zircote-plugins

Adversarial falsification of sigint research findings. Generates disconfirming queries, executes web-only adversarial search, assigns ordinal verdicts (falsified | weakened | survived | inconclusive), and applies remediation (quarantine, confidence downgrade, follow-up queue). Invocable standalone via `/sigint:falsify` or as Phase 3.6 gate inside the research-orchestrator before report finalization. Use when the user invokes /sigint:falsify.

Create GitHub issues from research findings as atomic deliverables. Orchestrates the issue-architect agent using the full swarm pattern (TeamCreate → TaskCreate → Agent(team_name) → SendMessage → TeamDelete). Use this skill when the user invokes /sigint:issues.

Begin a new market research session. Thin launcher that delegates to the research-orchestrator agent for all phase management.

Refresh existing research with latest data using swarm orchestration and delta detection. Delegates to the research-orchestrator agent in update mode.

Deep-dive into a specific area of current research. Orchestrates a single dimension-analyst using full swarm pattern (TeamCreate, TaskCreate, SendMessage). Use when the user wants to augment current research with deeper analysis of a specific area.

This skill should be used when the user asks to "analyze competitors", "map competitive landscape", "Porter's 5 Forces analysis", "competitor comparison", "competitive positioning", "identify competitors", "competitive intelligence", or needs guidance on competitor research methodology, market positioning analysis, or competitive strategy frameworks.

This skill should be used when the user asks to "understand customers", "customer research", "user personas", "customer needs analysis", "buyer journey mapping", "voice of customer", "customer segmentation", "user research", or needs guidance on customer discovery methodologies, persona development, or understanding buyer behavior.

This skill should be used when the user asks to "analyze financials", "revenue model", "unit economics", "pricing analysis", "cost structure", "profitability analysis", "financial projections", "business model economics", or needs guidance on financial metrics, revenue analysis, or economic viability assessment.

This skill should be used when the user asks to "release a project", "create a release", "bump version", "publish to GitHub", "prepare a release", "run release validation", or needs to perform SDLC-compliant releases for Claude Code plugins, Python, Node.js, Go, or Rust projects. Provides comprehensive pre-release validation including tests, lint, coverage, and security checks.

Generate branded SVG graphics for blog content including social preview images, flowcharts, architecture diagrams, data visualizations, and styled tables. USE THIS SKILL when user says "create social preview", "generate diagram", "add flowchart", "create hero image", "visualize this", "svg graphic", "mermaid to svg", or when content would benefit from visual enhancement. Auto-triggers during blog content creation.

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude AI models.

Build robust backend systems with modern technologies (Node.js, Python, Go, Rust), frameworks (NestJS, FastAPI, Django), databases (PostgreSQL, MongoDB, Redis), APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), testing strategies, security best practices (OWASP Top 10), performance optimization, scalability patterns (microservices, caching, sharding), DevOps practices (Docker, Kubernetes, CI/CD), and monitoring. Use when designing APIs, implementing authentication, optimizing database queries, setting up CI/CD pipelines, handling security vulnerabilities, building microservices, or developing production-ready backend systems.

Implement authentication and authorization with Better Auth - a framework-agnostic TypeScript authentication framework. Features include email/password authentication with verification, OAuth providers (Google, GitHub, Discord, etc.), two-factor authentication (TOTP, SMS), passkeys/WebAuthn support, session management, role-based access control (RBAC), rate limiting, and database adapters. Use when adding authentication to applications, implementing OAuth flows, setting up 2FA/MFA, managing user sessions, configuring authorization rules, or building secure authentication systems for web applications.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.

This skill should be used when the user asks about "structured MADR", "structured-madr", "frontmatter ADR", "comprehensive ADR", "auditable ADR", or needs guidance on creating ADRs using the Structured MADR format with YAML frontmatter and audit sections.

This skill should be used when the user asks about "ADR compliance", "architecture compliance", "ADR audit", "enforce ADRs", "check code against ADRs", "ADR violations", or needs guidance on auditing code compliance with accepted architectural decision records.

This skill should be used when the user asks about "business case ADR", "MBA-style ADR", "cost-benefit ADR", "SWOT ADR", "executive ADR", "ROI ADR", or needs guidance on creating ADRs using the business case format for executive and financial analysis.

This skill should be used when the user asks about "MADR format", "MADR template", "Markdown Architectural Decision Records", "MADR 4.0", "MADR sections", or needs guidance on creating ADRs using the MADR (Markdown Architectural Decision Records) format.

This skill should be used when the user asks about "Nygard format", "Nygard ADR", "classic ADR format", "simple ADR template", "Michael Nygard ADR", or needs guidance on creating ADRs using the original Nygard format.

This skill should be used when the user asks about "Y-statement format", "Y-statement ADR", "concise ADR", "one-sentence ADR", "Olaf Zimmermann ADR", or needs guidance on creating ADRs using the Y-Statement format for concise decision documentation.

This skill should be used when the user asks about "ADR integration", "ADR CI/CD", "ADR tooling", "ADR automation", "export ADRs", "ADR documentation site", or needs guidance on integrating ADRs with CI/CD, documentation sites, and other tools.

This skill should be used when the user asks about "decision drivers", "architectural forces", "quality attributes", "how to identify trade-offs", "non-functional requirements for ADRs", or needs help identifying, documenting, and weighing the forces that influence architectural decisions.

Choose the right agent type for each task including built-in agents (Bash, Explore, Plan, general-purpose) and plugin agents (review, research, refactoring, SDLC). Use when selecting agent types, understanding agent capabilities, or matching agents to tasks.

Debug and recover from agent team errors including common errors, hooks for quality gates, known limitations, and recovery strategies. Use when encountering team errors, enforcing quality gates with hooks, understanding limitations, or debugging agent issues.

Send messages between agents using SendMessage including direct messages, broadcasts, shutdown requests/responses, and plan approvals. Use when communicating between agents, understanding message formats, or handling structured protocol messages.

Master multi-agent orchestration using Claude Code's agent teams and task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns. Routes to specialized sub-skills for team management, tasks, messaging, patterns, backends, and error handling.

Apply proven orchestration patterns for agent teams including parallel specialists, pipelines, swarms, research+implementation, plan approval, and multi-file refactoring. Use when choosing a team structure, designing workflows, or implementing specific coordination patterns.

Manage shared task lists for agent teams including creating tasks, setting dependencies, claiming work, and tracking progress. Use when creating work items, building task pipelines, coordinating task ownership, or managing task dependencies.

Analyze large JSONL log files using schema-aware partitioned analysis. Discovers field schema, generates tailored jq extraction recipes, and orchestrates parallel chunk analysts with synthesis. Use when processing JSONL logs exceeding context limits, performing log analytics, or investigating incident logs.

Process files exceeding context limits using the RLM (Recursive Language Model) pattern with agent teams. Use when you need to process large files, analyze documents exceeding context, apply RLM chunking, chunk and analyze large content, or handle long context documents.

This skill should be used when the user asks about "AI development", "AI coding", "AI assistant", "CLAUDE.md", "AI context", "AI guidelines", "code generation", "AI workflow", "AI review", "AI configuration", or needs guidance on configuring AI assistants and AI-assisted development workflows.

This skill should be used when the user asks about "CI pipeline", "continuous integration", "GitHub Actions", "CI configuration", "CI jobs", "workflow", "CI caching", "CI environment", "pipeline structure", or needs guidance on setting up or configuring CI/CD pipelines.

This skill should be used when the user asks about "documentation", "README", "CHANGELOG", "CONTRIBUTING", "ADR", "architecture decision record", "changelog format", "keep a changelog", "doc comments", "API documentation", or needs guidance on project documentation requirements.

This skill should be used when the user asks about "observability", "logging", "metrics", "tracing", "monitoring", "structured logging", "log format", "log levels", "distributed tracing", "OpenTelemetry", "health checks", or needs guidance on implementing observability and monitoring requirements.

This skill should be used when the user asks about "code quality", "formatting", "linting", "lint rules", "code style", "error handling", "unsafe code", "documentation comments", "doc comments", "rustfmt", "prettier", "eslint", "clippy", or needs guidance on code quality enforcement and configuration.

This skill should be used when the user asks about "release process", "versioning", "semantic versioning", "semver", "release automation", "publishing", "package publishing", "release checklist", "version bump", "release notes", or needs guidance on release workflows and version management.

This skill should be used when the user asks about "security", "vulnerability scanning", "dependency audit", "supply chain security", "license compliance", "security audit", "CVE", "OWASP", "secrets scanning", "cargo-deny", "npm audit", or needs guidance on security requirements and vulnerability management.

This skill should be used when the user asks about "project setup", "project initialization", "repository setup", "new project", "bootstrap project", "project structure", "development environment", "toolchain setup", "project configuration", or needs guidance on setting up new projects that comply with SDLC standards.

Patterns and templates for creating comprehensive API documentation using OpenAPI/Swagger, AsyncAPI, and manual documentation approaches. Use this skill whenever the user wants to document REST endpoints, generate or improve an OpenAPI spec, create Swagger docs, document WebSocket/event-driven APIs with AsyncAPI, review API documentation completeness, add request/response examples, document authentication schemes, set up API documentation portals (Swagger UI, ReDoc, Stoplight), or convert between API doc formats. Also applies when discussing endpoint parameters, response codes, schema definitions, pagination patterns, error response formats, or code-first vs design-first API documentation. If the user mentions "API docs", "OpenAPI", "Swagger", "AsyncAPI", "endpoint documentation", "API reference", or "API spec", this skill likely applies.

Generate, update, review, and maintain changelogs using Keep a Changelog format, semantic-release, and conventional commits. Use this skill whenever the user wants to add a changelog entry, prepare release notes, document version changes, generate a changelog from git history, configure semantic-release, understand conventional commit mappings, review changelog format, create migration guides for breaking changes, or troubleshoot semantic-release issues. Also applies when discussing version bumps, release automation, CHANGELOG.md formatting, or any task involving documenting what changed between software versions. If the user mentions "changelog", "release notes", "version history", "what changed", "semantic-release", or "conventional commits", this skill likely applies. Also covers "what's new", "upgrade guide", and "release history" queries.

Classify, create, review, and maintain documentation using the Diátaxis framework — the four-quadrant system (tutorials, how-to guides, reference, explanation) that separates documentation by user need. Use this skill whenever the user wants to classify documentation into quadrants, perform a documentation gap analysis, check for mode mixing, create documentation following a specific quadrant template, organize docs by type, review documentation for Diátaxis alignment, add diataxis_type frontmatter, split mixed-mode documents, or structure new docs as tutorials vs how-to guides vs reference vs explanation. Also applies when discussing documentation taxonomy, learning-oriented vs task-oriented content, quadrant coverage matrices, cross-reference audits between doc types, or when the user is unsure whether something should be a tutorial or a how-to guide. If the user mentions "Diataxis", "documentation types", "tutorials vs guides", "quadrants", "mode purity", "gap analysis", "documentation classification", "do

Standards and patterns for creating, reviewing, and improving technical documentation — covering markdown formatting, heading hierarchy, code blocks, links, writing style, accessibility, and language-native doc toolchains (rustdoc, godoc, Sphinx, TypeDoc, Javadoc, DocC, ExDoc). Use this skill whenever the user wants to review documentation quality, audit markdown formatting, fix document structure, improve technical writing, check doc comment coverage, enforce doc standards, write better docs, or asks about documentation best practices. Also triggers for language-specific doc toolchain questions (rustdoc, godoc, pydoc, JSDoc/TSDoc, Javadoc/KDoc, DocC, ExDoc) and site generator integration (MkDocs, Sphinx, Docusaurus, Astro Starlight). If the user mentions "docs", "documentation", "README", "writing style", "doc comments", "markdown", or "technical writing" in a quality or standards context, this skill likely applies.

This skill should be used when the user asks to "create citation file", "generate CITATION.cff", "validate citation", "update citation", "export citation as bibtex", "export citation as apa", "add DOI to citation", "enrich citation metadata", "sync citation version", "create cff file", "citation workflow", or needs to create, validate, update, or export CITATION.cff files for proper academic citation of software projects.

This skill should be used when the user asks to "enhance readme", "add badges to readme", "create readme infographic", "improve readme marketing", "add shields.io badges", "create architecture diagram", "generate project infographic", "make readme more engaging", "add project badges", "create visual overview", or needs to improve README.md with marketing badges and visual infographics that capture project architecture, features, and purpose.

This skill should be used when the user asks to "update repo description", "improve repository description", "generate topics", "add labels to repo", "optimize github metadata", "make repo more discoverable", "improve repo SEO", "update project description", or needs to create engaging repository descriptions and topics that improve discoverability. Analyzes project files to generate optimized GitHub metadata.

This skill should be used when the user asks to "generate social preview", "create social image", "github social preview", "repository preview image", "og image", "social media card", "create repo image", "github card image", or needs to create an image that captures a project's spirit and purpose for social media sharing. Analyzes project files to understand intent and generates optimized SVG graphics or AI-generated images.

Guided feature development with swarm-orchestrated codebase exploration, multi-perspective architecture design, implementation, and quality review. Use this skill when the user wants to build a new feature, add new functionality, implement a capability, or create something that doesn't exist yet. Triggers on requests like "add X", "implement Y", "build Z", "create a new W", "I need a feature for...", or any request to develop new functionality (not refactor existing code).

Guided feature development with swarm-orchestrated codebase exploration, multi-perspective architecture design, implementation, and quality review

Automated iterative code refactoring with swarm-orchestrated specialist agents including deep codebase discovery, confidence-scored code review, and security analysis

Automated iterative code refactoring with swarm-orchestrated specialist agents including deep codebase discovery, confidence-scored code review, and security analysis. Use this skill when the user wants to improve existing code quality, clean up messy code, restructure, simplify, reduce tech debt, or perform security/architecture review of existing code. Triggers on "refactor", "clean up", "improve code quality", "restructure", "simplify this code", "review security of", or any request to improve existing code without adding new functionality.

This skill should be used when the user asks about "how hooks work", "UserPromptSubmit", "hook-driven testing", "test wrapper", "prompt interception", "hook JSON format", "state management", or needs to understand the architecture of hook-driven automated testing.

This skill should be used when the user asks to "write a test", "create test cases", "add test coverage", "define test expectations", "use contains vs regex", "chain dependent tests", or needs guidance on test definition schema, expectation types, variable capture, or test organization best practices.

This skill should be used when the user asks about "test validation", "assertion strategies", "regex vs contains", "handling flaky tests", "validation failures", "expected vs actual", or needs guidance on choosing validation approaches and handling edge cases.

Daily intelligence reporting for the GitHub Agentic Workflows (gh-aw) ecosystem. Executes 8+ targeted web searches, synthesizes findings into a structured Markdown report, updates the persistent knowledge base, and optionally posts to GitHub Discussions. Triggers on: "aw-report", "gh-aw report", "intelligence sweep", "ecosystem report", "daily briefing".

Author, validate, and improve GitHub Agentic Workflow (gh-aw) markdown files. Use when the user wants to create a new workflow, validate an existing workflow, improve a workflow, or debug workflow issues. Triggers on: "aw-author", "agentic workflow", "gh-aw workflow", "workflow markdown", "workflow frontmatter", "write a workflow", "create a workflow", "validate workflow", "debug workflow".

Fully autonomous daily pipeline for the aw-author plugin. Executes intelligence research (web search + GitHub activity queries), posts to Discussions, performs gap analysis against reference files, creates issues, implements changes on develop branch, creates PR, requests review, and auto-merges. Designed for unattended execution with zero human intervention. Triggers on: "aw-daily", "daily pipeline", "daily cycle", "autonomous update".

Autonomous skill and MCP server improvement loop inspired by Karpathy's autoresearch pattern. Iteratively modifies skills or MCP server code, evaluates against fixed evals, keeps or discards changes to converge on higher quality. Supports skill evals (evals.json) and MCP server evals (evaluation.xml with QA pairs). Includes eval management and convergence reporting. Use when users want to automatically improve a skill's quality, improve an MCP server, create or fix evals for a skill or MCP server, or view improvement loop results. Triggers on "autoresearch", "improve skill automatically", "auto-improve", "skill improvement loop", "run improvement loop", "eval doctor", "fix evals", "create evals for skill", "skill quality", "autonomous improvement", "improve MCP server", "MCP eval".

A sample skill for testing autoresearch.

A sample skill for testing autoresearch.

Design, review, or refactor CLI error messages so they serve BOTH human operators AND LLM agents using the RFC 9457 Problem Details envelope with mandatory agent extensions (retry_after, suggested_fix, code_actions[]). Use whenever the user works on CLI error output, stderr format, exit codes, machine-readable errors, structured error envelopes, dual-format CLI rendering, or reducing token cost of tool_result payloads. Triggers on phrases like "CLI error message", "stderr format", "machine-readable errors", "dual-consumer errors", "problem+json", "RFC 9457 errors", "agent-parseable errors", "review my CLI error messages", "refactor error handling", or when improving error reporting in any CLI (Go, Rust, Python, Node, Ruby, Java, C#, shell). Use this skill even when the user does not cite the RFC or dual-consumer framing — if the work touches CLI error output an agent might parse, this skill applies.

Review, refactor, or design error-handling source code across any language (Rust, Go, Python, TypeScript, Java, others) and any context (CLI, library, service, web). Produces classified violation reports (must-fix / should-fix / nit / question / praise), before/after diffs, and YAML work plans for large refactors. Triggers on "review my error handling", "audit error code", "find error-handling bugs", "fix exception handling", "improve error propagation", "review my Result usage", "audit my errors.Is calls", "check my try/except", "panic in library", "swallowed error", "lost cause chain", or when reviewing code where modified files contain error emission, propagation, recovery, or cleanup logic. Defers CLI envelope and format questions to sibling skill cdc-err (RFC 9457 Problem Details). Use even when the user does not request a review — if the work touches how errors propagate, get swallowed, get wrapped, or get logged, this skill applies.

Interpret and act on RFC 9457 problem+json error envelopes that a CLI (typically one shaped by sibling skill cdc-err) returns to an LLM agent in a tool_result. Three modes — Parse the envelope, Decide retry vs apply-fix vs handback vs abort, Act by emitting a concrete executable action plan. Always gates suggested_fix and code_actions[] on applicability markers (machine_applicable / maybe_incorrect / has_placeholders / unspecified) and treats missing/unspecified applicability as maybe_incorrect (safe default — surface to human, never auto-apply). Use this skill whenever a tool_result payload contains an application/problem+json envelope, fields like retry_after / suggested_fix / code_actions[], or status / title / type / detail / instance combinations characteristic of RFC 9457. Also use on explicit phrasing — "interpret this error", "should I retry this CLI error", "the CLI returned problem+json", "what does this retry_after mean", "can I auto-apply this suggested_fix", "the tool_result has an error envelope