Comprehensive skill for developing Caido plugins (frontend, backend, or both). Use this skill when creating Caido security testing tool plugins, extending Caido functionality, or building custom automation for web application security auditing within the Caido platform.
The full QC8 comment-quality catalog — eight bad comment shapes to delete with before/after examples, plus the keep-list of comments that earn their place. Load before writing or editing code comments, when a review flags comment quality, or to cite a QC8 shape number. AGENTS.md carries the rule and the keep-list…
Set up a new A/B experiment in Grafana Pathfinder end to end — MTFF flag, variant validation, enrollment seam, exposure and behaviour analytics, QA overrides, tests, docs, and a retirement plan. Use when the user runs /create-experiment, asks to add or run an experiment or A/B test, add a treatment/control variant…
Optimise Grafana app plugin bundle size using React.lazy, Suspense, and webpack code splitting. Use when the user asks to reduce plugin bundle size, optimise module.js, add code splitting, improve initial plugin load performance, split plugin chunks, lazy load plugin pages, or help implement lazy loading in a Grafana…
Sync Claude Code skills (plugins + personal) to Codex CLI by copying folders. Creates /bin/list-skills enumerator for skill discovery. Run after installing new Claude plugins.
Security scanner for AI Agent skills, plugins, and MCP servers. Use when: user asks to scan a skill, check if a plugin is safe, vet an MCP server, review skill security, detect malicious code, supply chain safety, or says 'is this safe to install', 'scan this skill', 'check this MCP server', 'security scan'…
Auto-loop execution workflow with quality gates. Use when starting any non-trivial implementation task. Provides automatic task decomposition, code implementation, testing (L1-L4), and iterative quality gates until completion. Invoke with /autoworker.
Structured deep discussion for Plan Mode. Runs inside EnterPlanMode to ensure thorough questioning before writing a plan. Covers motivation, assumptions, design, acceptance criteria. Call this immediately after entering Plan Mode for any non-trivial task.
Sync tracking documents based on current conversation results. Updates subtask, progress, findings, taskplan, project CLAUDE.md. Use when finishing a task or reaching a milestone.
Builds, deploys, and tests the typemux-cc Claude Code plugin locally. Handles the full cycle from cargo build through cache clearing, marketplace registration, plugin install, and LSP verification. Triggers on: 'plugin test', 'test plugin', 'plugin cycle', 'deploy and test', 'try new build', 'test the plugin'.
Prepare a version bump through a feature branch and pull request; merging to main auto-tags and publishes the release. Triggers on 'publish', 'release', 'bump version'.
Generates and improves CRC-style (Class-Responsibility-Collaborator) class comments for Smalltalk/Tonel classes. Use whenever lint (st-lint) flags a class as missing or having a poor class comment, when the user asks to "add class comments", "document classes in [package]", "check class documentation", or after…
Conduct SPARK methodology analysis for new project inception. Use at the beginning of a new project, when evaluating significant features, before bootstrap-project to validate viability, or when pivoting an existing project.
Bootstrap a new project at a chosen graduation tier (t0 minimum, t1 decision-tracked, t2 full pattern language) following AI-Assisted Project Orchestration best practices. Use when starting a new software project, promoting an existing project to a higher tier, or converting an existing project for AI-assisted…
Configure two-stage git hooks (pre-commit + pre-push) for quality automation, with either pre-commit or lefthook as the hook manager. Use after bootstrap-project and setup-adrs, when adding quality gates to an existing project, or when standardizing quality automation.
A diagnostic tool for finding unusual Claude Code usage. It checks six kinds of statistical irregularities, rates their severity, and examines suspicious sessions in more detail.
This skill should be used when the user asks to "analyze token usage", "check costs", "how much did I spend", "token analysis", "session analysis", "cta", or mentions Claude Code usage efficiency, token spending, or cost optimization. Routes to 6 workflow sub-skills: cta-health-check, cta-cost-audit, cta-anomaly-hunt…