automate-me

Files (1)

• SKILL.md

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, Amp's built-in `building-skills`, and the **unslop** skill. It sequences them; it does not replace them.

## Flow

### 0. Check for an existing skill

Look recursively for `.agents/skills/**/*-mode/SKILL.md` and `~/.config/agents/skills/*-mode/SKILL.md` matching the user's handle. If one exists, confirm whether to update it or start fresh unless the user already made that clear.

- 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 `find_thread` to locate the active project's recent Amp threads, defaulting to the last 2-4 weeks. Use `read_thread` only for candidates that appear relevant. Never search other projects without the user's request.

For a large history, partition candidate thread IDs and run local `orbstack_run_agent` workers on `low`. Each returns a short structured list of recurring patterns with Amp thread IDs as 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 structured questions rather than making the user describe their entire style 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. 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 **orb-mode** skill shows the shape. Read it for granularity. Don't copy its content; the user's rules are not the same as orb-mode's.

### 4. Draft the skill

Use Amp's built-in `building-skills` skill to author the skill. 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 `~/.config/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 `name` equal to the directory name and use one clear `description` scalar.
- Put the result in an Amp plugin only when the user wants a selectable agent mode. Otherwise create a normal project or personal skill.

### 5. Iterate on prose

Apply the **unslop** skill and `building-skills` 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 so the user can review it. 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 synthetic benchmark loop is not useful here. Check the draft with the user, then ship it.

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: use `building-skills` without history mining.
- 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 **orb-mode** skill: example of the output shape.
- The **unslop** skill: prose discipline for every line.
- Amp's built-in `building-skills` skill: skill authoring process and writing guidelines.

From MRL-00/orbstack, MIT.

More from MRL-00/orbstack