Agent Skills by Tacuchi
Showing 19 vetted skills indexed across 2 GitHub repositories.
workflow
Explain the agent-workflow harness structure, usage, and skills.toml binding cascade.
research
Create read-only research sessions and output ANALYSIS-FILE.md and CONCLUSIONS.md.
tools
Generate CLI tool code and documentation under docs/tools within plan-exec-loop workflows.
coding-standards
Enforce SOLID, naming, and DRY standards across Java/Spring, Angular/TypeScript, and Node projects.
diagrams
Generate architecture diagrams from system models using C4, Structurizr DSL, Mermaid, and PlantUML.
ui-spec
Generate structured Screen JSON and Markdown render from UI requirements.
testing
Determine unit, integration, or full testing level based on detected stack.
git
Verify the work branch and require approval before executing Git commits.
writing
Enforce six writing rules for technical prose in agent-workflow outputs.
sql
Manage versioned SQL scripts with read-only database access during migrations.
export-manuals
Consolidate workspace sessions and touched sources into structured operator manuals.
export-scripts
Consolidate pending SQL migrations into a single documented bundle with rollback.
export-diagrams
Generate Mermaid architecture diagrams from code and plan-doc deltas, optionally Structurizr DSL via --engine flag, into docs/diagrams/
export-reports
Consolidate workspace session data into a unified executive report.
plan-exec-loop
Execute multi-phase AI deployment plans with resumable sessions and git governance.
spec-refine-loop
Refine ambiguous draft specs into precise, testable requirements via a gap-driven loop.
quick-loop
Apply minimal code edits directly from user prompts in lightweight sessions.
plan-new-loop
Transform a refined spec into a structured PPP-plan.md document.
playstore-android-native
Prepare native Android projects for Google Play Store release with signing and AAB verification.