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 combines a history-mining pass, the **pstack-runtime** skill-authoring contract, and the **unslop** skill. It sequences them; it does not duplicate their rules.

## Flow

### 0. Check for an existing skill

Look for `*-mode/SKILL.md` matching the user's handle under the project's `.claude/skills/` or `~/.claude/skills/`. If one exists, confirm intent with the host's structured ask tool unless the user 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

Resolve transcript access through the **pstack-runtime** contract. Use only the active workspace and explicitly identified sessions. If no safe transcript path is available, mine the current conversation and ask what earlier period matters instead of scanning unrelated histories.

Survey recent conversations within that scope for recurring patterns. Run parallel read-only subagents across slices of history when there is enough material. Each returns a short structured list with evidence pointers. Default signals:

- 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. Use the host's structured ask tool rather than asking the user to type everything from scratch.

Ask one or two questions with 4-6 options each and enable multiple selection for category questions when the host supports it. Start broad ("Which areas matter most?"), then follow up on selected areas. Finish with one free-form question for 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 **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 under the **pstack-runtime** contract:

- Path: `.claude/skills/<handle>-mode/SKILL.md` in the project, or `~/.claude/skills/<handle>-mode/` when the user wants a personal skill.
- Handle: the user's first name or chosen identifier.
- Frontmatter `name`: `<handle>-mode`.
- Frontmatter `description`: trigger on their name, the explicit mode name, and "work in their style"; avoid generic triggers such as "write code" or "review PR".
- Frontmatter `disable-model-invocation: true` by default. Mode skills are heavy and opinionated; auto-trigger only when the user explicitly requests it.

### 5. Iterate on prose

Apply the **unslop** skill and the **pstack-runtime** authoring contract 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. Vibe-check with the user: does it read like them, and 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 rather than working conventions: author that skill directly under the **pstack-runtime** contract; 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.

## Reference files

- The **poteto-mode** skill: example of the output shape.
- The **unslop** skill: prose discipline for every line.
- The **pstack-runtime** skill: shared Claude Code and OMP authoring, transcript, and subagent contract.

From IgorKhramtsov/pstack-skills, MIT.

More from IgorKhramtsov/pstack-skills