A model-agnostic Agent Skills library for explicit routing, bounded context, and verifiable agent behaviour.
Scores and improves an existing Agent Skill against a spec + quality rubric, then proposes or applies concrete refactors (split monoliths, sharpen descriptions, fix portability). Use to review, grade, lint, or improve a skill, or to maintain a skill library at scale. Justifies each finding with verifying-reasoning and routes fixes back to authoring-skills.
Generates a new, spec-compliant, portable Agent Skill from a capability description, frontmatter, focused body, and the supporting file set, following progressive-disclosure and single-responsibility rules. Use when asked to create, scaffold, or package a skill. Sizes/splits via composing-skills and self-checks the output with verifying-reasoning, then hands to auditing-skills.
Routes a task to the smallest set of skills that covers it and sequences them without context bloat, instead of one monolithic instruction. Use when a task spans multiple capabilities, when many skills are installed, or when deciding which skills to apply. Reads the skill registry to discover specialists and respects the tier/dependency ordering.
Deliberately manages the context window to cut token cost and prevent quality decay on long runs. Use when a task is long-running, involves large files or many tool outputs, the context feels full, or cost matters. For finding external info efficiently use progressive-research; for surviving multi-session work use sustained-execution.
Turns a goal into a verifiable, risk-ordered plan with explicit success criteria before any work starts. Use at the start of any multi-step, ambiguous, or long-horizon task. Hands off to sustained-execution for long runs and verifying-reasoning to validate the plan.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A model-agnostic Agent Skills library for explicit routing, bounded context, and verifiable agent behaviour.
Small skills over standing prompt weight. Composition over monolithic instructions. Explicit routes over accidental activation.
Install · Plugin · Documentation · Quick Start · Roadmap · Capabilities · Routing · Verification
Created by Adrian Paredez, with Sole as his sovereign cognitive work partner.
Capability Fabric is an agent-improving skill layer for runtimes that support the open Agent Skills standard. It gives an agent a small set of process skills for planning, research, context budgeting, sustained execution, verification, code quality, autonomy, and skill authoring.
The library is deliberately narrow. Each skill has one responsibility, a portable
SKILL.md, and supporting references loaded only when needed.
[!IMPORTANT] Capability Fabric changes the agent's operating method, not a single task domain. Install it once, then state the task. The runtime selects matching skills from their names and descriptions, and loads the full body only when needed.
Install into every detected agent runtime:
git clone https://github.com/AdrianParedez/capability-fabric.git
cd capability-fabric
./install/install.ps1
If PowerShell blocks the script, run it without changing your policy:
pwsh -ExecutionPolicy Bypass -File ./install/install.ps1
macOS and Linux:
git clone https://github.com/AdrianParedez/capability-fabric.git
cd capability-fabric
./install/install.sh
Remove the installation:
./install/install.ps1 -Uninstall # Windows
./install/install.sh --uninstall # macOS / Linux
Installer options:
| Flag | Effect |
|---|---|
-All / --all | Target every known agent location, detected or not. |
-Link / --link | Symlink instead of copy. |
-NoDirective / --no-directive | Install skills only. |
-Uninstall / --uninstall | Remove installed skills and the routing block. |
Claude Code plugin install:
/plugin marketplace add AdrianParedez/capability-fabric
/plugin install capability-fabric
The Claude Code plugin metadata is experimental. The skills and installers are the supported distribution surface for the public release.
The public documentation is organized under docs/. Start with
docs/README.md.
Install the library, open an agent, and state the work in ordinary language:
research the current Agent Skills standard and write a report
plan this repository migration and keep a durable ledger
review this feature branch for behavioural regressions
create a new portable skill for release-note drafting
The routing block points the agent at skills/REGISTRY.md. The
registry defines the available capabilities and default composition paths.
Manual installation:
skills/<name>/ -> ~/.agents/skills/<name>/
skills/<name>/ -> ~/.codex/skills/<name>/
skills/<name>/ -> ~/.claude/skills/<name>/
See docs/release/ROADMAP.md for the current lane, planned work, and non-goals.
npx claudepluginhub adrianparedez/capability-fabric --plugin capability-fabricUI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.