SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

prose
Run, lint, and manage OpenProse contract-markdown workflows and ProseScript; interpret `prose` commands and execute or validate multi-step agent orchestrations.

llm-council-skill
Run decisions through a council of five AI advisors who independently analyze, peer-review, and synthesize a clear recommendation (Karpathy-style).

obsidian-mcp-server
Guided workflow for filing well-structured bug reports or feature requests against @cyanheads/mcp-ts-core when a framework API behaves incorrectly.

vvm
A small domain-specific language and runtime for writing agentic programs (.vvm) where the LLM is the execution runtime; provides compile, run, and inspection c

PPT as Code
Creator-first workflow to plan and build HTML-first presentations with staged modes (quick/basic/advanced), optional PPTX export, and clear QA and image plannin

comeonoliver
Guided workflow for drafting high-quality technical articles for developer audiences: intake, title/hooks, structure, drafting, images, and finalization.

mindos
Local/shared knowledge-base assistant: search, read, and safely write notes, SOPs, meeting summaries, and structured rows (CSV) with clear bootstrap/read-before

chorus
Admin-focused review workflow for Chorus: approve/reject proposals, verify completed tasks, and manage project governance to keep agent teams on track.

clawg
Produce a concrete, actionable markdown plan saved to .clawg/plans/ — planning-only mode that avoids execution or file mutations outside the plan file.

code-virtuoso
A step-by-step playbook to verify, review, choose an integration strategy, write PR messages, push, and clean up when finishing a development branch.

skills
Returns docs-grounded guidance and exact GitHub docs links for writing, explaining, migrating, securing, or troubleshooting GitHub Actions workflows.

agent-skills
Provides branching strategies, commit conventions, CI/CD recommendations, and repository hygiene patterns for teams adopting trunk-based development and stacked

the-startup
Create structured product or feature specifications from a short prompt; manages PRD/SDD/PLAN phases, directory scaffolding, and decision tracking.

anvil
Pick up a paused long-running task, make measurable progress, and save a concise breadcrumb file describing work done and what's left so another agent can conti

maestro-orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.

openai
Diagnostic coordinator skill that triages stuck, hung, or broken systems by checking logs, workflows, browser state, and deployment/environment in a strict, rep

activer007
Python library skill for importing, filtering, and comparing mass spectra (mzML/MGF/MSP); builds reproducible preprocessing pipelines and computes spectral simi

humanize
Refine annotated gen-plan documents by removing comment blocks and producing a QA ledger that records decisions, answers, and applied changes.

claude-code-plugins-plus-skills
Refactor features toward the intended architecture: remove legacy cruft and simplify code to reduce long-term operational cost.

vexjoy-agent
Plans multi-part content series: assesses viability, selects structure and cadence, and generates detailed per-part plans with cross-linking and publishing sche

thx-boris
Collection of production-tested patterns, templates and protocols for running Claude Code effectively: CLAUDE.md, subagents, hooks, sessions and parallel orches

ystack
Run final verification, check docs and tests, and create a pull request (or delegate to a repo pr-draft skill).

vexjoy-agent
Umbrella skill for content publishing: outline posts, run pre-publish checks, optimize SEO, batch-edit frontmatter, audit links/images, manage taxonomy, and upl

dots
Draft and apply a clear, imperative-style message to amend the last git commit without changing the commit contents; preserves co-author trailers and warns abou

spboyer
Iteratively improves SKILL.md frontmatter using the Ralph loop to meet compliance and testing standards.

orchestrate
Supervisor skill that composes multi-model runs, routes subtasks to the right models and skills, and manages implementation & verification runs.

citadel
A single-session meta-orchestrator that parses a direction, chains existing skills, and executes multi-step tasks end-to-end without unnecessary user prompts.

specs.md
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati

my-ai-tools
Generates structured Product Requirements Documents (PRDs) with clarifying questions, user stories, functional requirements, non-goals and success metrics — for

rlm-workflow
Orchestrates an RLM-inspired repository workflow with phase gates, lockable artifacts, and automated bootstrap for run folders — enforces TDD, traceability, and