Browse published AI skills maintained by Obsidian-Owl. Compare skill descriptions and follow each source repository for setup instructions.
Indexed skills
32Repository stars across indexed skills
0Repository forks
275Average repository stars per indexed skill
0Repository stars may repeat across skills from the same repository.
Decompose high-level design documentation into detailed Arc42 architecture documentation. Use when the user asks to create architecture documentation, generate Arc42 documents, analyze a codebase for architectu...
Research architecture decisions and create Architecture Decision Records (ADRs). Use when facing complex technical choices requiring deep research, options analysis, and formal documentation. Treats user as CTO...
Analyses Arc42 architecture documentation and decomposes it into well-sized Epics suitable for Speckit implementation. Use when breaking down architecture into implementable work, creating epic catalogues from...
A test skill for validation
Review test quality before PR - semantic analysis of test design for agentic code. Checks test type appropriateness (unit vs VCR vs evals), ADR-0011/0012 compliance, and Constitution alignment. Run as Level 2 r...
Guides test type selection for agentic code. Use when writing tests for LLM interactions, tool implementations, or behavioral quality. Covers unit tests, VCR integration tests, and TruLens evals per ADR-0011/00...
Implement ALL tasks in the current epic until completion (auto-loop, no confirmation). Use when batch processing tasks, automating implementation, or running unattended task completion.
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
Validate this Epic branch against main and detect contract changes before PR creation
ALWAYS USE when building semantic layer, working with metrics/dimensions, or integrating dbt with Cube consumption APIs. Use IMMEDIATELY when working with Cube REST API, GraphQL queries, or Postgres wire protoc...
Second-level architectural review validating alignment to target architecture (docs/)
ALWAYS USE when working with dbt models, SQL transformations, tests, snapshots, or macros. Use IMMEDIATELY when editing dbt_project.yml, profiles.yml, or creating SQL models. MUST be loaded before any transform...
ALWAYS USE when working with Pydantic models, BaseModel, Field, validators, or data contracts. MUST be loaded before creating any Pydantic schemas, configuration classes, or API contracts. Provides v2 syntax va...
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
Review test quality before PR - semantic analysis of test design, not just linting
ALWAYS USE when working with Helm charts, Kubernetes deployments, kubectl commands, pod debugging, or container logs. Provides context-efficient strategies for chart development, K8s troubleshooting, and log an...
Track complex, multi-session work with dependency graphs using beads issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For...
ALWAYS USE when building data lakehouse with DuckDB compute, configuring dbt-duckdb with Polaris plugin, or designing catalog-first architecture in floe-platform. Use IMMEDIATELY when reading/writing Iceberg ta...
ALWAYS USE when writing tests, test fixtures, test utilities, or debugging test failures. MUST be loaded before creating pytest tests, integration tests, or test infrastructure. Provides test quality patterns,...
Create or update the feature specification from a natural language feature description.
Generate a custom checklist for the current feature based on user requirements.
Convert tasks.md to Linear issues and reconcile completed work bidirectionally.
ALWAYS USE when working with Iceberg table storage, ACID transactions, or time-travel queries. Use IMMEDIATELY when creating/loading Iceberg tables, implementing schema evolution, querying historical snapshots,...
Implement the next ready task from Linear issue tracker with SpecKit integration. Use when implementing tasks, working on Linear issues, or continuing feature development.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.