Scripts

rules-distill is a maintenance skill for Skill Authors and prompt library curators. It scans installed skills, distills repeated patterns into reusable rules, and helps you append, revise, or create rule files with less guesswork than a generic review prompt.

diagnose is a structured debugging workflow for hard bugs, flaky tests, and performance regressions. It helps you reproduce the issue, minimise the failing case, form one hypothesis at a time, add instrumentation, fix the root cause, and lock it in with a regression test. Use the diagnose guide when “debug this” is not enough.

context-fundamentals is a practical guide to context engineering for AI agent systems. It helps you decide what belongs in the prompt, debug context issues, and manage token budgets with clearer context structure. Use this context-fundamentals skill when you need a grounded context-fundamentals guide for agent design and prompt optimization.

The huggingface-tool-builder skill helps you create reusable command-line tools for Hugging Face API work instead of one-off prompts. It is useful for chained API calls, intermediate processing, repeatable fetch/enrich steps, and API Development workflows with shell, Python, or TSX.

hv-analysis is a horizontal-vertical research skill for turning a product, company, concept, technology, or person into a structured analysis report. Use the hv-analysis skill for deep research, competitive comparison, and report-ready output, especially when you need hv-analysis for Data Analysis or a polished PDF workflow.

building-incident-response-playbook helps security teams create reusable incident response playbooks with step-by-step phases, decision trees, escalation criteria, RACI ownership, and SOAR-ready structure. It is designed for incident response procedure documentation, incident triage workflows, and audit-friendly operational response plans.

health runs a budget-aware Agent Health audit for Codex, Claude Code, Pi, agent instructions, hooks/MCP, verifier surfaces, and AI maintainability. Use the health skill to check why an agent ignores instructions, misses validation, or drifts into hard-to-maintain behavior. It is especially useful for Security Audit workflows, but not for debugging code or reviewing PRs.

skill-creator skill guide for Skill Authoring with Azure SDKs and Microsoft Foundry. Learn when to install it, how to inspect the references, and how to turn a domain or repo into a reusable skill with clearer workflows, constraints, and validation.

skill-creator is a guide for Skill Authoring that helps you create or update reusable Skills with clear scope, workflows, references, and scripts. Use the skill-creator skill when you need consistent behavior across sessions, practical packaging support, and less guesswork than a one-off prompt.

parallel-web is a web research and extraction skill powered by parallel-cli. It helps you search the web, extract URL content, enrich data from sources, and run deeper research with academic and scientific sources prioritized. Use it for parallel-web usage, web research, citations, and evidence-first workflows.

The data-structure-protocol skill helps agents build and navigate DSP graphs for codebases. It tracks modules, functions, imports, exports, and why links exist, making it useful for .dsp projects, bootstrap workflows, and safer code changes with structural context.

building-threat-intelligence-platform skill for designing, deploying, and reviewing a threat intelligence platform with MISP, OpenCTI, TheHive, Cortex, STIX/TAXII, and Elasticsearch. Use it for installation guidance, usage workflows, and Security Audit planning backed by repository references and scripts.

acquiring-disk-image-with-dd-and-dcfldd helps Security Audit and forensic users create a defensible bit-for-bit disk image with dd or dcfldd, using write protection, hash verification, and a clear acquisition workflow for incident response and evidence handling.

analyzing-active-directory-acl-abuse helps security auditors and incident responders inspect Active Directory nTSecurityDescriptor data with ldap3 to spot abuse paths like GenericAll, WriteDACL, and WriteOwner on users, groups, computers, and OUs.

Linear skill for managing issues, projects, initiatives, labels, and team updates in Linear. Use this Linear guide when you need reliable Linear usage for discovery-first workflows, status updates, issue creation, and repeatable project management with MCP or CLI fallback paths.

Use the finding-duplicate-functions skill to identify semantic duplicates: functions that do the same job with different names or implementations. It is built for LLM-generated and fast-growing JavaScript or TypeScript codebases, and it supports finding-duplicate-functions for Code Review, consolidation planning, and cleanup before refactors.

observe-whatsapp helps diagnose WhatsApp operations in Kapso: message delivery, webhook retries, API errors, and number health. Use the observe-whatsapp skill to move from a failure signal to the right check fast, with CLI-first steps and API fallback for production troubleshooting.

The minimax-pdf skill helps you create, fill, or reformat polished PDFs when visual quality and document identity matter. Use it for CREATE, FILL, or REFORMAT workflows with a token-based design system that turns rough input into print-ready output. This guide covers minimax-pdf install, minimax-pdf usage, and route selection for better results.

skill-authoring-workflow helps you turn rough notes, workshop output, or draft prompts into a compliant, repo-ready skills/<skill-name>/SKILL.md. Use this skill-authoring-workflow skill to create or update PM skills with less guesswork, follow repo standards, and validate before commit.

gh-fix-ci is a focused GitHub Actions troubleshooting skill for failing PR checks in repos where `gh` access is available. It inspects checks and log snippets, summarizes the failure context, drafts a fix plan, and waits for explicit approval before implementation. Built for fast, evidence-based diagnosis of CI failures.

gh-address-comments helps address review and issue comments on the open GitHub PR for your current branch using gh CLI. It verifies GitHub auth first, fetches comments and review threads, numbers them, and helps you choose which items to fix. Useful for gh-address-comments guide and gh-address-comments for PR Review workflows.

wp-project-triage is a deterministic first-pass inspector for WordPress repositories. It identifies project type, detects tooling and tests, surfaces version hints, and returns a structured JSON report to guide guardrails before you edit anything. Ideal for Workflow Automation and agent triage.