agentic-framework skills

PigeonDan1/paper_claw

Skill Claude CodeCodex

Fetch, classify, and summarize papers from multiple sources (arXiv, etc.) with AI-powered multi-language summaries and email delivery.

spencermarx/orc

Skill Claude CodeCodex

AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.

jorgegorka/ariadna

Skill Claude CodeCodex

Ruby on Rails backend conventions — models, controllers, jobs, API design. Use when implementing Rails backend code, creating models, writing controllers, or designing APIs.

jorgegorka/ariadna

Skill Claude CodeCodex

Ruby on Rails frontend conventions — Hotwire, Turbo, Stimulus, views, components, assets. Use when implementing frontend features, building views, or working with JavaScript/CSS.

jorgegorka/ariadna

Skill Claude CodeCodex

Ruby on Rails security conventions — authentication, authorization, OWASP protections, CSRF, input validation. Use when implementing auth, handling sensitive data, or reviewing security.

intelliswarm-ai/swarm-ai

Skill Claude CodeCodex

Parse XBRL financial documents and extract key taxonomy elements into structured JSON format.

intelliswarm-ai/swarm-ai

Skill Claude CodeCodex

a deterministic stub returned by the override engine in unit tests.

Open-Harness/open-harness

Skill Claude CodeCodex

Use when auditing a repo for ADR/spec drift, dual architectures, legacy compatibility layers, or conflicting event/state models before refactoring.

Open-Harness/open-harness

Skill Claude CodeCodex

Interactive task planning and autonomous execution using @open-harness/ralph. Interviews user, creates PRD, generates task list with Claude Code's built-in task tools, then executes tasks autonomously with full Claude Code capabilities. USE WHEN user says 'ralph', 'run ralph', 'autonomous task', 'execute plan'…

laragentic/agents

Skill Claude CodeCodex

Comprehensive API testing, validation, and test suite generation.

laragentic/agents

Skill Claude CodeCodex

Comprehensive code review for security, performance, and best practices.

laragentic/agents

Skill Claude CodeCodex

Expert data analysis, statistical modeling, and insight generation.

fluent-meaning-symbiotic/agentic_executables

Skill Claude CodeCodexCursor

Creates and updates architecture diagrams using Mermaid syntax across codebases. Use when documenting system relationships, data flows, or when the user asks about architecture diagram creation or updates.

fluent-meaning-symbiotic/agentic_executables

Skill Claude CodeCodexCursor

Installs, updates, and uses FAQ documentation across codebases. Use when working with FAQs, discovering package documentation, updating FAQs after code changes, or when the user asks about FAQ installation, updates, or usage.

fluent-meaning-symbiotic/agentic_executables

Skill Claude CodeCodex

Use this skill to execute Agentic Executables workflows through the ae CLI.

mohamed-hossam1/nextjs-skills

Skill Claude CodeCodex

Use when setting up or using next-action-handler, next-safe-action, actionClient/authedActionClient, action metadata/actionName, validationErrors, outputSchema, handleServerError, better-auth errors, or pino logging.

mohamed-hossam1/nextjs-skills

Skill Claude CodeCodex

Use this skill whenever the user wants to design or implement caching in a Next.js 16+ App Router project — setting up the "use cache" directive, building a cache tag registry, wiring mutations to invalidation utilities, structuring Suspense boundaries for partial prerendering, handling personalized content near cache…

richfrem/agent-plugins-skills

Skill Claude CodeCodex

Part of agent-agentic-os

Verifies that os-architect actually causes evolution — not just words. Dispatches os-architect in single-shot simulation mode for a given test scenario, then checks for real artifact presence (new files, HANDOFFBLOCK, plan files). Reports PASS / FAIL with grep evidence. Accumulates results into a test report. Use…

richfrem/agent-plugins-skills

Skill Claude CodeCodex

Part of agent-agentic-os

Continuously improves an existing agent skill based on eval results using the RED-GREEN-REFACTOR cycle. Apply when a skill's routing accuracy is low, trigger descriptions need sharpening, or os-eval-runner scores are below target. (1) run a RED baseline to observe the failure mode, (2) apply a focused patch and verify…

richfrem/agent-plugins-skills

Skill Claude CodeCodex

Part of agent-agentic-os

Self-healing and self-evolving pattern for agents operating against repo capabilities, scripts, skills, sub-agents, selectors, workflows, and external systems. Classifies evolution events into four tiers — Friction/Workaround, Gap, Failure, Regression — applies repo-profile-gated edits with appropriate autonomy…

AnmarHani/SwarmVault

Skill Claude CodeCodex

The developer-driven design lane — the user commits to each approach before anything is written, then the design goes to pseudocode, algorithms, invariants, sequence diagrams and test vectors in their chosen design language. Use when the user wants to own the system rather than receive it: "developer mode"…

AnmarHani/SwarmVault

Skill Claude CodeCodex

The SDLC router — figures out where a project stands and runs the right phase. Use at the START of any work in a SwarmVault project: continuing/resuming a project, starting a new one, "what's next", or before writing any feature code, spec, design, or ticket. Also use when unsure which phase (requirements, design…

AnmarHani/SwarmVault

Skill Claude CodeCodex

Optional autonomy control plane — configure, plan, launch, monitor, recover, or stop local CLI-agent workers through SwarmVault's durable supervisor. Use for fit/budget-aware platform + model + reasoning-effort routing; a consistent pre-start/live/boundary/on-demand board with ticket drill-down; TOLD/MEASURED/EST…

colinwilliams91/gaitor-orchestrator-cli

Skill Claude CodeCodex

Create a deliberate git checkpoint commit from staged or current working changes using a diff-based, model-written Conventional Commit message. Use when you want a clean commit boundary during intensive agentic iteration.