/ce-compound

name: ce-compound
description: Document a recently solved problem as a durable repo learning, or capture project vocabulary in CONCEPTS.md. Use when capturing a learning after work.
argument-hint: "[optional: brief context] [mode:non-interactive] [depth:lightweight|full]"

/ce-compound

Coordinate multiple subagents working in parallel to document a recently solved problem.

Setup

Run this once at the start of this invocation, before any subagent dispatch, and follow the directives it prints — except where one conflicts with this skill's own rules on asking the user questions, whether those rules are scoped to a non-interactive mode or apply in every mode, in which case this skill's rules win and no blocking question is asked. Run the fence exactly as written, as its own command: do not pipe or filter it (no `head`, `tail`, or `grep`), do not truncate its output, and do not bundle it into a batch with other commands. Its output opens with a `=== skill context` header and ends with `CE_CONTEXT_END`; if you received one of those lines without the other, the output was truncated — rerun the fence verbatim once. That recovery is the only rerun: otherwise do not rerun it within the same invocation; a later invocation of this or any other skill runs its own. If no Node runtime is available the skill proceeds unchanged.

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

Purpose

Captures problem solutions while context is fresh, creating structured documentation in `<root>/solutions/` with YAML frontmatter for searchability and future reference. Uses parallel subagents.

**Why "compound"?** Each documented solution compounds your team's knowledge. The first time you solve a problem takes research. Document it, and the next occurrence takes minutes. Knowledge compounds.

Usage

/ce-compound                            # Document the most recent fix
/ce-compound [brief context]            # Provide additional context hint
/ce-compound mode:non-interactive              # Non-interactive run for automations
/ce-compound mode:non-interactive [context]    # Non-interactive run with context hint
/ce-compound mode:non-interactive depth:lightweight [context] # Lower-overhead non-interactive run
/ce-compound mode:non-interactive depth:full [context]        # Full non-interactive run
# mode:headless is a deprecated alias for mode:non-interactive (same depth rules)

**One learning per run.** The workflow's grounding, overlap detection, and cross-referencing all assume a single solved problem. When a session produced multiple distinct learnings, run the skill once per learning, sequentially — each run grounds fresh against the tree. Do not batch several learnings through one run and stitch cross-references between the drafts afterward; drafting-context numbering ("Learning 3") leaking into written docs is the failure this rule prevents.

CONCEPTS.md bootstrap requests

If invoked specifically to create or bootstrap `CONCEPTS.md` from scratch rather than to document a solved problem, do not run the normal phases — `ce-compound` populates `CONCEPTS.md` only as a side effect of documenting a real learning (it seeds the *learning's area*, not the whole repo; see Phase 2.4). Repo-wide concept-map creation is `ce-compound-refresh`'s job. Redirect a standalone bootstrap request to `ce-compound-refresh` (which asks whether to build the concept map or run a refresh cycle), then exit.

Mode Detection

Enter non-interactive mode when **either** holds: the arguments you were invoked with contain the `mode:non-interactive` token or its deprecated alias `mode:headless`, **or** the invocation makes non-interactive intent unmistakable — a caller or standing instruction asking to run `ce-compound` "headless", "non-interactively", "unattended", or "without prompts/questions". `mode:non-interactive` is the explicit form; `mode:headless` is a **deprecated alias** for the same mode (both together is not a conflict). A clear natural-language request for a non-interactive run is equivalent. Bare "automatically" or "auto-run" is **not** on its own a non-interactive signal — it speaks to *invoking* the skill, not to suppressing its prompts — so an ambiguous or absent signal defaults to interactive. Tokens starting with `mode:` or `depth:` are flags, not context — strip them before treating the remainder as the brief context hint.

Depth is an explicit non-interactive-only selector. In non-interactive mode, accept at most one depth token: `depth:lightweight` routes directly to Lightweight Mode, while `depth:full` routes to Full Mode with its automatic session-history probe. `mode:non-interactive` without a `depth:` token remains backward compatible and runs Full Mode (same for the deprecated `mode:headless` alias). Non-interactive lightweight asks no blocking questions and launches no subagents. If the invocation contains an unknown `depth:` token, multiple `depth:` tokens, or a `depth:` token without non-interactive intent, do not guess; emit the non-interactive failure report with the reason and end with `Documentation skipped`.

| Mode | When | Behavior | |------|------|----------| | **Interactive** (default) | No non-interactive token or clear non-interactive intent | Auto-pick Full vs Lightweight and report the choice; run session history as an automatic probe (Full only); prompt for Discoverability Check consent; end with a plain summary (no "What's next?" menu) | | **Non-interactive** | `mode:non-interactive` or deprecated alias `mode:headless` present, or the invocation makes non-interactive intent unmis