| Internal template for creating or refactoring a skill into the repository's reference-first shape.
npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill _template_reference_first
This package is the default starting point for new or refactored skills in this repo.
It demonstrates the intended split of responsibilities:
SKILL.md routes the workflowreferences/ holds method, judgment, and exemplarsassets/ holds machine-readable contractsscripts/ handles deterministic execution onlyUse it as a shape to copy and customize, not as a domain-specific skill.
SKILL.mdreferences/overview.mdreferences/examples_good.mdreferences/examples_bad.mdassets/schema.jsonscripts/run.pySKILL.md as a routerreferences/references/overview.mdreferences/examples_good.md and references/examples_bad.mdSKILL.md; avoid deep reference chainsassets/assets/assets/schema.json for the structured artifact that the skill validates or emitsscripts/run.py deterministicSKILL.md explicitly tells the agent when to read each reference filereferences/references/overview.md before customizing or applying this template.references/examples_good.md when the skill writes reader-facing text or shapes another writer skill.references/examples_bad.md when cleaning up generator voice, pipeline jargon, or weak deliverable framing.assets/schema.json: a generic contract for a reference-first skill manifest; adapt it to the concrete skill you are building.scripts/run.py is a minimal validator and manifest builder.Stop and fix the package before reuse if any of these are true:
SKILL.md duplicates long reference content instead of routing to references/run.py contains domain defaults, sentence libraries, or filler proseSKILL.md stays lean and references other files explicitlyreferences/ contains the actual method and exemplarsassets/ contains machine-readable contracts onlyscripts/run.py stays deterministic and smallSKILL.md and the referenced files without reading all Python firstExecute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.
GitHub CLI - manage repositories, issues, pull requests, actions, releases, and more from the command line.
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti
Take willoscar/_template_reference_first from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.