capability-brainstorm

# Capability Brainstorm ## Kill criteria (read before running) After ≥8 invocations, run: ``` bun ${CLAUDE_PLUGIN_ROOT}/scripts/proposal-metrics-report.ts .claude-code-hermit --source=capability-brainstorm ``` Triage-survival < 25% or acceptance < 30% → cut this skill rather than tune it — the signal-to-noise ratio isn't there. `INSUFFICIENT` output means the ≥8-verdict sample hasn't been reached yet; wait and re-check. ## 1. Gather capability signals (harness-context — read before dispatch) These three sources require the main session's harness context and cannot be delegated: - *Skills:* use the harness available-skills list loaded in your context — that is authoritative. - *MCPs:* call `ListMcpResourcesTool` to enumerate currently online MCP tools. - *Channels:* read `config.json` → `channels` keys. ## 2. Dispatch the eval runner Pass the capability signals from Step 1 in the dispatch prompt. Dispatch `claude-code-hermit:skill-eval-runner` pointed at `${CLAUDE_PLUGIN_ROOT}/skills/capability-brainstorm/reference.md`. Include in the dispatch prompt: - `plugin_root`: `${CLAUDE_PLUGIN_ROOT}` (resolved absolute path — the runner needs it for the sibling-scan, since `${CLAUDE_PLUGIN_ROOT}` is not substituted in `reference.md` content) - `skills_list`: the harness available-skills list (one skill per line) - `mcp_tools`: the `ListMcpResourcesTool` output - `channels_keys`: the `channels` key list from config.json The runner reads memory topic files, compiled artifacts, ...