Oscar
Community@oskrgab · Houston, USA
Senior Reservoir Engineer | Python Developer | Data Science
Agent Skills by Oscar
Showing 13 vetted skills indexed across 1 GitHub repositories.
oskrgabsetup-matt-pocock-skills
Configures issue tracker, triage labels, and domain docs for engineering skills.
oskrgabhf-cli
Manages Hugging Face Hub models, datasets, spaces, jobs, and repos via the hf CLI.
oskrgabimprove-codebase-architecture
Identifies shallow modules and proposes deepening refactors to improve codebase testability and navigability.
oskrgabtriage
Triage GitHub issues through a label-driven state machine with agent briefs.
oskrgabdiagnose
Diagnose hard bugs and performance regressions through a structured reproduce-hypothesise-fix workflow.
oskrgabto-issues
Breaks plans and specs into vertical-slice issues on a project issue tracker.
oskrgabzoom-out
Generates a high-level map of relevant modules and callers for unfamiliar code areas.
oskrgabwrite-a-skill
Create new agent skills with structured SKILL.md files and bundled resources.
oskrgabgrill-with-docs
Interviews users to stress-test plans against domain glossaries and records decisions in CONTEXT.md and ADRs.
oskrgabcaveman
Compresses AI responses by removing filler words while preserving technical accuracy.
oskrgabtdd
Guides test-driven development using the red-green-refactor loop with behavior-focused tests.
oskrgabgrill-me
Interviews the user question-by-question to stress-test plans and design decisions.
oskrgabto-prd
Generates a PRD from conversation context and publishes it to the project issue tracker.
Frequently Asked Questions About Oscar
FAQPage SchemaWhat tasks can I accomplish with oskrgab's skills?▼
You can triage issues through a state machine, turn conversations into PRDs, break plans into vertical-slice issues, run test-driven red-green-refactor cycles, diagnose bugs and performance regressions, stress-test plans against ADRs, and manage Hugging Face Hub models, datasets, spaces, and Inference Endpoints.
Who are these skills designed for?▼
Software engineers and technical leads managing issue trackers, writing PRDs, practicing TDD, or refactoring codebases, plus ML practitioners working with the Hugging Face ecosystem. The maintainer is a senior reservoir engineer and Python developer with a data science background.
How do I set up and run these skills in my repository?▼
Run setup-matt-pocock-skills first: it writes an Agent skills block into AGENTS.md or CLAUDE.md and creates docs/agents/ so downstream skills know your issue tracker, triage label vocabulary, and domain doc layout. Then invoke to-issues, to-prd, triage, diagnose, tdd, or zoom-out as needed.
What prerequisites or dependencies do these skills require?▼
Skills expect a repository with an issue tracker (GitHub or local markdown), triage labels, and domain docs such as CONTEXT.md and docs/adr/ for architecture-informed features. The hf-cli skill requires the Hugging Face Hub hf command line, replacing the deprecated huggingface-cli.
Can these skills reduce token usage or improve agent communication?▼
Yes. The caveman skill cuts token usage roughly 75% by dropping filler, articles, and pleasantries while preserving technical accuracy, triggered by 'caveman mode' or /caveman. The zoom-out skill forces broader context when you are unfamiliar with a code section.