Skills for Real Engineers. Straight from my .agents directory.
krillinai-pipeline
Agent skill fromkrillinai/OpenCreator
Use when validating or documenting a multi-stage KrillinAI CLI output plan; the current pipeline command supports dry-run planning only, not end-to-end execution.
How to install krillinai-pipeline
npx skills add krillinai/OpenCreator# or add only this skill to Claude Code: copy the folder
skills/krillinai-pipeline/
# into
~/.claude/skills/krillinai-pipeline/ (all projects)
.claude/skills/krillinai-pipeline/ (one project)
1# KrillinAI Pipeline23Use this skill to validate a requested stage plan. Run real work through the individual stage commands because non-dry-run `pipeline` execution returns `unsupported_command`.45## Plan Validation67```bash8(cd "$KRILLINAI_CWD" && "$KRILLINAI_CLI" pipeline \9 --outputs "subtitle,tts,vertical-bilingual" \10 --dry-run)11```1213## Outputs Values1415| Output | Stage |16|---|---|17| `subtitle` | Generate subtitle files |18| `tts` | Generate dubbing |19| `horizontal-bilingual` | Render landscape bilingual video |20| `horizontal-dubbed` | Render landscape dubbed video |21| `vertical-bilingual` | Render portrait bilingual video |22| `vertical-dubbed` | Render portrait dubbed video |23| `cover` | Generate cover |2425The dry-run validates output names and returns a successful pipeline-stage JSON response. It does not execute stages or write a task manifest.2627## Execute The Plan2829Map the validated outputs to `subtitle`, `tts`, `render-horizontal`, `render-vertical`, and `cover`. Run each required command independently and use the same absolute `--workdir`.3031## Recovery Strategy3233- If `subtitle` succeeds and render fails, rerun only render with the same `--workdir`.34- If TTS fails, keep subtitle outputs and rerun `tts` after fixing provider config.35- Read `krillinai_manifest.json` before rerunning to avoid repeating expensive work.3637## Verification3839- Require terminal JSON with `"ok": true` for dry-run validation.40…
Excerpt shown under the repository's Apache-2.0 license.
More skills in OpenCreator
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
