Plugin Claude Code
A testable knowledge base of real engineering practice — every skill backed by its own deterministic eval suite, checked automatically with this repository's own eval runner (smeval).
Plugin Claude Code
A testable knowledge base of real engineering practice — every skill backed by its own deterministic eval suite, checked automatically with smeval, this repository's own eval runner.
Command Claude Code
Validate and run a skill's eval suite with smeval, then summarize the result.
Command Claude Code
Scaffold a new skill directory following this repo's spec.
Instructions file
Instructions for shennawardana23/skillme, a project described as: :pagefacingup: Skillme — Agent Skills Production-grade engineering skills for AI coding agents.
Skill Claude CodeCodex
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
Skill Claude CodeCodex
This skill should be used when the user asks to "build an agent with ADK Go", "create an ADK agent in Go", "add a tool to my Go agent", "use google.golang.org/adk", "compose sub-agents in ADK Go", or writes Go code against Google's Agent Development Kit for Go (google.golang.org/adk/v2). Provides verified API patterns…
Skill Claude CodeCodex
Use when a long-running agent session has drifted from its original goal, when reviewing why an agent kept working on something it wasn't asked to do, when designing checkpoint or re-anchoring behavior for an autonomous/long-horizon agent loop, or when asked about "agent focus", "agent losing the plot", or preventing…
Skill Claude CodeCodex
Use when designing or reviewing the tool/function interface an LLM agent calls through — naming and scoping tools, shaping observation payloads, writing error-recovery contracts, or deciding between ReAct-style and structured function-calling loops. Trigger phrases include "design a tool for the agent", "the agent…
Skill Claude CodeCodex
Use when planning how to hand an implementation task to an AI coding agent — deciding how to decompose the work, which model tier to route it to, when to define eval/regression criteria before starting, and where to focus human review of the agent's output. Trigger phrases include "break this down for the agent"…
Skill Claude CodeCodex
Use when designing team-level process, architecture standards, review policy, or hiring/evaluation criteria for an engineering org where AI agents generate a large share of the implementation. Trigger phrases include "how should our review process change for AI-generated code", "what architecture makes this codebase…
Skill Claude CodeCodex
Use when an AI coding agent has fixed a bug or modified API/backend logic and you need to prevent the same class of bug from recurring — especially in codebases with two parallel code paths (sandbox/mock mode vs production, or feature-flagged variants). Trigger phrases include "the agent keeps missing the same bug"…
Skill Claude CodeCodex
Guides internal interface and module-boundary design — Go interfaces, package APIs, and cross-team contracts inside a codebase, as distinct from the wire-level REST/RPC contract shape covered by the api-design skill. Use when defining an interface between packages, deciding where an interface should live, choosing…
Skill Claude CodeCodex
Guides REST and RPC API design across Go, TypeScript, and PHP backends. Use when designing new endpoints, defining request/response contracts, planning breaking or additive schema changes, or reviewing an existing API for consistency in error handling, pagination, or naming.
Skill Claude CodeCodex
Use when choosing or designing an architecture for running a coding agent repeatedly with little or no human intervention — a scripted sequence of non-interactive agent invocations, a parallel-generation loop, an iterative PR-and-merge loop, or a spec-driven multi-agent pipeline. Trigger phrases include "set up an…
Skill Claude CodeCodex
Guides backend service architecture — layering, N+1 query prevention, caching, retries, rate limiting, and background job processing, in Go primarily and TypeScript/PHP where the pattern is language-agnostic. Use when structuring handler/service/repository layers, reviewing a service for N+1 queries, adding a cache in…
Skill Claude CodeCodex
Use when the user asks to "deprecate this endpoint/field", "set a sunset date", "plan a breaking change rollout", "write a deprecation notice", "how long should we support the old version", or is retiring an API version, a config format, a CLI flag, or an internal library's old interface. Guides the organizational…
Skill Claude CodeCodex
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
Skill Claude CodeCodex
Use Chrome DevTools MCP to inspect, debug, and verify anything that runs in a browser — DOM structure, console errors, network requests, performance traces, and accessibility. Use when building or fixing browser UI, diagnosing a runtime bug that isn't visible from source code alone, or verifying a fix actually works…
Skill Claude CodeCodex
This skill should be used when the user asks to "triage this bug", "what severity is this", "classify this incident/bug", "is this a Sev1 or Sev2", "what priority should this ticket be", or is deciding SLA/response urgency for a reported defect. Use for assigning severity and priority to bugs and incidents…
Skill Claude CodeCodex
Guides integrating a hotel PMS with online travel agencies (OTAs) via a channel manager. Use when implementing rate/availability push, reservation pull, reconciling a channel-manager sync failure, or reviewing code that treats an OTA's view of availability as always in sync with the PMS.
Skill Claude CodeCodex
Guides CI/CD pipeline design — quality gates, GitHub Actions for Go/TypeScript/PHP, feature-flag-decoupled deploys, secrets scoping, and pipeline optimization. Use when setting up or modifying a build/test/deploy pipeline, adding an automated quality gate, configuring CI secrets, or diagnosing a slow or flaky…
Skill Claude CodeCodex
Use when the user asks to "set up CODEOWNERS", "who should review this", "define module boundaries", "this service keeps needing changes across three teams", "reorganize our repo structure", or is designing team/service boundaries, module ownership, or review-routing rules. Guides applying CODEOWNERS-based review…
Skill Claude CodeCodex
Runs code review as a change-management process — right-sizing the diff, labeling findings by required-vs-optional severity, applying structural remedies for complexity, and resolving reviewer/author disagreements. Use when a change needs splitting before review, when review comments need severity labels, when a…