---
title: "toolkit-workflows"
description: "Research decisions, verify software, create engineering diagrams, and maintain agent workflows."
canonical: https://agentpluginsdirectory.com/plugins/toolkit-workflows
last-updated: 2026-10-21
---

# toolkit-workflows
Research decisions, verify software, create engineering diagrams, and maintain agent workflows.
- Slug: toolkit-workflows
- Publisher: Brian Li
- Repository: https://github.com/BrianLiDesign/blidesign-ai-toolkit
- Manifest: plugins/toolkit-workflows/plugin.json
- Version: 0.4.0
- License: MIT
- Category (editorial): other
- Skills: 12 (architecture-diagrams, dependency-graphs, editable-diagrams, engineering-diagrams, engineering-visuals, find-docs, pr-closeout, project-check, release-acceptance, research-and-recommend, security-check, toolkit-smoke-test)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-09-10
- Repository last pushed: 2026-10-19
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/toolkit-workflows
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- architecture-diagrams: Explain or propose software architecture using C4 context, container, and component views, including system boundaries and before/after designs. Applies regardless of the chosen renderer.
- dependency-graphs: Build evidence-backed graphs of module imports, package dependencies, build relationships, or coupling, using Graphviz DOT when appropriate. Preserve edge meaning and distinguish static dependencies from runtime calls.
- editable-diagrams: Create or revise editable draw.io diagrams when manual layout or a.drawio deliverable is required, preserving object identities and validating both the source and exported view.
- engineering-diagrams: Create or revise software flowcharts, API sequence diagrams, state machines, and entity-relationship diagrams using Mermaid by default, with notation-specific checks and editable source.
- engineering-visuals: Route engineering visual requests to specialist skills for behavior diagrams, C4 architecture, dependency graphs, or editable draw.io diagrams. Use proactively when a visual materially clarifies development work.
- find-docs: Fetch current library, framework, SDK, API, CLI, or cloud-service documentation with Context7 for syntax, configuration, setup, migration, and technology-specific debugging.
- pr-closeout: Finish an authorized GitHub PR through review remediation, CI, metadata, merge, and post-merge verification. Use for PR closeout; keep assessment-only requests read-only.
- project-check: Discover and run a project's verification commands, recording commit-specific results and missing checks. Use to validate a change or establish the repository's verification gate.
- release-acceptance: Verify a deployed release against public behavior and persistence requirements, recording inspectable evidence and cleaning up owned test data.
- research-and-recommend: Research an open question or unfamiliar implementation, compare viable approaches against the user's constraints, and recommend the best fit using primary sources and applicable standards. Use when the user wants evidence-backed options and a recommendation; a single documentation lookup belongs to…
- security-check: Assess security implications of a software change using project scanners, dependency and secret checks, and changed trust boundaries. Use for requested security checks or changes affecting authentication, permissions, untrusted input, or sensitive data.
- toolkit-smoke-test: Verify a toolkit update across installed agent hosts using skill discovery, installed versions, MCP startup, and harmless tool calls. Use after installation or for cross-host release checks.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.