SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
claude-code-plugins-plus-skills
Ingests public X/Twitter complaints, clusters related reports, scans repos for evidence, and drafts or files GitHub issues with owner routing and human confirma
gsd-skill-creator
Autonomously triage GitHub issues, submit fixes as PRs, and perform adversarial PR reviews to find security and quality problems.
design-system-ops
Quickly assess a design system's state and recommend a short, prioritized run plan of skills to run first.
bug-hunter
Run an adversarial, sequential-first pipeline (Recon → Hunter → Skeptic → Referee) to find, verify, and optionally auto-fix runtime bugs and security issues acr
opensoul
Orchestrates fetching GitHub issues, confirming targets, and spawning code-fix sub-agents to create PRs and handle review comments via the GitHub REST API.
claude-matrix
A 5-agent, context-aware code review pipeline for comprehensive PR and staged-change reviews, including security detection, blast-radius analysis, triage, remed
ai-runbooks
Find potentially duplicate or similar cases before deep analysis by running a similarity check against existing cases and returning matching case IDs.
claude
A structured root-cause debugging workflow: investigate, understand, reason, and fix — with commands and templates for code search, GitHub issue lookup, log ana
catalyst
Command reference and workflows for the Linearis CLI to read, search, create, update, and manage Linear tickets, milestones, cycles and labels.
insurance-skills
MCP skill for listing, analyzing, reporting, and managing InsurGateway (IGW) integration errors across test and production, with filters, reports, and write-saf
decepticon
High-volume codebase scanner that shards work, ranks suspicious locations, and promotes a concise set of candidates for deeper analysis.
ryanb/dotfiles
Generate a ranked, clickable list of open PRs prioritized by review ease, with grouping for PR dependency chains and optional preference directives.
tta-lab
Unified review comments tool for plan reviews, PR reviews, triage reports, and verdicts.
tackline
Create structured bug reports from descriptions or review output, with repro steps and priority to file issues in your tracker.
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.
mitre-attack-agent-skills
Defensive analysis skill for MITRE ATT&CK T1560.003: helps map observations, produce detection ideas, and create triage and mitigation briefs for custom archive
nexus-agents
A disciplined, test-first workflow for reproducing, triaging, and fixing software bugs while preventing regressions.
claude-code-toolkit
Create or link bug sub-issues: interactively gather context, create a well-structured GitHub bug issue, or add existing issues to a tracking PR.
skillshub
Automates continuous open-source contributions using a 9-agent swarm: finds good-first-issues, implements fixes/tests/docs, creates PRs, and handles review feed
claudefiles
Run a 3-agent adversarial bug hunt (Hunter, Skeptic, Referee) to find and verify real bugs in a codebase.
claude-fuer-deutsches-recht
Implements the court's insolvency opening decision into practical administration: organize the estate (Masse), prepare registers and tables, run the first reali
claude-fuer-deutsches-recht
Entry triage and workflow routing for defending against Strafbefehl (German summary penalty orders): secures deadlines, classifies uploads, and routes to specia
crypto-project-security-skill
Run a structured risk analysis of a DeFi protocol covering smart contracts, governance/admin keys, oracle design, economic mechanisms, and incident history.
capsem
Structured, per-bug review workflow: confirm, validate or push back, get agreement, implement TDD fixes, and commit with changelog — one bug per commit.
buildwithclaude
Prioritises operational work across fires, unread comms, ready-to-merge PRs, sprint issues, and revenue-impact GSD tasks to recommend the next action.
agentic-dev-team
A four-phase debugging protocol (reproduce, investigate, root-cause, fix) that enforces evidence-driven fixes and prevents guess-and-fix thrashing.
specialist-agent
A four-phase, evidence-first debugging methodology agent skill: gather evidence, analyze patterns, formulate hypotheses, and implement & prove fixes.
K.I.T (Known Issue Triager)
Consolidate audit reports into a canonical known-issues.json register, extend existing registers, or check whether a reported issue is already known.
plugins
Diagnostic coordinator skill that triages stuck, hung, or broken systems by checking logs, workflows, browser state, and deployment/environment in a strict, rep
nexus-agents
Structured bug-fix workflow and triage protocol: reproduce, localize, reduce, fix, add regression test, and verify before resuming development.
