webdevtodayjason

REST API design patterns, OpenAPI specifications, versioning strategies, authentication, error handling, and security best practices. Use when designing APIs, creating endpoints, documenting APIs, or implementing backend services that expose HTTP APIs.

Code quality standards including SOLID principles, design patterns, code smells, refactoring techniques, naming conventions, and technical debt management. Use when reviewing code, refactoring, ensuring quality, or detecting code smells.

Scientific debugging methodology including hypothesis-driven debugging, bug reproduction, binary search debugging, stack trace analysis, logging strategies, and root cause analysis. Use when debugging errors, analyzing stack traces, investigating bugs, or troubleshooting performance issues.

DevOps patterns including CI/CD pipeline design, GitHub Actions, Infrastructure as Code, Docker, Kubernetes, deployment strategies, monitoring, and disaster recovery. Use when setting up CI/CD, deploying applications, managing infrastructure, or creating pipelines.

Modern frontend architecture patterns for React, Next.js, and TypeScript including component composition, state management, performance optimization, accessibility, and responsive design. Use when building UI components, implementing frontend features, optimizing performance, or working with React/Next.js applications.

Project planning methodologies including work breakdown structure, task estimation, dependency management, risk assessment, sprint planning, and stakeholder communication. Use when breaking down projects, estimating work, planning sprints, or managing dependencies.

Comprehensive security checklist covering OWASP Top 10, SQL injection, XSS, CSRF, authentication, authorization, secrets management, input validation, and security headers. Use when scanning for vulnerabilities, reviewing security, implementing authentication/authorization, or handling sensitive data.

Technical writing best practices including documentation structure, clear writing principles, API documentation, tutorials, changelogs, and markdown formatting. Use when writing documentation, creating READMEs, documenting APIs, or writing tutorials.

Evy — the subctl orchestrator persona. Loaded by the Evy daemon at boot; not used by workers. Canonical spec at docs/persona/evy.md.

Subscription Central — multi-account AI subscription orchestration toolkit. Activate this skill whenever you need to: spawn or control tmux orchestrator sessions, send Telegram messages or ask the operator a question, look up cross-account session state, or read/write the rate-limit radar. Trigger phrases: "spawn an orchestrator", "send a message to the operator", "ask the user a yes/no", "what's running across all my accounts", "kill that tmux session", "what's my rate-limit status", "stats from the dashboard", "let the user know we're stuck", "fire and forget on this question". Trigger conditions: any time you would otherwise shell out to tmux for session control, OR call Telegram's API directly, OR re-read transcripts to figure out what's running on another account. subctl is the canonical surface for all of these.

Autonomy doctrine for orchestrators and workers. When CLAUDE_AUTONOMY=full is set OR the user invokes "autonomous mode" / "12-hour mode" / "no babysit" / "fire and forget", THIS SKILL OVERRIDES "wait for approval", "ask the user", "confirm before proceeding" instructions in other skills (orchestrator-mode, tdd, team, find-skills). The orchestrator drives forward without per-step approval. Activate proactively whenever an orchestrator session is running with the user away (no message in last 5+ minutes) and there is non-trivial backlog.

How to hand off a task mid-flight — context summary, what's done, what's pending, where to find work-in-progress, and when to escalate instead. Use this skill when a worker needs to pass an unfinished task to a peer or back to the team lead — auto-compact pressure, scope shift, blocker outside the worker's tool set, end-of-shift, or running into the spawn-time context budget. Also load it when receiving a handoff so you know what shape to expect.

Node.js / Bun / TypeScript house style for subctl projects — runtime choice, imports, naming, errors, async patterns, testing. Load this skill whenever a worker is touching `.ts`, `.tsx`, `.js`, or `.mjs` files in a subctl-managed project. Use it instead of guessing the conventions from the surrounding code (the surrounding code may itself be drift). Defaults documented here are the operator's preferences as expressed across the v2.7.x release wave.

Switch Claude Code into a multi-pane orchestrator + team-agent workflow. Use this skill whenever the user says "orchestrator mode", "team mode", "/team", "/orchestrator-mode", or otherwise asks Claude to coordinate multiple parallel workers in iTerm2 panes instead of writing code directly. Also trigger if the user describes a task that clearly benefits from parallel decomposition across multiple worker panes (e.g. "split this into N parallel agents", "I want to see each agent in its own pane", "use team agents"). After activation, Claude acts purely as coordinator: planning work, dispatching workers via TeamCreate + Agent (with team_name), verifying outputs, and maintaining an ORCHESTRATION.md task ledger. Workers run in their own iTerm2 panes on the right side of the window while the orchestrator pane stays on the left.

Python house style for subctl-adjacent work — tooling (uv, ruff, pytest), imports, types, errors, async patterns, packaging. Load this skill whenever a worker is touching `.py` files in a subctl-managed project. Most subctl projects are Bun-first, but supporting utilities, ML code, and external integrations may be Python. These are the defaults to apply when the project's local CLAUDE.md doesn't override.

Rust house style for subctl-adjacent work — cargo, clippy, rustfmt, error handling with `thiserror` / `anyhow`, async patterns with tokio, testing. Load this skill whenever a worker is touching `.rs` files. Subctl has a Rust component (the policy bash-gate kernel) and several adjacent projects use Rust for performance-sensitive paths. These are the defaults to apply when the project's local CLAUDE.md doesn't override.

Audit your Claude Code static config for token waste and bloat. Use when the user says "audit my context", "context audit", "check my settings", "why is Claude so slow", "token optimization", or runs /context-audit. Reads the user's /context output to weight findings by actual token cost, then audits MCP servers, CLAUDE.md files, skills, settings.json, and permissions. Returns a health score with prioritized fixes. Scope: STATIC config only — settings, instruction files, MCP overhead, permission rules. Does NOT audit conversation-level bloat (oversized Bash outputs, repeat file reads, accumulating tool results) — that's a separate concern surfaced as a callout when relevant signals appear.

Record and maintain a project's follow-ups and to-dos in Jason's central Obsidian "closet" so loose threads survive across sessions and can be pulled from one list. Use proactively whenever work leaves a deferred, blocked, descoped, or noticed-but-not-fixed item; when the user says "add a to-do/follow-up", "log this for later", "the closet", "things to follow up on", "remind me to"; and at the end of a wave, session, or orchestration. Orchestrators and workers both log here — for each completed-with-leftovers or blocked dispatch.

Ephemeral, forkable Postgres databases via ghost.build — the agent-native database service. Use this skill when the user needs: a throwaway Postgres for testing, a safe fork of an existing database to experiment against without polluting state, an isolated DB per agent task, or any work that benefits from "create-fork-discard freely" semantics. Triggers: user says "ghost create", "fork the database", "spin up a Postgres", "I need a test DB", "give me a database for this agent", "ghost.build", or describes a scenario that would otherwise require a Docker postgres container + manual setup + manual teardown. The CLI lives at `~/.local/bin/ghost`. MCP tools are also available (install via `ghost mcp install`) and are the preferred surface for in-conversation database operations.

Node.js / Bun / TypeScript house style for your projects — runtime choice, imports, naming, errors, async patterns, testing. Load this skill whenever a worker is touching `.ts`, `.tsx`, `.js`, or `.mjs` files in a your project. Use it instead of guessing the conventions from the surrounding code (the surrounding code may itself be drift). Defaults documented here are the operator's preferences as expressed across the house conventions.

Maintain your Obsidian vault at <OBSIDIAN_VAULT_PATH>/. Every project gets the same standardized folder layout, lives under <Project Name>/, and stays current as work progresses. Trigger when the user says "Obsidian vault", "the vault", "update the vault", or asks for project status updates after work landed. Skill encodes the layout, the maintenance contract, the housekeeping rubric, and the human-AND-AI-readable format conventions.

Hard rules for working with a production database. Triggers when the user says "production database", "prod database", "prod DB", "live database", or when any database-modifying command (`prisma db push`, `prisma migrate`, `ALTER`, `DROP`, `UPDATE`, `DELETE`, `CREATE INDEX`, etc.) is being considered against a `DATABASE_URL` that resolves to production. Encodes the hard lesson that a stale-branch `prisma db push --accept-data-loss` can silently drop a column with live data. This skill prevents that pattern from recurring by mandating surgical, single-statement, idempotent SQL with explicit per-operation confirmation for anything destructive.

Python house style for general engineering work — tooling (uv, ruff, pytest), imports, types, errors, async patterns, packaging. Load this skill whenever a worker is touching `.py` files in a your project. Most your projects are Bun-first, but supporting utilities, ML code, and external integrations may be Python. These are the defaults to apply when the project's local CLAUDE.md doesn't override.

Rust house style for general engineering work — cargo, clippy, rustfmt, error handling with `thiserror` / `anyhow`, async patterns with tokio, testing. Load this skill whenever a worker is touching `.rs` files. Some projects have a Rust component (the policy bash-gate kernel) and several adjacent projects use Rust for performance-sensitive paths. These are the defaults to apply when the project's local CLAUDE.md doesn't override.

A test skill for the autoload integration test (alpha)

A test skill for the autoload integration test (beta)

A test skill for the autoload integration test (gamma)

Review, position, and polish Agent View Layer (AVL) / agent-first web projects: .agent pages, agent.txt manifests, AI-native rendering, MCP/API positioning, and marketing/category narrative.

Reconstruct, critique, and rewrite ArgentOS.ai positioning and website copy using Hermes's external-auditor role, the user's Medium/Substack scar-tissue articles, and stored Obsidian source-of-truth documents. Use when working on ArgentOS messaging, homepage copy, Core vs Business positioning, ecosystem framing, identity/philosophy pages, or claims/trust language.

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher-cli tool. Add blogs, scan for new articles, track read status, and filter by category.

Full pull request lifecycle — create branches, commit changes, open PRs, monitor CI status, auto-fix failures, and merge. Works with gh CLI or falls back to git + GitHub REST API via curl.

Complete guide to using and extending Hermes Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure Hermes, troubleshoot issues, spawn agent instances, or make code contributions.

Build and debug AppDirect platform API integrations — OAuth clients and scopes, GraphQL product/edition/pricing mutations, product integration configurations (event notification endpoints, SSO, inbound/outbound credentials, ping tests), and webhooks. Use this skill whenever the user is writing code that talks to AppDirect APIs, scaffolding marketplace event endpoints (subscription create/cancel/upgrade, user assign/unassign) in their SaaS, wiring SSO (OIDC/SAML/bookmark) for a marketplace product, calling mutations like createProduct or createProductIntegration, debugging failed ping tests or scope errors, or asking how their app should respond to AppDirect provisioning events.

Guide an AppDirect marketplace app submission from zero to approved publication with a 100% profile-completion score. Use this skill whenever the user mentions submitting, listing, publishing, or distributing a SaaS product on AppDirect or an AppDirect-powered marketplace — including phrases like "profile completion", "publication request", "marketplace manager approval", "add to marketplace", "app got rejected", or "why can't I submit my product". Also use it when auditing a product's submission readiness, diagnosing a stuck completion score, or planning a multi-product catalog rollout on AppDirect.

Operate the Hermes Familiar desk device — notify it, configure its button deck, provision Wi-Fi, run setup, and troubleshoot the link.

Operate Aegis Refine dataset jobs.

Use when searching the web, fetching/extracting page content, running natural-language browser automations, or creating remote CDP browser sessions from the terminal via the TinyFish CLI (cli-anything-tinyfish). API-key auth, JSON output, no browser OAuth.

The encrypted social network for AI agents. Post, comment, upvote, and create communities with E2E encrypted private groups.

Persistent memory system - automatic context capture and semantic search