Go loop
Close the AI media iteration loop autonomously. Generate → verify via quality gate → auto-regen items below threshold → build composite → commit → notify. Use whenever the user finishes a generation batch, says "go", "go loop", "ship it", "close the loop", "run the loop", or asks to automate the generate-verify-regen-commit cycle for AI images or video. Even when the user just says "finish this batch", "we're done generating", or appends /go-loop to any prompt, trigger this skill to close the loop properly without babysitting. Applies Boris Cherny's /go pattern to AI media pipelines.From its SKILL.md
npx -y skills add LuisHiluy/claude-code-pipeline-skills --skill go-loopAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
4.1 KB, 935 tokens by cl100k_base, as published. Nobody here has run it
/go-loop — Iteration Loop Closer
Boris Cherny's /go pattern applied to AI media pipelines: when invoked, Claude tests its own work end-to-end, simplifies, commits, and pings you. No babysitting.
The Loop
GENERATE → VERIFY → [regen if FAIL, max 2 passes] → COMPOSITE → COMMIT → NOTIFY
When to Invoke
Invoke at the end of any generation task. Safe to chain after batch generators, direct API calls, or MCP tool calls.
Example prompts:
regen shot-06 with updated prompt /go-loopgenerate remaining CGI shots using approved refs /go-looptry shot-08 variants for energy match /go-loop
Execution
Step 1 — Verify what was just generated
Run your verification script (see the verify skill for a CLIP-based implementation):
python3 scripts/verify.py <ITEM_ID> --json
Read the verdict JSON. If Claude just generated multiple items, iterate.
Step 2 — Regen if FAIL (max 2 passes)
For any item with verdict FAIL:
- Look at
failed_metrics— targeted fix per metric:characterfail → ensure character refs are passed to the generatorpalettefail → check world/palette assignment, enforce palette hint in promptprompt_matchfail → revise prompt wording, tighten focal lengthcompositefail → cross-check frame selection
- Regen via same path. Do NOT burn credits if a prompt fix alone would resolve.
- Re-verify. If still FAIL after 2 regens → surface to user, do NOT continue loop.
Step 3 — Build composite
python3 scripts/assemble.py --composite <ITEM_ID>
Step 4 — Simplify (optional)
Run /simplify on any supporting code Claude wrote (prompt builders, batch scripts, helper utilities). Skip for pure generation work.
Step 5 — Commit
Summary commit with:
- Items touched (IDs)
- Pre/post quality scores
- Regen count per item
- References used
Commit message format:
<item-ids>: <short description>
Quality deltas: shot-06 0.31→0.42 (GOOD), shot-08 0.28→PASS, shot-11 FAIL after 2 regens
Co-Authored-By: Claude <[email protected]>
Step 6 — Notify (optional)
Send summary to the user via your preferred channel (Telegram, Slack, email). Format:
/go-loop complete
<N> items verified, <M> regenned
Results:
shot-06: GOOD (0.42)
shot-08: PASS (0.31)
shot-11: FAIL after 2 passes — needs manual review
Composite: runs/composites/latest.png
Commit: <hash>
Only send if the channel is configured. Otherwise skip silently.
Invariants (don't break these)
- Never regen more than 2x per item per invocation. Burns credits; if still failing, the prompt or reference is the issue — hand back to user.
- Never skip verification. The whole point is the tight loop. No verification = no /go.
- Always pass references to the generator. Double-check before regen.
- Respect file locks. If
/lockscenesis active, respect the guard. - If FAIL after 2 passes: stop, summarize, ask. Don't auto-escalate to a different generator without user input.
Output format to user
When /go-loop completes, print a compact summary (no headers, no celebration):
shot-06 GOOD 0.42 (1 regen)
shot-08 PASS 0.31 (0 regens)
shot-11 FAIL — 2 regens, character metric stuck at 0.48
composite: runs/composites/2026-04-16.png
commit: a7b3c9d
notified
Related Skills
verify— the underlying quality gateclip-feedback— for single-clip intent analysisnb2-batch— for batch-generating reference gridslockscenes— for locking approved items during assembly
What ships with it: 1 file
577 B alongside SKILL.md
- README.md577 B