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), Hermes' skill_manage tool (authoring), and the unslop skill (prose discipline). It sequences them; it doesn't replace them.

Flow

0. Check for an existing skill

Look recursively for project .hermes/skills/**/*-mode/SKILL.md and ~/.hermes/skills/*-mode/SKILL.md matching the user's handle. Mode skills can live in a personal category directory (.hermes/skills/<handle>/), not only at the top level. If one exists, confirm intent with clarify (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.

1. Mine their history

Use the parent's session_search tool to find relevant recent conversations. Start with distinctive terms and a newest-first search, then open only matching windows or session links. Do not infer transcript paths or scan unrelated sessions. Delegated children cannot use session_search; if parallel analysis helps, the parent first gathers exact excerpts and passes one bounded excerpt set to each no-write child.

Survey those in-scope conversations for recurring patterns. Each mining pass returns a short structured list with session links or message anchors as evidence. 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 clarify tool (structured multi-choice) rather than asking the user to type from scratch. Lower cognitive load, higher hit rate.

Shape: one or two questions with at most 4 choices each, multi_select=true for category questions. Start broad ("Which areas matter most?"), then follow up on selected areas with specific options. If needed, use one open-ended clarify question for anything the choices 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

Use Hermes' skill_manage tool for a user-level skill. For a project-local skill, follow the Hermes skill-authoring workflow and write inside that repository instead. Placement:

• Path: preserve an existing mode skill's category. For a new project mode, use .hermes/skills/<handle>-mode/SKILL.md; for a personal skill created through skill_manage, use the active Hermes profile's user skill store.
• 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 Hermes skill frontmatter rules. Keep description as one YAML scalar; quote it or use description: >- with indented continuation lines when punctuation or wrapping requires it.
• Hermes frontmatter does not create a sticky or explicit-only mode. Keep only supported metadata, make the description's trigger precise, and state in the body that the user should load the skill again after a reset or new session.

5. Iterate on prose

Apply the unslop skill and Hermes' skill_manage writing guidelines to every line. Both apply to any agent-read prose, not just skills.

Show the draft to the user and take feedback. Expect multiple iterations. Cut ruthlessly; a mode skill is not a manual.

6. Land it

For a project-local skill, work in an isolated branch or worktree and open a PR only when the user authorized that remote write. For a user-level skill, show the proposed content and apply it through skill_manage after approval; there is no repository PR unless that skill store is itself version-controlled.

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 skill-authoring 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): skill_manage 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 poteto-mode skill: example of the output shape.
• The unslop skill: prose discipline for every line.
• Hermes' skill_manage tool skill: skill authoring process and writing guidelines.