← ClaudeAtlas

tq-forge-queuelisted

Show queued forge work — intents deferred while the halt flag was set, plus items flagged "needs_manual_review" because their score stayed below 7 after a refine attempt. Lets you remove, reorder, or run the next item. Use when asked for "/tq-forge-queue", "what's queued", "show pending forges", or "process the queue".
tanishq286/tq-forge · ★ 1 · AI & Automation · score 70
Install: claude install-skill tanishq286/tq-forge
# /tq-forge-queue — view + manage deferred forge work ## When to use `/tq-forge` and `/tq-forge-skill` queue the requested intent (instead of running it) when `$TQ_FORGE_HOME/halt.flag` is set, and flag artifacts as `needs_manual_review` when scoring stays <7. This skill is the cockpit for both: inspect what's pending, drop entries you don't want, and run the next one when you're ready. ## Procedure ```bash export TQ_FORGE_HOME="${TQ_FORGE_HOME:-$HOME/.tq-forge}" S="${CLAUDE_PLUGIN_ROOT:-${TQ_FORGE_HOME:-$HOME/.tq-forge}/install}/scripts" source "$S/common.sh" && tq_ensure_home ``` 1. **Render both lists.** ```bash bash "$S/forge-checkpoint.sh" status ``` Two arrays matter: `queue` (intents waiting to run) and `needs_manual_review` (slugs scored <7). 2. **Ask the user what to do next** via AskUserQuestion: - **Run next** — pop item #1 and process it via the `/tq-forge` procedure. - **Run all** — loop through every queued intent. Stop if the halt flag re-appears. - **Drop one** — prompt for the index, remove it. - **Clear queue** — drop all `queue` entries (keeps `needs_manual_review`). - **Open review** — for a `needs_manual_review` slug, print its sandbox path so the user can edit by hand, then `/tq-forge-test` it. 3. **Run next** pops atomically: ```bash INTENT="$(bash "$S/forge-checkpoint.sh" pop)" test -n "$INTENT" && echo "Processing: $INTENT" # then follow /tq-forge ``` 4. **Run all** loops, checking the halt