cleargate

Use to orchestrate the five-dispatch sprint loop end-to-end — Architect → QA-Red → Developer → QA-Verify → Reporter — across one ClearGate sprint. Activates from sprint kickoff (preflight + cut sprint branch + state init) through per-story execution (worktree → dev → QA → flashcard gate → merge) into walkthrough and Gate-4 close. Triggers: SessionStart banner mentioning an active sprint; explicit user phrases "start the sprint", "run the sprint", "execute the sprint", "begin sprint execution", "kick off SPRINT-NN", "run STORY-NNN-NN"; CLI directives ending with `→ Load skill: sprint-execution`. The skill does not draft work items, run triage, or manage planning — those stay in always-on CLAUDE.md surface.

Render or serve the branded sprint-progress dashboard (`cleargate sprint dashboard`). Use when a human wants a visual, point-in-time or live view of the active sprint's story states, milestone/wave grouping, token spend by agent, worktrees, and dispatch reports. Triggers: explicit user phrases "show me the dashboard", "open the sprint dashboard", "sprint progress view"; automatically opened (best-effort) after `cleargate sprint init` succeeds. Not for CI/automation — this is a human-facing visual surface, not a data source other tooling should scrape (use `state.json` / `token-ledger.jsonl` directly for that).

Append-only project lesson log at .cleargate/FLASHCARD.md. Use BEFORE starting non-trivial work to read past gotchas ("check" mode). Use WHEN you (a) hit a surprise, (b) found the winning path after a non-trivial task succeeded, or (c) were corrected by the user — record a one-liner for future agents ("record: <text>" mode). One-liners only; tag with #schema/#auth/#test-harness/etc. Also triggers on phrases: "turns out", "unexpected", "gotcha", "wasted time on", "starting work on", "before implementing", "user pushed back", "prefer X over Y", "winning path", "after several attempts", "the recipe that worked".