Edit Diagnostics

SkillProductivity

Lets your agent diagnose failed or confusing ClipTalk video flows, like stuck planning or subtitle issues.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Edit Diagnostics skill

About this skill

Diagnoses failed or confusing ClipTalk Agent flows, including missing content, stale task state, wrong aspect, reused covers, stuck planning, short clips, subtitle issues, and export readiness.

What this skill tells your AI

The instructions your AI receives, as published by gml-mmgroup/cliptalk in skills/cliptalk-edit-diagnostics/SKILL.md and read by ahel’s review.

Explain why an Agent workflow failed or looks wrong.

  • Inspect current task status, active plan, failed steps, output versions, source scope, evidence, timeline, cover, subtitles, and delivery previews.
  • Prefer concrete causes over generic retry language.
  • Distinguish missing source evidence, duration infeasibility, stale task state, wrong output selection, unavailable preview, and formal export not yet approved.
  • Return actionable next steps without changing media state.

Signals

GitHub stars
128
Forks
9
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
cliptalk-edit-diagnostics
Source
github.com/gml-mmgroup/cliptalk