Multi-Skill Chain Orchestration
Paste the following prompt into your AI chat to install this skill:
Please install @user_800d68d6/skill-sub into my AI assistant according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem Solved
When multiple skills must run in sequence, pass data, or wait for manual approval, calling them one by one does not express the whole workflow. skill-sub targets reusable multi-skill call chains: it captures steps, dependencies, branches, loops, and gap handling so the model does not need to improvise orchestration every time.
How It Works
It parses user intent, searches candidate steps, selects steps, marks milestones, validates I/O, and generates a structured execution plan with serial and parallel markers. Key capabilities include:
- Chain management: create, query, update, and delete chains.
- Gates and validation: hard gates, blueprint fingerprint checks, and private baseline checks before execution.
- Adhesion points: mark gaps that skills cannot automate, with manual, auto, or skip resolution.
- Historical chain reuse: match similar intents to existing chains and reduce repeated creation.
Boundaries
Best suited to stable, dependency-driven, reusable workflows; not suited to single-skill tasks, one-off operations, independent parallel tasks, or highly dynamic flows. Creation still must respect hard limits on step count, dependency depth, and adhesion ratio.
Use Cases
- Chain data cleaning, validation, and report generation skills into a reusable workflow with conditional backfill.
- Check step blueprint fingerprints and private chain baselines before execution to catch interface drift.
- Mark manual approval gaps as adhesion points in release workflows and configure manual fallbacks.
- Reuse similar historical chains for recurring multi-skill tasks instead of replanning steps each time.
Best For
- Data engineers who need to solidify multi-step data pipelines into reusable skill chains.
- Platform engineers maintaining release or approval workflows and configuring manual fallbacks for non-automatable steps.
- Agent maintainers managing multiple AI skill interfaces and validating blueprint fingerprints and baseline drift before runs.
- Automation leads who want to turn recurring business workflows into chains and reuse similar historical chains.
Related Skills
A free matrix publishing assistant for Skill developers, guiding distribution to Tencent SkillHub, XiaLiao, XiaYou SkillHub, GitHub, and ClawHub with create, update, and delete safeguards.
A guide for writing Seedance 2.0 video prompts, covering @ references, camera moves, time segments, audio direction, and common pitfalls.
Collects daily conversations, task logs, and errors, then runs a nine-module review to surface blind spots, generate actions, and update memory.
Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.