Skip to content
Automation
Skill

/domain-brainstorm

On-demand dev-voice brainstorm: reads codebase friction signals (git churn, manifest drift, README coverage) and emits at most 2 improvement ideas, each gated by proposal-triage before becoming a proposal task. Invoke when the operator asks "what should I be fixing?", "anything

From plugin
hermitd
8489 skills14 agents

Claude Code

$ npx -y skills add gtapps/hermitd --skill domain-brainstorm --agent claude-code

SKILL.md

domain-brainstorm.SKILL.md
name: domain-brainstorm
description: On-demand dev-voice brainstorm: reads codebase friction signals (git churn, manifest drift, README coverage) and emits at most 2 improvement ideas, each gated by proposal-triage before becoming a proposal task. Invoke when the operator asks "what should I be fixing?", "anything wrong with X?", or "brainstorm improvements". Never runs autonomously.

Domain Brainstorm

Kill criteria (read before running)

After ≥8 invocations, check the `capability-brainstorm` segment of core's proposal metrics: run `.hermit/bin/hermitd-run proposal metrics .hermit --source=capability-brainstorm` (the project-resident `bin/hermitd-run` resolves core's plugin root, which a path relative to this plugin can't reach). When its `status` is `kill`, treat it as a class-level signal that brainstorm output is noisy and raise it with the operator, naming the `kill_reasons` with their `triage_survival_pct` and `acceptance_pct`. The segment is shared with core's `capability-brainstorm` and the other domain brainstorm skills, so it cannot by itself say which skill to cut.

Gate 0 — Gather inputs

Read these in parallel — all are cheap working-tree reads. Do not run the test suite or install tools.

**Git activity**

git log --oneline -50
git log --format= --name-only -50 | sort | uniq -c | sort -rn | head -20

Note the 5 most-churned files and any subsystem clusters.

**Manifest drift** `ls` for `package.json`, `Cargo.toml`, `pyproject.toml`, `go.mod`. For each found, check its lockfile (`package-lock.json`/`yarn.lock`/`pnpm-lock.yaml`, `Cargo.lock`, `poetry.lock`, `go.sum`) exists alongside it. Flag any mismatch.

**README coverage** Read `README.md` and a one-level `ls` of the repo root. Note features or modules claimed in the README with no corresponding directory or file visible.

Gate 1 — Generate ideas (max 2)

Think across all three inputs. For each candidate, both constraints must pass before including it:

1. **Concrete friction** — state the operator pain in one sentence. What breaks, slows, or misleads today without this fix? If no specific pain, discard. 2. **≥2 named grounding items**: cite at least two by name (e.g. `git:cli/index.js`, `file:package-lock.json missing`, `readme:§Feature X`). These support the friction; friction is the bar.

Map each passing idea to the closest dev prefix: `[missing-tests]`, `[tech-debt]`, `[dependency]`, `[tooling]`, or `[architecture]`.

Cap at 2 ideas. Emit-zero if none pass. Record discarded candidates (one line each) for Gate 4.

Gate 2 — Create proposals

For each idea, invoke `/hermitd:proposal-create` once:

Title: [<prefix>] <short idea title>
Evidence Source: capability-brainstorm
Evidence: <one paragraph: friction sentence + named grounding items>

Set task metadata: `source: auto-detected`, `category: improvement`, `tags: [capability-brainstorm]`.

> `Evidence Source: capability-brainstorm` is reused intentionally: it is the only source `proposal-triage` recognizes for the single-pass recurrence bypass, and adding a dedicated `domain-brainstorm` source is a core edit this skill deliberately avoids. Provenance is carried by the `tags` above, which `proposal-create` writes onto both the `triage-verdict` row and the proposal task metadata. The cost: these proposals share core `capability-brainstorm`'s kill-criteria segment, so the numbers are combined rather than per-skill.

Parse the verdict:

  • `CREATE: <title> — <task-id> (<handle>)`: proposal task opened; record its T- id.
  • `SUPPRESS: <title> — <code>: <reason>`: record the suppression code. Don't retry.
  • `DUPLICATE: <title> — <task-id>: <reason>`: record the existing task id. Don't create.

Do NOT invoke `proposal-triage` directly — `/proposal-create` handles it.

Gate 3 — Emit batch message

Send one message per the Operator Notification protocol.

Zero-emit:

🔧 Domain brainstorm — 0 ideas emitted (<reason: thin context | all suppressed | all duplicates>)

Non-zero:

🔧 Domain brainstorm (<N> idea(s))

1. **[prefix] <title>** — <one-line description>
   _Grounding: <item 1>, <item 2>_
   _Friction: <one-sentence pain>_
   T-YYYYMMDD-HHMMSS created  ·  (or: suppressed — <code>  ·  or: duplicate of T-YYYYMMDD-HHMMSS)

Gate 4 — Compiled artifact (non-empty runs only)

If ≥1 proposal task was created (not suppressed or duplicate), write:

`.hermit/compiled/domain-brainstorm-YYYY-MM-DD-HHMM.md`

---
title: Domain brainstorm — <ISO timestamp>
type: domain-brainstorm
created: <ISO timestamp with timezone>
tags: [domain-brainstorm, ideation]
source: interactive
proposals_created: [T-YYYYMMDD-HHMMSS, ...]
---

Body (150-line cap): ideas that passed (one paragraph each), discarded candidates (one line each), triage verdicts, inputs scanned (paths only, no content).

Do not tag `foundational` — this is a time-bounded ideation snapshot.

**Zero-emit runs:** skip the artifact entirely. Inside an open record's turn, pipe one line into `.hermit/bin/hermitd-run task note .hermit <id>`; otherwise skip the note: `domain-brainstorm: 0 ideas emitted (<reason>)`

Read more
@gtapps
Ships withhermitd

Run an always-on Claude Code agent on your own machine, for you or your team. Start and orchestrate sessions from chat in any project it can reach. Take over the same session in the Claude app or the CLI.

8489 skills14 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
84
Star history of gtapps/claude-code-hermit on GitHub, a chart by star-history.com

Other skills on hermitd.

bump-core-req

bump-core-req

Updates the minimum core version requirement for a fleet plugin in all three canonical places: `required_core_version` and…

@gtapps@gtappsInstall Skill
commit

commit

Changelog and commit — lightweight motion for day-to-day plugin dev work in the monorepo. One commit per plugin scope; CHANGELOG…

@gtapps@gtappsInstall Skill
docs-drift

docs-drift

Documentation-drift audit for the plugin monorepo. Audits either each scoped plugin's unreleased changelog claims or its latest…

@gtapps@gtappsInstall Skill
downstream-impact

downstream-impact

Explain in plain language what a fix, feature, PR, or plan will actually change for downstream hermits and the operators chatting…

@gtapps@gtappsInstall Skill
fleet-release

fleet-release

Use this skill whenever the user wants to release, ship, prep, or cut versions for two or more plugins together on the current…

@gtapps@gtappsInstall Skill
pipeline-digest

pipeline-digest

Daily release-pipeline digest with a change gate — reports which plugins are pending release, whether main's CI is green, which…

@gtapps@gtappsInstall Skill

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n12d209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
agent-browser

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…

@vercel-labs-2@vercel-labs-2Install Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about domain-brainstorm.

Which coding agents can use domain-brainstorm?
domain-brainstorm installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.