nerymurillohnd
- 40 skills
- 0 followers
- yesterday last updated
- ▌ Testing Before Implementation · nerymurillohnd bundleImplements code changes test-first (TDD). Writes a failing test that names the break it catches, watches it fail for the right reason, writes the minimal code that passes, then checks the full suite, lint and types against a baseline, recording the command and output of each run. Use when implementing a feature, fixing a bug or changing behavior in code that can be tested, or when the user asks for TDD, test-first or red-green-refactor, even if they don't mention tests. When the work spans several steps or files, plan it first with planning-before-execution and apply this skill to each code task. Not for configuration-only edits, documentation, visual styling, or adding tests to existing code without a behavior change.
- ▌ Writing Hooks · nerymurillohnd bundleUse for every request or task that creates, rewrites or wires a hook or hook script for Claude Code or Cowork, including the hooks entry in settings.json, even when the user never says hook. Load it before or with update-config whenever that settings change is a hook. That includes setting something up to run automatically, from now on, in every session or every time an event happens (whenever Claude edits a file, after it reads files, before a command runs, when a session starts or ends), to block, allow, log or check commands, tool calls, prompts or file changes, to make Claude always or never do something with a guarantee instead of a memory or an instruction, and to add hooks to a plugin, a skill, a subagent or user, project, local or managed settings. Writes hooks of every type (command, HTTP, MCP tool, prompt, agent) from the current official docs, picks the optimal event and location, and verifies them with real inputs. Not for Git hooks, React hooks or webhooks.
- ▌ Planning Before Execution · nerymurillohnd bundlePlans multi-step work before anything changes. Researches current official sources and the code, then writes a self-contained, verifiable plan with a file map, tasks, checks and acceptance criteria, and sets how completion is proven. Use whenever a task spans several steps or files, changes architecture, migrates or upgrades something, touches data or deployments, or is costly to redo, and whenever the user asks to plan, scope, break down or design an approach, even if they never say plan. Also use for multi-step operations or content work that Claude will carry out. Not for one-line edits, questions, explanations, writing a plan document as the deliverable itself (such as a business plan), or work that already has an approved plan.
- ▌ Claude Md And Rules · nerymurillohnd bundleRequired before creating or changing any Claude Code instruction file (CLAUDE.md, CLAUDE.local.md, ~/.claude/CLAUDE.md, .claude/rules/**/*.md), even a one-line addition, because every change must be checked against the whole instruction set first. Also use it to review, audit, debug, reorganize or refactor these files; whenever the user wants a behavior persisted ("remember this", "make sure this doesn't happen again", "Claude keeps doing X", "make it stop"), including before configuring a hook for it, to find why the written instruction failed; when a rule is ignored or not loading; or when they mention project or global instructions or memory files. Finds contradictions, semantic duplicates, ambiguity, no-op and misplaced lines and procedures that should be skills; decides CLAUDE.md vs always-on or path-scoped rules vs skill vs hook; includes a read-only checker. Not for writing skills, hooks, settings, READMEs or one-off prompts, except to recommend them.
- ▌ Tailwind Official Docs · nerymurillohnd bundleLearn from the official Tailwind CSS v4 documentation for knowledge and guidance, and prefer it over training knowledge. Always use it first, before any other skill, when the user asks about Tailwind and when you work on or plan anything Tailwind on your own, from code, integration, setup and migration to front-end design and styles.
- ▌ Plugin Testing And Debugging · nerymurillohnd bundleTests, troubleshoots and debugs Claude Code plugins with the official CLI - claude plugin validate, list, details, eval and eval init, /plugin, /reload-plugins and --plugin-dir - and the documented loading rules. Use when a plugin, marketplace or skills-directory plugin will not install, load, enable, update or run its skills, hooks, MCP or LSP servers; when a copy behaves differently installed than with --plugin-dir; when a plugin keeps loading after being turned off; when reading a plugin error, Errors-tab entry or exit code; when reviewing a plugin or marketplace before publishing; and when writing, running, reading or gating CI on plugin evals and graders. Also use it in cloud sessions, project threads, Claude on the web, desktop and mobile, and the Agent SDK, where plugins load differently. Use it even when the user only pastes an error or says "my plugin doesn't work".
- ▌ Svelte Best Practices · nerymurillohnd bundleWrites, reviews and explains Svelte 5 and SvelteKit 3 code by current practice (runes, snippets, events, routes, load, forms, env, config) and migrates SvelteKit 2 or Svelte 4 projects. Use for any task that writes or changes Svelte or SvelteKit code, including a pasted component, a route or a param matcher.
- ▌ Public Marketplace Dev · nerymurillohnd bundleCurrent knowledge, CLI commands and references from the official sources that teach Claude how to create, build, develop, structure, publish and maintain a public Claude Code plugin marketplace hosted on GitHub. Use when the user asks about or requests, or the task involves, designing or planning, creating, developing, structuring, versioning, tagging, auditing, troubleshooting and debugging, adding components or dependencies, releasing or distributing, and maintaining or answering questions about plugins in a Claude Code plugin marketplace served to third parties from a public GitHub repository. Use only for plugins that belong to such a marketplace or repository.
- ▌ TS Lifecycle · nerymurillohnd bundleResearches, writes, edits, reviews and verifies TypeScript and JavaScript code with official sources, LSP code intelligence and behavioral evidence. Use for every task that writes, edits, audits or answers questions about TypeScript or JavaScript code, including scripts, tsconfig and jsconfig, modules, declarations, migrations, type errors, editor and tsc disagreements, broken builds, failing checks and cross-tool behavior. Not for other languages, comment-only or formatting-only edits, or syntax explanations that depend on neither the project nor a version.
- ▌ Cleanup And Debug · nerymurillohnd bundleAudits a Git repository and its GitHub project, local and remote, for what was left behind, then plans and runs the cleanup the user approves, behind a verified backup. Finds stale, merged or diverged branches, orphaned worktrees, forgotten stashes, abandoned pull requests, failed or stuck workflow runs, dangling commits, oversized blobs, secrets ever committed and leftovers of interrupted operations. Use when the user wants to audit, clean up or tidy a repository, prune old branches, compare the local clone with GitHub, recover lost work or a stash, or find the commit that introduced a bug, even if they only say the repository is a mess. Not for reviewing code or docs, taking a pull request to merge, setting up templates, forms or labels, or fixing GitHub Actions workflows, which this plugin's other skills cover.
- ▌ Github Files Setup · nerymurillohnd bundleWrites a GitHub repository's pull request templates, issue forms, discussion forms, labels, Dependabot configuration and CODEOWNERS, adapted to that repository from reference models, and sets its merge message and, with approval, which merge methods it allows. Use when the user wants to set up, add or update any of these, or to make a repository's issues and pull requests arrive with the information maintainers need, even if they only say that issues arrive incomplete. Not for CONTRIBUTING, SECURITY, SUPPORT, code of conduct or README files, filing or triaging individual issues, taking a pull request to merge, auditing or cleaning up a repository, or auditing and fixing GitHub Actions workflows, which this plugin's other skills cover.
- ▌ CLI Commands Guide · nerymurillohnd bundleExact, current reference for the Claude Code plugin CLI and for how plugins install, load and update - every claude plugin and claude plugin marketplace subcommand, every /plugin form, /reload-plugins, --plugin-dir and --plugin-url, with flags, defaults, aliases, messages, JSON fields, exit codes, scopes, minimum versions and the gotchas that break plugin work. Use for any task or question that involves Claude Code plugins of any kind, with or without a marketplace or a repository - designing, planning, building, testing, installing, enabling, configuring, updating, validating, evaluating, tagging, releasing, debugging or removing plugins, mods, skills-directory plugins, synced plugins or marketplaces; scripting plugin commands with --json; or reading a plugin command's output, error or exit code. Load it before answering from memory about anything that involves plugins.
- ▌ Claude Github Actions · nerymurillohnd bundleDiagnoses, audits, hardens and repairs GitHub Actions workflows, specializing in workflows that run Claude through anthropics/claude-code-action. Finds why a Claude step failed, did nothing or posted nothing; audits workflow files for injection, excess permissions, unpinned actions and claude-code-action misconfiguration, with an exact patch per finding; and repairs failing CI on the default branch, asking the user before any rerun, workflow change or push. Use when the user asks why a claude-code-action step failed or never commented, wants a workflow reviewed, audited or hardened, or wants the default branch green again, even if they only say "CI is broken" or "the Claude review did nothing". Not for a pull request's failing tests or code, a repository cleanup, or writing templates and forms, which this plugin's other skills cover.
- ▌ Tailwind UI Design · nerymurillohnd bundleDesign, build, refactor and review Tailwind CSS v4 interfaces with a product designer's craft, from visual hierarchy and design tokens to every state and visual verification. Always use it to create, redesign, polish or review any page, view or component, and for any class edit that changes how something looks or reads.
- ▌ Review Evals · nerymurillohndReviews a Claude Code plugin's eval cases before paid runs — checks that each case measures what the plugin adds over plain Claude, that graders count in both arms, that triggering is measured as a rate, and that fixtures are correct; dry-runs fixtures and applies fixes only after asking. Use when the user asks to review, check or debug plugin eval cases, after claude plugin eval init drafted a suite, or when scores or deltas look wrong. Not for writing a suite or for skill-creator's evals.json.
- ▌ Test Install · nerymurillohnd bundleTests a Claude Code plugin the way its users receive it — installs a copy from a commit into a throwaway Claude Code configuration, checks that every file arrived and that it loads, runs its eval suite or real requests against that copy, then cleans up; can also package it for a Claude app upload. Use when the user wants to test or smoke-test a plugin as an end user would install it, before publishing or releasing it, or asks if it works outside their own setup. Not for reviewing eval cases.
- ▌ Write Handoff · nerymurillohnd bundleWrites this project's end-of-session handoff, the file the next session starts from with what was done, decided, corrected, learned and left open. Use when the user is wrapping up a work session, says they are stopping for now, or asks for a handoff, session summary or notes for the next session.
- ▌ Write Records · nerymurillohnd bundleWrites architecture decision records (ADRs) and keeps a technical-debt ledger. Use when an important decision is made, a problem cannot be fixed now, or logged debt is closed.
- ▌ Hook Development · nerymurillohnd bundleUse when the user asks or the task involves designing, planning, creating, writing, scaffolding, auditing, or debugging Claude Code hooks. If any other applicable skill is present, load this first and query others on demand for best results. Do not use for Git hooks.
- ▌ Cc Mods Guidance · nerymurillohndDesigns, creates, reviews, tests, debugs, and maintains Claude Code mods, verifying behavior against the current official documentation and the installed build's generated declarations. Use when working with hooks modules, mods API calls, event interception, mod UI, reactive or persistent state, mod policy controls, or mod distribution.
- ▌ Auto Pr Lifecycle · nerymurillohndTakes a GitHub pull request from its current stage to merge. Opens it, watches its checks and reviews, fixes failing CI and review findings, answers and resolves review threads, and merges it, asking the user before every push and before the merge. Use when the user wants to open a pull request for a branch, ship or land a branch, babysit or check on a PR, fix a PR's failing checks, address review comments, get a PR merged, or resume a stalled PR, even if they only say "ship this" or "why is my PR red". Not for a plain commit or push, a repository's templates, forms or labels, a repository audit or cleanup, or auditing and hardening GitHub Actions workflows, which this plugin's other skills cover.
- ▌ Plugin Evals · nerymurillohnd bundleExpertise in Claude Code plugin evals (claude plugin eval, eval init). Designs suites that prove what a plugin adds; writes cases, graders, fixtures and MCP mocks; gives the commands to run, debug and gate them in CI such as GitHub Actions; reads results, checked against the installed CLI and live docs. Use for any task about evaluating, testing or benchmarking a plugin or its skills, agents, hooks or MCP servers, even when the user never says "eval". Not for Claude API app evals (/claude-api build-eval).
- ▌ Prompt Writer · nerymurillohnd bundleCreates, rewrites, audits, and refines prompts for Claude, tailored to the target model, effort level, and execution setup. Use when the user wants to turn an idea into actionable instructions, improve an existing prompt, troubleshoot unsatisfactory output, or design a prompting workflow. Clarifies intent conversationally, recommends an appropriate strategy, and delivers copy-ready prompts with follow-up guidance when useful.
- ▌ Doc Keeper · nerymurillohnd bundleUse when directly creating, completing, auditing, updating, or repairing changelogs, release history, or ADRs, and after completed work, release preparation, or explicit architectural decisions. Do not use for routine implementation, generic README prose, formatting-only work, or test-only work.
- ▌ Hook Creator · nerymurillohnd bundleDesign, create, integrate, review, test, or debug Codex lifecycle hooks, including hooks.json, inline TOML, command and MCP handlers, background execution, managed and plugin hooks, subagent events, trust, CI/CD, and GitHub Actions. Use when Codex must turn an operational intent into correctly wired hooks or explain why an existing hook does not work. Do not use for Git hooks or unrelated OpenAI Agents SDK callbacks.
- ▌ Declarative Plugin Pipeline · nerymurillohnd bundleUse when creating, changing, validating, or releasing a Codex Essentials plugin package, its manifest, skills, hooks, apps, MCP resources, documentation, marketplace registration, or release metadata. Do not use for unrelated repository work.
- ▌ Live Research · nerymurillohnd bundleVerify time-sensitive and change-sensitive claims with current authoritative sources. Use for current facts about software, APIs, integrations, regulations, statistics, people, products, compatibility, prices, schedules, or news, even when the user does not explicitly ask to browse.
- ▌ Block No Verify · nerymurillohnd bundleRecommend and, only with approval, install and maintain a Codex hook that blocks Git --no-verify, --no-gpg-sign, and falsy commit.gpgsign bypasses. Use for Git commit, signing, hook-policy, or verification-bypass work; do not invoke for ordinary read-only Git inspection.
- ▌ Astro Commands · nerymurillohnd bundleUse when planning or executing Astro project work that depends on Astro CLI behavior, dev or preview servers, integrations, type generation, CI checks, flags, version drift, or official command selection.
- ▌ Prompt Architect · nerymurillohnd bundleUse when writing, improving, auditing, structuring, or generating prompts for agentic, coding, research, repository, production-adjacent, multi-step, high-risk, or underspecified work.
- ▌ Repo Maintenance · nerymurillohnd bundleUse when auditing, creating, or updating repository READMEs, changelogs, ADRs, maintenance debt records, licenses, or conditional skill metadata. Propose the documentation structure before writing it; do not use for source-code implementation or remote release actions.
- ▌ System Ops Audit · nerymurillohnd bundlePlan, run with approval, or analyze a read-only macOS operational baseline for one local machine. Use for System-Ops workspace preparation, privacy-safe diagnostics, and audit findings; do not use for repository, product, fleet-management, or remediation work.
- ▌ Svelte Architect · nerymurillohnd bundleUse when planning Svelte 5 or SvelteKit app architecture, major features, migrations, routing models, state ownership, adapter strategy, or shared component systems before implementation.
- ▌ Configure Prettier · nerymurillohnd bundleUse when auditing, proposing, configuring, upgrading, or troubleshooting repository Prettier setup, editor integration, formatting checks, hooks, CI, conflicts, or version drift. Require explicit approval before mutation.
- ▌ Sveltekit Engineer · nerymurillohnd bundleUse when implementing, reviewing, or debugging SvelteKit routes, layouts, load functions, form actions, endpoints, hooks, cookies, auth, env, adapters, redirects, or server-only modules. Do not use for component-only work.
- ▌ Svelte Verification · nerymurillohnd bundleUse when verifying Svelte or SvelteKit work before completion, including MCP docs, Svelte CLI commands, autofix, checks, tests, builds, preview servers, browser validation, diagnostics, or failure recovery.
- ▌ Prettier After Edit · nerymurillohnd bundleUse after Codex edits files that should be formatted with Prettier immediately. Resolve project-local Prettier first, fall back to PATH, and do not install dependencies or change configuration.
- ▌ Audit And Cure Memories · nerymurillohnd bundleUse when auditing, verifying, reconciling, or preparing approval-gated updates for Codex memory artifacts at project scope, global scope, or both, including stale-memory cleanup, consistency review, and memory correction.
- ▌ Svelte Component Engineer · nerymurillohnd bundleUse when writing, editing, reviewing, or debugging Svelte 5 components, .svelte.ts modules, props, runes, snippets, bindings, events, accessibility, styles, or component tests. Do not use for route/server-only SvelteKit work.
- ▌ Skill Design Standards · nerymurillohnd bundleDesign, audit, or improve Agent Skills and Codex skills, including plugin-bundled skills. Use when reviewing or changing SKILL.md structure, workflow instructions, supporting resources, or agents/openai.yaml.