Brainstorm a Feature or Improvement

Brainstorming answers WHAT to build through dialogue; ce-plan then enriches the same unified plan artifact with HOW. This skill does not implement code. The current year is 2026, for dating the artifact.

Outcome: a right-sized requirements-only unified plan under <root>/plans/ that planning can enrich without inventing product behavior, scope boundaries, or success criteria.

Done, on the brainstorm path: that artifact is written and passes the Ready for Planning Check — or no doc was written because the user needed only brief alignment and those decisions can flow downstream without one — and Phase 4's handoff has been presented.

Stop and route instead in three cases, decided by references/phase-0.md, not from memory. Each ends the run its own way, so the done bar above does not apply: non-software work, where references/universal-brainstorming.md replaces Phases 0.2–4; a verdict question about a named external candidate, where you offer the ce-pov handoff; and neither — quick help, a factual question, a single-step task — answered directly.

The feature description is what the invocation carries, whether the user wrote it or a calling skill passed it. If none came, ask the user what they want to explore and do not proceed until you have one.

Setup

Run this once per invocation, before any subagent dispatch, and follow the directives it prints; where one conflicts with this skill's rules on asking questions, those win and no blocking question is asked. Run the fence exactly as written, as its own command — no piping, filtering, truncating, or batching. Its output starts === skill context and ends with CE_CONTEXT_END; one without the other means truncation, so rerun it verbatim once. A later invocation runs its own.

SKILL_DIR="<absolute path of the directory containing the SKILL.md you just read>";
NODE="$(for c in node nodejs; do command -v "$c" >/dev/null 2>&1 && "$c" -e '' >/dev/null 2>&1 && { echo "$c"; break; }; done)";
if [ -n "$NODE" ]; then
"$NODE" "$SKILL_DIR/scripts/context.mjs" || echo "context script failed; continue with the skill's normal behavior";
else
echo "no Node runtime; continue with the skill's normal behavior";
fi

Artifact Root

Resolve <root> the first time you compose or read a <root>/ path, never earlier; a scratch-only or no-repo run that touches none skips this entirely.

Resolve the CE artifact root <root> before composing any artifact path.

• Read docs_root from <repo-root>/.compound-engineering/config.yaml only (<repo-root> = git rev-parse --show-toplevel). Do not read it from config.local.yaml. Unset -> <root> is docs, exactly as before.
• Validate a set value: a repo-relative directory whose real, symlink-resolved path stays inside the repo and is neither the repo root nor under .git/. Otherwise stop with an error naming docs_root and the value -- never fall back to docs.
• Use <root> as the sole artifact location: create it if absent, compose each path as <root>/<subdir> with this skill's own subdirectory, and never also read docs.

brainstorm_output and brainstorm_model resolve by this rule instead:

Resolve ordinary CE yaml keys from the two repo files.

• Read <repo-root>/.compound-engineering/config.local.yaml, then config.yaml (<repo-root> = git rev-parse --show-toplevel). Missing files are skipped. Gitignore does not change resolution.
• Win with the first active (non-commented) value. For scalars, empty is unset; an invalid value continues to the next layer, then the skill default. For lists and maps, a present key — including an empty list or map — replaces the whole key.
• Do not use this rule for docs_root — that key is config.yaml only.

Execution Flow

Phases run in this order. Each names the files it cannot run correctly without: read them when you reach it, and never do its work from this table alone.

These rules hold without any read:

OUTPUT_FORMAT is exclusive — markdown OR HTML, never both — and pipeline mode (LFG, or any disable-model-invocation context) forces md.

On the brainstorm path the artifact contract does not change: write to <root>/plans/YYYY-MM-DD-HHMM-<type>-<topic>-plan.<md|html>, with HHMM from local wall-clock time at write; frontmatter carries artifact_contract: ce-unified-plan/v1, artifact_readiness: requirements-only, and product_contract_source: ce-brainstorm; the body is a Goal Capsule plus the Product Contract. Do not emit a Goal Launch Block or Reader Index. The non-software route writes none of this.

Do not declare the artifact written or enter Phase 4 while any check fails in the Ready for Planning Check. An improvised Phase 4 menu is the other silent failure: it surfaces options that must be hidden and passes the wrong payload downstream.

The Phase 1.1 grounding scout, the Phase 2.6 claim verifier, and the opt-in Slack researcher are tiered by task shape, never hardcoded to a model name; read references/model-tiers.md before dispatching one. Model elevation is a separate mechanism (references/reasoning-elevation.md).