All authors
Claude Skills by shennawardana23
github.com/shennawardana23150 skills1 installs86 views
- My OwnThis skill should be used when the user asks to "critique this as my own principal engineer", "give me your harshest technical review", "would you sign off on this architecture", "judge this against my own standards", or wants an adversarial, opinionated critique of a design, codebase, or AI-infrastructure proposal from a principal-engineer persona spanning backend, frontend, and AI infrastructure architecture — not a policy reference. Judges a specific artifact against strict, verifiable exi...Votes: 0GitHub stars: 2
- Mysql PatternsGuides MySQL/MariaDB query design, indexing strategy, data types, and concurrency patterns — the InnoDB-specific counterpart to postgres-patterns. Use when choosing a primary key strategy, picking a charset, writing an UPSERT, deciding on isolation level, or porting a query pattern from PostgreSQL to MySQL/MariaDB (or the reverse) and needing to know what actually differs.Votes: 0GitHub stars: 2
- Observability And InstrumentationGuides instrumenting Go (and TypeScript/PHP) services with structured logging, RED/USE metrics, and distributed tracing so production behavior is diagnosable from telemetry alone. Use when adding logging, metrics, or tracing to a new feature or service, reviewing a PR that adds retries/queues/external calls, setting up or reviewing alerting rules, or when a production issue took too long to diagnose because the data wasn't there.Votes: 0GitHub stars: 2
- One On Ones And Feedback FrameworksThis skill should be used when the user asks to "give feedback using SBI", "structure a 1:1", "how do I tell my report about this issue", "write feedback for a performance review", or needs to deliver behavioral feedback (positive or corrective) or structure a recurring one-on-one meeting. Use for the structure and delivery of feedback and 1:1s — not for formal performance-review calibration processes.Votes: 0GitHub stars: 2
- OrchestratorUse when a request could be handled by more than one skill in your catalog, or the task type isn't obvious from the wording (e.g. it mixes a code review with a security question, or a feature request with test generation). Trigger phrases include "not sure which skill applies", "this touches security and code style", "route this to the right skill", or "what's the process for a request like this". Teaches how to build and use a signal-to-skill routing table rather than guessing.Votes: 0GitHub stars: 2
- Performance OptimizationGuides measurement-first performance optimization for Go backend services (pprof profiling, allocation reduction, N+1 avoidance) and frontend Core Web Vitals for the Vue/Nuxt stack. Use when a performance requirement exists, a regression is suspected, profiling reveals a bottleneck, or someone proposes an optimization with no measurement backing it.Votes: 0GitHub stars: 2
- PerformanceOptimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit". For Go backend profiling/measurement-first triage use performance-optimization instead — this skill is the deep frontend reference (budgets, caching, image/font formats, third-party scripts, code splitting).Votes: 0GitHub stars: 2
- Php Codeigniter Legacy Auth SessionGuides authentication and session security for classic CodeIgniter 2.x/3.x applications - session/cookie design, CSRF, and object-level authorization, where the framework's built-in mechanisms are weaker or differently-shaped than CodeIgniter 4's. Use when reviewing login/session code, a cookie-setting call, or an endpoint that accepts an identifier (hotel_id, tenant_id, resource_id) from client input in a classic CodeIgniter app.Votes: 0GitHub stars: 2
- Php Codeigniter Legacy PatternsGuides classic CodeIgniter 2.x/3.x applications (the application/ directory, bcit-ci/CodeIgniter, no PHP namespaces) - a fundamentally different framework generation from CodeIgniter 4. Use when working in a codebase with an application/ directory and CI_VERSION below 4, extending MY_Controller or a *_model class, adding a route, or reviewing code that assumes CI4-style namespaces or DI.Votes: 0GitHub stars: 2
- Php Codeigniter PatternsGuides CodeIgniter 4 application architecture — Controllers, Models (Query Builder, not an ORM), Entities, the Validation library, Filters (CI4's middleware equivalent), and Services. Use when building a CI4 controller or route, working with a CI4 Model or Entity, wiring a Filter to a route group, or adding a custom Service.Votes: 0GitHub stars: 2
- Php Codeigniter SecurityUse when configuring CodeIgniter 4-specific security mechanisms - CSRF protection mode (cookie vs session), output escaping with esc(), Config\App's baseURL and forceGlobalSecureRequests, or Model $allowedFields mass-assignment guards. For generic web-security review (injection, secrets, auth-vs-authz on any stack) use security-review instead; this skill is for getting CI4's own framework mechanisms configured correctly.Votes: 0GitHub stars: 2
- Php Codeigniter TddDrives CodeIgniter 4 test development — CIUnitTestCase, DatabaseTestTrait's migrate/refresh/seed lifecycle, the dedicated `tests` database group, and FeatureTestTrait for HTTP-level assertions. Use when writing or fixing a CodeIgniter 4 test, when a test touches the database, or when a test suite is unexpectedly slow or appears to be affecting the wrong database.Votes: 0GitHub stars: 2
- Php Codeigniter VerificationUse when asked to verify a CodeIgniter 4 project before a PR, after a major refactor or dependency upgrade, or before deploying to staging/production. Runs a phased env-check -> lint -> test -> security -> migration -> route/filter -> deploy-readiness pipeline via the spark CLI, stopping at the first failing gate rather than reporting every phase's output at once.Votes: 0GitHub stars: 2
- Planning And Task BreakdownBreaks an existing spec or clear requirement into a dependency-ordered, sized task list with checkpoints and parallelization notes. Use when a task feels too large to start, when scope needs estimating, or when work can be split across parallel agents/sessions. For a single lightweight plan document for one request, use planning instead.Votes: 0GitHub stars: 2
- PlanningConverts a single feature request, bug report, or vague task into one short, ordered plan document with a goal, acceptance criteria, sized steps, and risks. Use for a single task or feature that needs structure before work starts. For decomposing an already-specced body of work into a dependency-ordered task list, use planning-and-task-breakdown instead.Votes: 0GitHub stars: 2
- Postgres Hotel PartitioningThis skill should be used when the user asks to "write a query for a hotel-partitioned table", "review this SQL for partition safety", "add a hotel_id filter", "check partition pruning", "write a migration for a partitioned table", or writes/reviews Go or SQL code touching any PostgreSQL table partitioned by hotel_id. Provides patterns for keeping queries, joins, and migrations partition-safe.Votes: 0GitHub stars: 2
- Postgres PatternsGuides PostgreSQL query design, indexing strategy, data types, and row-level security patterns — the query/schema layer, as distinct from the migration-execution safety covered by database-migrations and the hotel_id partition-pruning rules covered by postgres-hotel-partitioning. Use when choosing an index type, designing a composite or partial index, picking a column data type, writing an UPSERT or a queue-processing query, or setting up row-level security.Votes: 0GitHub stars: 2
- Production SchedulingCodified expertise for production scheduling, job sequencing, line balancing, changeover optimization, and bottleneck resolution in discrete and batch manufacturing, including Theory of Constraints/drum-buffer-rope, SMED, OEE analysis, and disruption response. Use when scheduling production, resolving bottlenecks, optimizing changeovers, responding to a disruption (breakdown, shortage, absenteeism), or balancing a manufacturing line.Votes: 0GitHub stars: 2
- Project Guidelines ExampleShows what a project-specific guidelines document (architecture map, directory contract, response/error shape, exact commands, deployment steps, Always/Ask-first/Never boundaries) needs to contain to be useful to an agent working in that codebase, with one worked example. Use when asked to write a CLAUDE.md-style project guide, a "house rules" doc for a specific repo, or a project-onboarding reference -- not when authoring a new reusable skill for this catalog (see skill-catalog-authoring for...Votes: 0GitHub stars: 2
- Prompt OptimizerAnalyze a draft prompt, diagnose gaps, match it to relevant skills already in this catalog, and output a ready-to-paste improved prompt — advisory only, never executes the task itself. Use when the user says "optimize this prompt", "improve my prompt", "how should I prompt for X", or pastes a draft prompt asking for feedback. Do not use when the user wants the task executed directly or says "just do it".Votes: 0GitHub stars: 2
- Qa Test Strategy DesignThis skill should be used when the user asks to "design a test strategy", "figure out our testing approach for this feature", "how much should we test this", "what's our test plan for this release", or needs to decide test-level allocation and where to focus coverage before writing any actual tests. Use for planning what to test and how much, at the feature or release level — not for writing or debugging individual tests (see e2e-testing for Playwright execution, test-driven-development for r...Votes: 0GitHub stars: 2
- Raw Sql Querybuilder Testing PatternsGuides Go services that use database/sql directly with a lightweight in-house query builder (not an ORM like GORM or a codegen tool like sqlc), including how to make repositories unit-testable via mock-generated interfaces. Use when writing or reviewing a repository method built on database/sql, adding a new repository interface for mocking, or debugging a nil-scan/mock-drift test failure.Votes: 0GitHub stars: 2
- Release Management And Rollback PlanningThis skill should be used when the user asks to "plan a canary release", "design a rollout strategy", "write a rollback runbook", "should this go behind a feature flag", "how do we release this safely", or is deciding how a change reaches production and how to back out of it if something goes wrong. Use for the rollout/rollback strategy itself — not for the CI/CD pipeline mechanics or the code change being released.Votes: 0GitHub stars: 2
- ResearchRun a structured, codebase-first technical research workflow to answer a specific engineering question — check internal docs and source before searching externally, verify claims against actual code, and stop within a bounded number of iterations. Use for narrow, verifiable technical questions like "does this library version support X" or "which error-handling pattern does this codebase use", not for open-ended topic research.Votes: 0GitHub stars: 2
- Roadmapping And Tradeoff CommunicationGuides building Now/Next/Later, outcome-based roadmaps and communicating tradeoff decisions to stakeholders who push for a specific feature with a hard date. Use when the user asks to "build a roadmap," "create a Now/Next/Later roadmap," "turn this feature list into an outcome roadmap," "respond to a stakeholder demanding a date," "push back on a feature request," "explain why we can't commit to this date," or is reviewing a roadmap that is really just a dated feature list.Votes: 0GitHub stars: 2
- ScaffoldGenerates a complete, compilable project scaffold -- directory structure, entry point, config, Makefile, README -- for a new Go (or other language) service, following clean architecture and dependency injection instead of global state. Use when starting a brand-new service or CLI from nothing, not when adding a feature to an existing project.Votes: 0GitHub stars: 2
- Search FirstSearch for an existing solution — in this repo, as an installed MCP server, as an existing skill, or as a maintained package — before writing custom code for a new utility, dependency, or integration. Use before creating a new helper/abstraction, before adding a dependency, or whenever a request to "add X functionality" is about to turn into new code that already exists somewhere else.Votes: 0GitHub stars: 2
- Security AnalysisRuns a two-pass vulnerability scan on a snippet, file, or diff — a static pattern pass across fixed categories (injection, secrets, auth, crypto, deserialization, path traversal, resource exhaustion), then an LLM-reasoning pass for business-logic and race-condition flaws the patterns can't catch. Use for a dedicated security audit that must produce a per-finding severity, exact location, and concrete remediation.Votes: 0GitHub stars: 2
- Security And HardeningHardens a feature against attack before or while it's built — threat-model trust boundaries with STRIDE, apply the Always/Ask-First/Never tiers, and prevent OWASP Top 10 classes by construction. Use when building anything that accepts user input, handles auth, sessions, file uploads, webhooks, payments, PII, or calls an LLM — as opposed to auditing code that already exists.Votes: 0GitHub stars: 2
- Security ReviewReviews code for security vulnerabilities across Go, TypeScript, PHP, and infrastructure config. Use when adding authentication or authorization, handling user input or file uploads, creating API endpoints, working with secrets or credentials, calling third-party APIs, or handling payment or other sensitive data.Votes: 0GitHub stars: 2
- Security ScanAudits an agent harness's own configuration — CLAUDE.md, .claude/settings.json, MCP server configs, hooks, and agent definitions — for prompt-injection surface, overly permissive tool grants, and hardcoded secrets, grading the result A-F. Use after creating or editing .claude/ config, before committing configuration changes, or when onboarding to a repo with an existing agent setup. This scans the agent's own config, not application source code — for that, use security-review or security-and-...Votes: 0GitHub stars: 2
- SeoOptimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".Votes: 0GitHub stars: 2
- Shipping And LaunchPrepare a production launch so it's reversible, observable, and incremental — pre-launch checklist, feature-flag strategy, staged rollout with rollback thresholds, and post-launch monitoring. Use when preparing to deploy to production, releasing a significant user-facing change, migrating data or infrastructure, or opening a beta program.Votes: 0GitHub stars: 2
- Skill Catalog AuthoringThis skill should be used when the user asks to "add a new skill to skillme", "add a skill to this catalog", "write an eval for this skill", "validate this skill's evals", "run smeval on this skill", or otherwise extends or maintains a skill inside this plugin's skills/ directory. Provides the required directory layout, SKILL.md conventions, and evals.json schema for this repository's own eval runner.Votes: 0GitHub stars: 2
- Skill InspectorReviews a third-party AI agent skill — a local directory, downloaded archive, or repo URL — for safety before installing it, using NVIDIA's SkillSpector static scanner plus source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious, or before running "claude plugin install"/"npx skills add" on anything not already vetted. This inspects a skill someone else wrote, not this catalog's own harness conf...Votes: 0GitHub stars: 2
- Source Driven DevelopmentGrounds framework-specific code decisions in official documentation instead of training data or memory. Use before writing framework- or library-specific code (forms, routing, data fetching, auth, state management), when the user asks for "current best practices" or "documented"/"verified" code, or before reviewing code that leans on framework conventions.Votes: 0GitHub stars: 2
- Spec Driven DevelopmentWrites a structured, human-reviewed specification before any code, deriving implementation from that written contract rather than from a vague request. Use when starting a new project or feature with no spec yet, when requirements are ambiguous or only exist as an idea, or before an architectural decision on a change that would take more than about 30 minutes to implement.Votes: 0GitHub stars: 2
- Stakeholder Communication And Status UpdatesGuides writing narrative-style stakeholder status updates and strategy memos instead of bullet-point decks, grounded in Amazon's 6-page narrative memo discipline. Use when the user asks to "write a status update," "draft a weekly update for stakeholders," "write a project update email," "prepare a 6-pager," "turn these bullets into a narrative," "write a stakeholder memo," or is reviewing a status update/deck that seems to be hiding risk or fuzzy thinking behind bullet points.Votes: 0GitHub stars: 2
- Strategic CompactUse when deciding whether to manually compact conversation context now versus later — at a phase boundary (research done, plan written, milestone shipped), before switching to an unrelated task, or when responses feel slower/less coherent from context pressure. Trigger phrases include "should I compact now", "context is getting full", "switching to a different task", or "we just finished planning, what next". Covers what survives compaction and what doesn't, so the decision is informed rather...Votes: 0GitHub stars: 2
- Tdd WorkflowRuns the full TDD workflow for a TypeScript/JavaScript feature — user journeys to test cases, unit tests (Jest/Vitest + Testing Library), API/integration tests, Playwright E2E, and a coverage gate wired into CI. Use when building a Next.js/React/Node feature end to end, not just a single unit test, or when asked to set up a coverage threshold or CI test step.Votes: 0GitHub stars: 2
- Team BuilderUse when a task would benefit from several different specialist perspectives run in parallel — composing an ad-hoc team from a directory of agent persona files, dispatching them simultaneously, and synthesizing their outputs into one report. Trigger phrases include "team builder", "get me a security and performance review together", "compose a team of agents for this", or "what would a few different specialists say about this". Not for a single task routed to one skill — see orchestrator for ...Votes: 0GitHub stars: 2
- Technical Decision RecordsThis skill should be used when the user asks to "write an ADR", "document this architecture decision", "record why we chose X over Y", "create a decision record", or is capturing a significant, hard-to-reverse technical decision so future readers understand why it was made. Use for recording an already-made decision concisely — not for broad open-ended design exploration, which belongs in a design doc.Votes: 0GitHub stars: 2
- Test Driven DevelopmentDrives development with tests written before implementation code, in Go, TypeScript, PHP, or any language. Use when implementing new logic or behavior, fixing a reported bug (write the reproduction test first), modifying existing functionality, or when asked to "add a test," "TDD this," or "prove this works." Use even when the user doesn't say "test" explicitly but describes a bug report or a behavior change.Votes: 0GitHub stars: 2
- Test GenerationGenerates comprehensive unit, table-driven, and concurrency tests for a given function or module — happy paths, error paths, boundary values, and mocked dependencies — following Go and TypeScript idioms. Use when a function or file needs test coverage, a bug fix needs a regression test, or existing tests only cover the happy path.Votes: 0GitHub stars: 2
- Twelve Factor App PrinciplesUse when the user asks to "check twelve-factor compliance", "review this service for 12-factor", "design a new microservice", "where should config live", "should this write to a local file", or is scaffolding a new backend service, containerizing an app, or debugging "works on my machine but not in prod" issues. Guides applying the publicly documented Twelve-Factor App methodology (codebase, config, backing services, statelessness, logs, dev/prod parity) to a service under review or in design.Votes: 0GitHub stars: 2
- User Research SynthesisGuides synthesizing raw qualitative user research into defensible themes using affinity mapping (the KJ method) and conducting Jobs-to-be-Done "Switch" interviews about past purchase decisions. Use when the user asks to "affinity map these notes", "synthesize interview findings", "cluster these observations into themes", "run a JTBD interview", "find out why customers switched to us", or reviews raw interview transcripts, support tickets, or survey verbatims for patterns.Votes: 0GitHub stars: 2
- Using Agent SkillsMeta-skill for how this agent discovers and decides which of its own available skills to invoke for the current task. Use at the start of any task to check the available-skills listing for a match, when unsure which skill applies, when multiple skills seem relevant, or when deciding whether to force-fit a skill versus proceeding without one.Votes: 0GitHub stars: 2
- Vue Nuxt Frontend PatternsGuides Vue 3 Composition API and Nuxt 3 development — composables, reactivity, SSR data fetching, and component patterns. Use when building Vue or Nuxt components, writing composables, fetching data in a Nuxt page or component, managing shared state with Pinia, or debugging a value that "isn't reactive" after being passed around.Votes: 0GitHub stars: 2
- Web Quality AuditComprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".Votes: 0GitHub stars: 2
- Writing Product RequirementsGuides writing product requirements as a PR-FAQ (press release plus frequently-asked-questions) using Amazon's working-backwards methodology, or as a lighter PRD when a PR-FAQ is overkill. Use when the user asks to "write a PR-FAQ", "write product requirements", "draft a PRD", "work backwards from the customer", "write a press release for a product that doesn't exist yet", or asks for a critique/review of an existing PR-FAQ or PRD draft.Votes: 0GitHub stars: 2