trigger on description matching. Opt out only if the user explicitly wants their mode to apply on every turn.
5. Iterate on prose
Apply the unslop skill and the writing rules of Pi skill authoring to every line. Both apply to any agent-read prose, not just skills.
Show the draft to the user and take feedback. Expect multiple iterations. Cut ruthlessly; a mode skill is not a manual.
6. Land it
Work in a worktree off main and commit there when the task's commit policy allows. Pushing and opening a PR so the user can review it each need the user's explicit authorization (../poteto-mode/references/authorization.md). Without it, report the branch, the commit and the diff. Don't push to main directly.
Guardrails
- Don't overfit to one conversation. A preference stated once and contradicted another time is noise. Require multiple instances before codifying it.
- Don't be clever. Restating other skills' contents, inventing metaphors, or writing "poetic" prose for an agent reader is cost without benefit. Keep it operational.
- Reference, don't inline. Other skills the user relies on should appear as path references, not pasted excerpts. Same for any principle docs they maintain elsewhere.
- Keep sections minimal. Only add a section if the user has a specific, non-default rule there. "Communicate clearly" is not a section. "Short paragraphs. Tables when comparing options. Bullets only when items are genuinely parallel." is.
- Name conventions generic. Use "the user" or "the human" in imperatives, not the author's first name. Others may read or adopt the skill.
- Don't force symmetry. If a user has no process rules worth writing down, skip the Process section entirely. Sparse is fine; bloated is not.
Evaluation
A -mode skill is subjective output. A benchmark-style test and iterate loop isn't useful here. Vibe-check with the user: does it read like them? Did it miss anything? Then ship.
Run a description-optimization loop only if the skill's trigger accuracy turns out to be a problem in practice.
When not to use
- User wants a task-specific skill (not working conventions): Pi skill authoring alone, no mining required.
- User wants to capture one narrow workflow (e.g. "how I write commit messages"): that's a regular skill, not a mode skill.
Reference files
- The poteto-mode skill: example of the output shape.
- The unslop skill: prose discipline for every line.
- Pi's skills documentation and
../poteto-mode/playbooks/authoring-a-skill.md: skill authoring process and writing guidelines.
04 同仓库更多 Skills
poteto-mode
Test fixture. A different skill that reuses the poteto-mode name, to check shadowing diagnostics.
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 /skill:technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
swarm
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.