execute-batchlisted

Execute one "chat" from an Implementation Strategy in this fresh session — run its stories sequentially (execute-story → run-testplan → close-out-story) with atomic per-story finalisation, a context-budget guard, and clean failure recovery; then flip the chat's executed flag so the dashboard shows it done. Use when the user invokes /tandem:execute-batch with a chat id (e.g. CHAT-01), or asks to run/execute a batch or chat from the execution-strategist's plan. Operates as Dev/QA hat. This command DOES change story status (unlike execution-strategist, which is dry-run).
DATA-AI-XYZ/Tandem · ★ 0 · AI & Automation · score 70

Install: claude install-skill DATA-AI-XYZ/Tandem

# Tandem: execute-batch (Dev/QA hat) Operate as **Dev/QA hat** in a **fresh chat**. The user has an Implementation Strategy (from `/tandem:execution-strategist`) and wants to clear one of its **chats** — a small set of stories grouped to run together — end to end, without re-warming context per story. A "chat" is the execution-strategist's batch unit (`CHAT-01`, `CHAT-02`, …). This skill runs the chat's stories **sequentially**, finalising each atomically before the next. It composes the three existing per-story skills; it does **not** re-implement their logic. ## Inputs needed - **A chat id** — e.g. `CHAT-01`. If the user didn't supply one, ask, or list the chats in the latest strategy. - **The strategy** — default to the latest `_00-Project-Management/41-Reports/EXECUTION-STRATEGY-*.json` (the structured sidecar `execution-strategist` writes). Fall back to the paired `.md` report if the JSON is absent. The user may name a specific strategy file. ## Load into context Use `Read` / `Glob`; treat missing files as "not present", never throw. - **The named chat** from the latest `EXECUTION-STRATEGY-*.json`: its `stories` (with `ready` flags), `lanes` (serial/parallel), `verify` command, `sub_agents`, and `executed` flag. - **Each story + its paired testplan** under `32-Stories/` + `33-Testplans/`. - **SOP** — `90-Standards/SOP.md` (DoR/DoD, status enum, WIP limits §5). - **The three sub-skills** this one delegates to: `execute-story`, `run-testplan`, `close-out-sto