automate-me

Files (1)

• SKILL.md

SKILL.md (first lines)

# Automate me

Read [the Pi execution contract](../../docs/harness/pi.md). Mine authorized history with available investigators or inline, and report unavailable history and lost independence.

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`).

Mine the evidence, author a native Pi skill, and use the **unslop** skill for prose discipline.

## Flow

### 0. Check for an existing skill

Look for matching mode skills in the active project's `.pi/skills/` and the user's `~/.pi/agent/skills/`. Preserve an existing location. If intent is unclear, ask whether to update the existing skill or start fresh:

- 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

Use the advertised Pi history tool or the current workspace's explicitly identified session paths. Do not search unrelated workspace sessions without authorization.

Survey relevant conversations within that scope for recurring patterns. Assign independent slices to authorized investigators or mine them serially yourself. Return a short list of patterns with evidence pointers. 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 hasn't come up yet. Ask about material user-owned choices not answered by existing instructions, using the available question tool or conversation.

Keep questions focused; do not ask the user to repeat preferences already established in scope.

### 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

Follow Pi's skill documentation and repository guidance to author the skill. Placement:

- Path: preserve an existing mode skill's category. For a new mode, use `.pi/skills/<handle>-mode/SKILL.md` in the project or `~/.pi/agent/skills/<handle>-mode/SKILL.md` for a user-wide skill.
- 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 skill YAML rules. Keep `description` as one YAML scalar. Quote it or use `description: >-` with indented continuation lines when punctuation or wrapping requires it.
- Frontmatter `disable-model-invocation: true` by default. Opt out only if the user explicitly wants their mode to apply on every turn.

### 5. Iterate on prose

Apply the **unslop** skill and Pi's skill-writing guidance to every line.

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. Commit and open a PR. 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.
- **Don't force symmetry.** If a user has no process rules worth writing down, skip the Process section entirely.

## Evaluation

A `-mode` skill is subjective output. Check it against the user's stated preferences and available evidence; get feedback when that decision belongs to the user.

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): use the Pi skill-authoring guidance; no history 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.

From fitchmultz/pi-pstack, MIT.

More from fitchmultz/pi-pstack