Json

continuous-learning automatically extracts reusable patterns from Claude Code sessions and saves them as learned skills. It uses a Stop-hook flow, supports configurable thresholds in config.json, and is best for skill authors, repo maintainers, and power users who want a practical continuous-learning guide for session-end capture.

Firecrawl Automation helps Claude Code run Firecrawl through Composio to scrape pages, crawl sites, extract structured data, batch process URLs, and map site structures with scoped, credit-aware workflows.

tc-tracker helps AI coding sessions create, update, validate, resume, and close repository-local Technical Change records in docs/TC/. Use it for structured issue-like change tracking, lifecycle status, test evidence, and handoff notes.

agent-workflow-designer helps plan production multi-agent workflows with pattern selection, handoff contracts, retries, timeouts, context limits, and quality gates. Use it to design sequential, parallel, router, orchestrator, or evaluator flows and generate starter skeletons with scripts/workflow_scaffolder.py.

code-tour helps agents create VS Code CodeTour .tour files for persona-targeted repository walkthroughs with real file and line anchors. Use it for onboarding, architecture tours, PR reviews, RCA paths, contributor guides, and Technical Writing workflows where the output should be a navigable .tours artifact, not source edits.

procurement-optimizer helps Procurement Operations run SaaS audits, UNSPSC-aligned spend categorization, Pareto and YoY review, purchasing-cycle bottleneck analysis, and risk-aware supplier consolidation with tier-1 break-glass safeguards.

json-canvas helps create and edit valid .canvas files for Obsidian-style boards, with correct nodes, edges, IDs, coordinates, groups, and references.

obsidian-bases helps create and edit Obsidian .base files with filters, formulas, summaries, and table, cards, list, or map views. Best for turning note metadata into working knowledge base views, with YAML validation and function-reference guidance from the skill files.

baoyu-imagine is a multi-provider image generation skill with a typed CLI, mandatory EXTEND.md setup, reference image support, aspect ratio controls, and batch runs across OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream, and Replicate.

dummy-dataset generates realistic test data in CSV, JSON, SQL, or Python script form. It helps with mock datasets, demos, database seeding, QA, and data cleaning by letting you define columns, row counts, and constraints for believable sample records.

Perform cohort-analysis on user retention, engagement decay, and feature adoption by cohort. This cohort-analysis skill is built for Data Analysis workflows that need validation, calculation, visualization, and clear insights from structured user behavior data.

Use the huggingface-datasets skill for Hugging Face Dataset Viewer API workflows to validate datasets, resolve splits, preview and paginate rows, search text, apply filters, and fetch parquet links or statistics. It is a practical huggingface-datasets guide for read-only dataset exploration.

sarif-parsing is a post-scan skill for reading, filtering, deduplicating, summarizing, and converting SARIF 2.1.0 results from tools like CodeQL and Semgrep. Use it when you already have scan output and need clear parsing, aggregation, or CI/CD-ready transformation. It is not for running scans.

interpreting-culture-index helps interpret Culture Index surveys, profile exports, and related hiring or coaching notes. Use this interpreting-culture-index skill for role fit, team dynamics, burnout risk, candidate debriefs, onboarding plans, and conflict mediation. It emphasizes arrow-relative reading, anti-pattern checks, and practical outputs for data analysis and decision support.

plugin-forge helps Claude Code plugin authors scaffold plugin structure, manage `plugin.json` and marketplace metadata, add components like commands or skills, test locally, and keep versions synchronized with the included helper scripts and workflow references.

The openapi-to-typescript skill helps you convert OpenAPI 3.0 JSON or YAML specs into TypeScript interfaces, endpoint request and response types, and runtime type guards. Use it when you already have a valid API spec and want a structured workflow for validation, generation, and saving output such as `types/api.ts`.

vega is a chart-authoring skill for turning structured data into interactive, data-driven visualizations with Vega-Lite for most cases and Vega for advanced layouts. Use it for bar, line, scatter, heatmap, area, stacked, and multi-series charts when you have real data fields and need valid JSON specs.

canvas creates JSON Canvas diagrams with free positioning and explicit x/y coordinates. Use it for mind maps, knowledge graphs, concept maps, planning boards, and other Diagramming workflows where spatial layout matters more than sequence. It is not the right choice for flows or data charts. Use the canvas skill when you need editable nodes, links, and structured layout.

obsidian-bases helps create and edit valid Obsidian .base files with YAML views, filters, formulas, properties, and summaries. Best for Knowledge Bases workflows where you need table, cards, list, or map views with less schema guesswork.

json-canvas helps agents create and edit valid .canvas files for Obsidian and other JSON Canvas apps. Use it to generate structurally correct nodes, edges, groups, positions, and layering for mind maps, flowcharts, and lightweight diagramming workflows.

veo-3.2-prompter is a prompt-design skill for Google Veo 3.x workflows. It helps turn mixed assets and rough intent into a structured JSON prompt with reference-role mapping, recommended parameters, and practical guidance for install, usage, and Veo-ready prompt writing.

seedance-2.0-prompter helps turn multimodal Seedance 2.0 assets into structured prompts with clear roles, @asset syntax, and reusable templates for install, setup, and practical usage.

read-file helps an agent read and inspect CSV, JSON, Parquet, Avro, Excel, SQLite, spatial files, or remote URLs with DuckDB. Use it to preview rows, check schema, profile data, and answer what’s in this file. It’s best for read-file usage on real data artifacts, not source code.

The query skill runs DuckDB queries against an attached database or directly against files. It accepts SQL or natural-language questions, supports session and ad-hoc modes, and is useful for Data Analysis, quick checks, and iterative query work with DuckDB Friendly SQL.