tonone
claudeThird-party: tonone by tonone-ai (MIT). Vendored unmodified; see vendor/tonone/LICENSE.
200 skills · 100 agents · hooks
Engineering workflows: debugging, testing, refactoring, scripts, stack operations.
Plugin loxihart-engineering from marketplace loxihart-skills in Krosebrook/loxihart-skills. Commands read from the repo's manifest — today.
administering-supabaseManages Supabase database operations for FlashFusion's production stack — schema design, Row Level Security policies, migrations, Edge Functions, and debugging. Active project: flashnframe-app (etctmappdhpjuwptdbeb). Use when the user mentions: Supabase, RLS, row level security, migration, schema, d
auditing-logicAudits code for logical errors before they become bugs — control flow gaps, data contract violations, schema/type drift, business logic inconsistencies, and silent failure paths. Produces a severity-rated issue list with a one-line diagnosis and one-line fix per finding. Use this skill whenever code
code-auditorPerforms comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.
code-transferTransfer code between files with line-based precision. Use when users request copying code from one location to another, moving functions or classes between files, extracting code blocks, or inserting code at specific line numbers.
debug-like-expertDeep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis. Triggers on: debug this, root cause anal
engineering-patternsProduction engineering pattern library spanning 11 phases — Foundation, Resilience, Performance, Data Integrity, Observability, Deployment, Scalability, Edge Cases, Security Deep, Compliance/DR/FinOps, and AI/HITL. Use when auditing code for production readiness, applying hardening patterns, reviewi
engineering-staff-workflowsOperates as a security-first, scope-gated Staff Engineer workflow for production system builds across a 50–200 engineer organization. Routes every task through mandatory SCOPE_MODE gating, applies WSJF backlog prioritization, enforces AppSec-grade threat modeling, and covers the full stack from fron
fixing-testsRun tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.
generating-build-specsGenerates project-aware pre-build specs using project knowledge and codebase context. Phase 1 runs a 7-section spec: outcome contract, states, data contract, failure taxonomy, platform constraints, adversarial questions, unknown unknowns. Phase 2 generates actionable artifacts: build prompt, state s
governing-stack-costsTracks, alerts on, and optimizes cloud infrastructure costs across the production stack — Anthropic API token spend, Supabase compute and egress, Vercel function invocations, and n8n executions. Establishes per-service budget thresholds, monthly review workflow, and quick-win optimization patterns.
hardening-client-side-keysRemoves provider API keys from browser / client-side tools by putting a fail-closed edge proxy (Cloudflare Worker) in front of the LLM or API call, then rewiring the tool to call the proxy instead of the provider. Use when the user mentions: API key in the browser, client-side key, key in the fronte
implementing-review-feedbackProcess and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
instrumenting-production-stackSets up observability for the Vercel + Supabase + n8n + Anthropic stack. Live operational path runs through PostHog (MCP connected). Datadog is NOT connected — all Datadog steps are static setup references only, clearly labeled, and not executable via MCP. Use when the user mentions: PostHog instrum
kyle-vibe-codingRapidly prototype and build complete web apps on Kyle's production stack — React 19, Vite, TypeScript, Tailwind, Supabase (auth, RLS, Postgres), Cloudflare Workers/Pages, Resend, Stripe, PostHog. Enforces security-first defaults, the no-placeholder rule, and a mandatory 6-persona audit loop before a
managing-credential-lifecycleManages the lifecycle of API keys, tokens, and credentials across a multi-service production stack — inventory, rotation schedules, audit procedures, and emergency revocation for Vercel env vars, Supabase service keys, the n8n credential store, Anthropic API keys, and MCP server tokens. Use when the
operating-n8n-productionManages n8n workflow automation in production — credential management, execution monitoring, error handling, workflow versioning, worker health, and blocked workflow recovery. Covers the Base44 Bearer credentials pattern and SCH-02 lane field fix for the FlashFusion platform. Use when running n8n in
organizing-projectsAnalyze, reorganize, and scaffold project repositories — structure audits, convention enforcement, migration planning, and new project scaffolding. Use this skill whenever someone asks about repo or codebase organization, project folder layout, naming conventions, monorepo decisions, file placement
project-bootstrapperSets up new projects or improves existing projects with development best practices, tooling, documentation, and workflow automation. Use when user wants to start a new project, improve project structure, add development tooling, or establish professional workflows.
refactoring-codePerforms bulk code refactoring operations including renaming variables and functions across files, replacing patterns, and updating API calls. Use when renaming identifiers, replacing deprecated code patterns, updating method calls, or making consistent changes across multiple locations.
sparc-methodology-coachGuide structured development through 5 phases — Specification, Pseudocode, Architecture, Refinement (TDD), and Completion — with explicit time budgets per phase and a mandatory 6-persona staff-level audit loop at Completion that evaluates systemic risk, blast radius, and architectural coherence befo
workflow-automationBuild automated workflows using no-code/low-code platforms (n8n, Zapier, Make/Integromat) and custom automation scripts. Use when connecting SaaS tools, automating business processes, or orchestrating multi-step workflows. Also triggers on mentions of n8n, Zapier, Make, Integromat, webhook, cron job
writing-shell-scriptsWrites production-ready shell and automation scripts (Bash .sh and PowerShell .ps1) with a mandatory adversarial audit gate, MSP-grade error handling, input validation, idempotency, structured logging, and a paired README. Use when the user mentions: write a script, automate this with a script, depl
Third-party: tonone by tonone-ai (MIT). Vendored unmodified; see vendor/tonone/LICENSE.
200 skills · 100 agents · hooks
Loxihart AI enablement, solution architecture, agent building, and leadership communication.
37 skills
UI/UX, design systems, frontend execution, and the verified UI pattern library.
17 skills
Business operations, marketing, content, and digital product launches.
14 skills
Loxihart service desk, endpoint imaging, and knowledge-base operations.
7 skills
Build, patch, and register the FlashFusion Agent Control Center as a Cowork live artifact. Dark glassmorphic dashboard with live Supabase data and per-panel Demo fallback. PERSONAL lane only. v1.1 adds FF-PLAT-CORE-SOT canonical authority and refactors SKILL.md to a navigation layer per Anthropic progressive disclosure.
1 skill · 3 commands
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.
25 skills · 4 agents
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.
12 skills
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
4 skills · 3 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.