workflow-bridge — pipeline phase automation workflow-bridge, community, pipeline phase automation, ide skills, deterministic continuation instructions, context compaction, plan mode handoff, technical discussion skills, technical specification skills, silent processing mode

v1.0.0

About this Skill

Ideal for AI Agents like Cursor and AutoGPT needing seamless pipeline phase automation and efficient workflow management. workflow-bridge is a skill that enables deterministic continuation instructions for pipeline phase automation in AI agents.

Features

Enters plan mode with deterministic continuation instructions
Discovers next pipeline phase and creates plan mode handoff
Survives context compaction for efficient workflow management
Invoked by processing skills like technical-discussion and technical-specification
Adheres to ZERO OUTPUT RULE for silent processing
Produces no output until step or reference file explicitly specifies display content

# Core Topics

leeovery leeovery
[1]
[0]
Updated: 3/13/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reviewed Landing Page Review Score: 10/11

Killer-Skills keeps this page indexable because it adds recommendation, limitations, and review signals beyond the upstream repository text.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review Locale and body language aligned
Review Score
10/11
Quality Score
57
Canonical Locale
en
Detected Body Locale
en

Ideal for AI Agents like Cursor and AutoGPT needing seamless pipeline phase automation and efficient workflow management. workflow-bridge is a skill that enables deterministic continuation instructions for pipeline phase automation in AI agents.

Core Value

Empowers agents to automate pipeline phases using deterministic continuation instructions, ensuring context compaction and efficient workflow management through technical skills like technical-discussion and technical-specification, while supporting protocols for plan mode handoffs.

Ideal Agent Persona

Ideal for AI Agents like Cursor and AutoGPT needing seamless pipeline phase automation and efficient workflow management.

Capabilities Granted for workflow-bridge

Automating pipeline phase handoffs
Generating plan mode instructions for context compaction
Ensuring seamless workflow transitions between phases

! Prerequisites & Limits

  • Requires processing skills like technical-discussion and technical-specification
  • Survives context compaction but may require specific phase configurations

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is workflow-bridge?

Ideal for AI Agents like Cursor and AutoGPT needing seamless pipeline phase automation and efficient workflow management. workflow-bridge is a skill that enables deterministic continuation instructions for pipeline phase automation in AI agents.

How do I install workflow-bridge?

Run the command: npx killer-skills add leeovery/agntc/workflow-bridge. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for workflow-bridge?

Key use cases include: Automating pipeline phase handoffs, Generating plan mode instructions for context compaction, Ensuring seamless workflow transitions between phases.

Which IDEs are compatible with workflow-bridge?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for workflow-bridge?

Requires processing skills like technical-discussion and technical-specification. Survives context compaction but may require specific phase configurations.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add leeovery/agntc/workflow-bridge. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use workflow-bridge immediately in the current project.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

workflow-bridge

Install workflow-bridge, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Enter plan mode with deterministic continuation instructions.

This skill is invoked by processing skills (technical-discussion, technical-specification, etc.) when a pipeline phase concludes. It discovers the next phase and creates a plan mode handoff that survives context compaction.

ZERO OUTPUT RULE: Do not narrate your processing. Produce no output until a step or reference file explicitly specifies display content. No "proceeding with...", no discovery summaries, no routing decisions, no transition text. Your first output must be content explicitly called for by the instructions.

Instructions

This skill receives context from the calling processing skill:

  • Topic: The topic name
  • Work type: greenfield, feature, or bugfix
  • Completed phase: The phase that just concluded

Step 1: Run Discovery

!.claude/skills/workflow-bridge/scripts/discovery.sh

If the above shows a script invocation rather than YAML output, the dynamic content preprocessor did not run. Execute the script before continuing:

bash
1.claude/skills/workflow-bridge/scripts/discovery.sh

The output contains three sections: features:, bugfixes:, and greenfield:. Use the known work type and topic from the calling context to extract the relevant data:

If work type is "feature"

Find the topic entry under features: > topics: and extract its next_phase.

If work type is "bugfix"

Find the topic entry under bugfixes: > topics: and extract its next_phase.

If work type is "greenfield"

Parse the greenfield: section for phase-centric state:

  • state: Counts of artifacts across all phases
  • Phase-specific file lists with their statuses

→ Proceed to Step 2.


Step 2: Route to Continuation Reference

Based on work type, load the appropriate continuation reference:

If work type is "feature"

Load feature-continuation.md and follow its instructions as written.

If work type is "bugfix"

Load bugfix-continuation.md and follow its instructions as written.

If work type is "greenfield"

Load greenfield-continuation.md and follow its instructions as written.


Notes

Feature/bugfix continuation references:

  1. Use discovery output to compute a single next_phase
  2. Call EnterPlanMode tool, write plan file with instructions to invoke start-{next_phase} with topic + work_type
  3. Call ExitPlanMode tool for user approval

The user will then clear context, and the fresh session will invoke the appropriate start-* skill with the topic and work_type provided, causing it to skip discovery and proceed directly to validation/processing.

Greenfield continuation is interactive — greenfield is phase-centric with multiple actionable items, so there is no single next phase. The reference displays state, presents a menu of choices, waits for user selection, then enters plan mode with that specific choice. The plan mode content is deterministic (same as feature/bugfix) once the user has chosen.

Related Skills

Looking for an alternative to workflow-bridge or another community skill for your workflow? Explore these related open-source skills.

View All

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

Generate customizable widget plugins for the prompts.chat feed system

149.6k
0
AI

flags

Logo of vercel
vercel

The React Framework

138.4k
0
Browser

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
Developer