automate-me

Files (2)

• SKILL.md
• openai.yaml · agents/

SKILL.md (first lines)

# 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), the authoring guidance in `../poteto-mode/playbooks/authoring-a-skill.md`, and the **unslop** skill (prose discipline). It sequences them. It doesn't replace them.

## Flow

### 0. Check for an existing skill

Look recursively for `.agents/skills/**/*-mode/SKILL.md` and `~/.agents/skills/*-mode/SKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.agents/skills/<handle>/`), not only at the top level. If one exists, confirm intent with `AskQuestion` (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. Replace a `disable-model-invocation` line in its frontmatter with the gate that step 4 describes.

### 1. Mine their history

Use the **pstack-harness** skill to locate the active workspace's transcripts before fanning out. Use only this workspace's store. Don't read other workspaces' sessions. That crosses workspace boundaries and reads private chats from unrelated projects.

Survey recent agent conversations within that scope for recurring patterns. Run multiple parallel subagents on the `routine` role across slices of history (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Use the **pstack-harness** skill's **Spawn a role** section to resolve the role. Each slice mining subagent reads transcripts from the workspace-scoped path the parent provides, 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 hasn't come up yet. Use the `AskQuestion` tool (structured multi-choice) rather than asking the user to type from scratch.

Shape: one or two questions with 4-6 options each, `allow_multiple: true` for category questions. Start broad ("Which areas matter most?"), then follow up on selected areas with specific options. After the structured rounds, one free-form chat question catches anything the options missed.

Don't dump 20 questions.

### 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 per `../poteto-mode/playbooks/authoring-a-skill.md`. Placement:

- Path: preserve an existing mode skill's category. For a new mode, use `.agents/skills/<handle>/<handle>-mode/SKILL.md` when the repo has an established personal category for that handle. Otherwise default to `.agents/skills/<handle>-mode/SKILL.md` in the project (or `~/.agents/skills/<handle>-mode/` if the user prefers a personal 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: Keep frontmatter valid YAML. Keep `description` as one YAML scalar. Quote it or use `description: >-` with indented continuation lines when punctuation or wrapping requires it.
- Gate the skill by default, so it loads only when the user types it or a skill names it. Write `agents/openai.yaml` beside its `SKILL.md`, with `allow_implicit_invocation: false` under `policy:`, which gates it on Codex. On Claude Code, offer to add `"<handle>-mode": "name-only"` under `skillOverrides` in the user's `~/.claude/settings.json`, as setup-pstack step 0c does for pstack's own skills. Write the entry only after the user says yes, and keep every other key. Never write `disable-model-invocation`, because Claude Code's Skill tool then refuses the skill when another skill names it. Opt out of the gate only if the user explicitly wants their mode to apply on every turn.

### 5. Iterate on prose

Use the **unslop** skill on every line, with the authoring-a-skill playbook's writing guidelines.

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.** Name another skill the user relies on with "Use the **<name>** skill.", for example "Use the **unslop** skill.", using that skill's bare name, per the authoring playbook, never as a pasted excerpt. Point at principle docs they maintain elsewhere by path.
- **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. A test/iterate benchmark 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): the authoring-a-skill playbook 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.

From mdsmithaustin/pstack, MIT.

More from mdsmithaustin/pstack