rcdelfin
UserCross-harness AI skills & instructions — one source of truth for every AI coding assistant
Categories
Indexed Skills (27)
clickup
Work with ClickUp from Hermes: MCP server setup, REST API patterns, task card pulls, and triage workflows.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
clickup-issue-workflow
Fix a ClickUp-tracked issue end-to-end by ID (e.g. GYMED-100): ingest the card into the local wiki → branch as fix/{clickup_id} → fix on the branch → push (no MR until asked) → wait for the ai_code_review pipeline → resolve every review thread. Uses the clickup, tweak, git-actions, mr-review, and local-wiki skills. Trigger: a ClickUp-tracked issue keyed by its ID (e.g. 'fix GYMED-100').
dox
Self-documenting AGENTS.md hierarchy for AI agents. Root contains project-wide rules and child index; child AGENTS.md files in subdirectories define local contracts. Agent walks the full path from root to target before any edit, updates affected files after. No installation needed — just Markdown instructions. From agent0ai/dox. Load when: initializing project context, creating AGENTS.md files, encountering a DOX hierarchy, or when Rule 4/6 of global behavioral guidelines references DOX pattern.
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
improve
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
local-wiki
Ingest source content (ClickUp cards, meeting notes, transcripts, specs) into the project's governed local knowledge base. Dynamically locates the wiki (prefers docs/wiki/), then obeys the wiki's own AGENTS.md for structure and rules. Trigger: 'ingest into the wiki', 'add to wiki', 'capture this card/note locally', or any workflow that needs to persist a source doc locally before working on it.
mr-review
Fetch and resolve GitLab MR review feedback (AI Assistant, human reviewers, bots). Trigger on: fix MR review, address review comments, fix AI assistant findings, resolve MR feedback, or any mention of MR review + fix. Covers the full loop: fetch comments → categorize by severity → fix locally → test → commit → push.
openspec
OpenSpec artifact-driven workflow. Covers OPSX commands, schemas, project config. Use when applying the artifact-driven workflow (OPSX), planning or reviewing changes based on artifact dependencies, or working with OPSX commands and schema/template resolution. Keywords: OPSX, artifact graph, /opsx:.
ponytail
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.
analogical-thinking
Apply analogical reasoning to problems — find structural parallels across domains, ask the 4 core questions, detect when analogies break. Use when stuck on novel problems or when domain-specific tools aren't sufficient.
laravel-11-12-app-guidelines
Guidelines and workflow for working on Laravel 11 or Laravel 12 applications across common stacks (API-only or full-stack), including optional Docker Compose/Sail, Inertia + React, Livewire, Vue, Blade, Tailwind v4, Fortify, Wayfinder, PHPUnit, Pint, and Laravel Boost MCP tools. Use when implementing features, fixing bugs, or making UI/backend changes while following project-specific instructions (AGENTS.md, docs/).
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers, implementing Sanctum auth flows, building Livewire components, optimising Eloquent queries, or writing Pest/PHPUnit tests for Laravel features.
pest-testing
Use this skill for Pest PHP testing in Laravel projects only. Trigger whenever any test is being written, edited, fixed, or refactored — including fixing tests that broke after a code change, adding assertions, converting PHPUnit to Pest, adding datasets, and TDD workflows. Always activate when the user asks how to write something in Pest, mentions test files or directories (tests/Feature, tests/Unit) or architecture tests. Covers: it()/expect() syntax, datasets, mocking, browser testing, arch(), Livewire component tests, RefreshDatabase, and all Pest 4 features. Do not use for editing factories, seeders, migrations, controllers, models, or non-test PHP code.
php-best-practices
PHP 8.x modern patterns, PSR standards, and SOLID principles. Use when reviewing PHP code, checking type safety, auditing code quality, or ensuring PHP best practices. Triggers on "review PHP", "check PHP code", "audit PHP", or "PHP best practices".
systems-thinking
Apply systems thinking to every engineering decision — trace state ownership, feedback loops, and deletion blast radius before writing, reviewing, or debugging code. Integrates existing skills (debugging, code review, security audit, planning) into a unified systems lens.
tailwindcss-development
Always invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex/grid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3/v4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML/CSS component, CSS file audits, build tool configuration, and vanilla CSS.
tweak
Lightweight change planning — produces a self-contained four-artifact plan (proposal, specs, design, tasks) and, on archive, folds delta specs into a system-wide source of truth. Stores changes under `plans/<slug>/` when available, adapting to coexist with other content; otherwise under `docs/tweaks/<slug>/`. Standalone: no CLI, no schema, no tool integrations. Use when you want OpenSpec-style change planning without installing `@fission-ai/openspec`. Trigger words: tweak, plan change, proposal, design doc, RFC, change doc, scaffold feature, change set.
caveman-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
scrutinize
Outsider-perspective end-to-end review of a plan, PR, or code change. First questions intent and whether a simpler/more elegant approach would achieve the same goal, then traces the actual code path (not just the diff) to verify the change does what it claims. Output is concise, actionable, and every call carries its rationale. Trigger on /scrutinize and proactively whenever the user asks to review, audit, sanity-check, or get a second opinion on a plan, PR, diff, design doc, or proposed code change.
skill-orchestration
Skill router — activates at the start of any non-trivial task to match the task to the right domain skills and MCP tools before acting. Trigger proactively on every task, or when unsure which skills apply. Provides a decision matrix mapping task signals to skills and MCP routes. Reduces missed skill activations and ensures MCP tools are used where they add value.
eloquent-best-practices
Best practices for Laravel Eloquent ORM including query optimization, relationship management, and avoiding common pitfalls like N+1 queries.
security-audit-light
Perform a PR-scoped security audit on a small to medium code change (1-20 files, additive endpoint, schema change, refactor). Produces a structured findings table with confidence scores, no false positives, and a clean verdict. Trigger only when the user explicitly asks for a "security audit", "security review", "vulnerability check", "is this safe to ship", or "OWASP check" of recent changes. NOT for greenfield threat modeling, full-codebase reviews, or infrastructure audits — those need heavier tooling. NOT for proactive scanning while writing code.
security-best-practices
Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.