AGENT SKILL

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 create-skill + unslop, optionally pulling fresh evidence from recent transcripts.

License 许可
MIT
最近更新
2026-11-13
Stars
★ 0
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 create-skill + 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 an inline mining pass, skill-creator, writing-for-agents, and unslop. It sequences them; it doesn't replace them.

Flow

Read HOST-COMPATIBILITY.md before the first host-specific lookup or question.

0. Check for an existing skill

Look recursively for .agents/skills/**/*-mode/SKILL.md and the current host's user-level skill directories matching the user's handle. Mode skills can live in a personal category directory. If one exists, confirm intent through structured input when available, 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

Use the host's task or conversation APIs when available. Otherwise use only the workspace-scoped transcript location supplied by the host. Never scan unrelated projects. If no history interface exists, use the visible conversation and state the smaller evidence window.

Survey recent agent conversations within that scope for recurring patterns. Divide the requested time window into coherent semantic slices and dispatch them as bulk-reader through the active profile. The partition route maps those slices onto the user-configured roster and both task limits. Each read-only leaf reads only the workspace-scoped transcripts its unit names and returns a short structured list of patterns 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 structured multi-choice input when the host provides it. Otherwise ask concise chat questions.

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 agent-mode skill shows the shape. Read it for granularity. Do not copy its content because the user's rules may differ from Agent mode.

4. Draft the skill

Invoke skill-creator and writing-for-agents to author the skill. Placement:

  • Path: preserve an existing mode skill's category. For a new repository skill, use .agents/skills/<handle>-mode/SKILL.md. Use the current host's user-level skill root only when the user asks for 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: follow skill-creator 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. 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 unslop, skill-creator, and writing-for-agents 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.
  • 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 create-skill-style 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): create-skill 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 agent-mode skill. Use it as an example of the output shape.
  • The unslop skill: prose discipline for every line.
  • The skill-creator and writing-for-agents skills: skill authoring process and writing guidelines.

04 同仓库更多 Skills