SkillsAdd

smithery/fall4knight

yanhu-run-pipeline

Run the local pipeline end-to-end on a given video and produce overview.md, timeline.md, highlights.md with artifact links.

Installation

$ npx skills add smithery/fall4knight --skill yanhu-run-pipeline
View on skills.sh ↗ Website ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

bigquery-pipeline-audit Similar name
github/awesome-copilot

Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Retu…

8.8K installs
creating-ec2-image-builder-pipeline Similar name
aws/agent-toolkit-for-aws

Creates a complete EC2 Image Builder pipeline that builds a custom AMI with pre-installed softw…

4K installs
azure-pipelines Similar name
microsoft/vscode

Use when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds…

2.8K installs
recruiting-pipeline Similar name
anthropics/knowledge-work-plugins

Track and manage recruiting pipeline stages. Trigger with "recruiting update", "candidate pipel…

2.6K installs
pipeline-review Similar name
anthropics/knowledge-work-plugins

Analyze pipeline health — prioritize deals, flag risks, get a weekly action plan. Use when runn…

2.5K installs
tao-run-automl-deft-pipeline Similar name
nvidia/skills

Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Pha…

1.5K installs
More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 690 B
  • docs SUMMARY.md 149 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

When invoked, do:

  1. Confirm input video path and session_id naming.
  2. Run CLI steps in order: ingest -> segment -> extract -> understand(asr/vision if configured) -> compose.
  3. Verify outputs exist and links resolve:

- sessions/<sessionid>/manifest.json - sessions/<sessionid>/timeline.md - sessions/<session_id>/highlights.md

  1. If any step fails, diagnose with minimal edits and re-run only the failed step.

Rules:

  • Never delete sessions/ outputs.
  • Prefer incremental reruns (cache by segment hash).