Claude Skills by edhoferdian

github.com/edhoferdian

39 skillsA× 37B× 20 installs13 views

Api Design Edho FerdianADesign and evolve API boundaries and contracts — REST resource naming, status-code semantics, pagination strategy, versioning policy, and the discipline of treating one contract artifact (OpenAPI/schema) as authoritative so client and server never drift. A design-time activity, distinct from system-design-edho-ferdian (broader architectural trade-offs) and code-review-edho-ferdian (reviewing an already-written endpoint). Trigger phrases: "desain API untuk fitur ini", "bagaimana struktur endpo...ai-agentsgocode-reviewVotes: 0GitHub stars: 5
Backend Engineering Edho FerdianAAuthoring server-side code between the API contract and the datastore — layering and ports/adapters boundaries, error taxonomy and resilience (typed errors, Result style, retry with backoff, circuit breakers), background jobs and queues, structured logging emission, and adding a new integration that matches the repo's existing connector pattern. The backend counterpart to frontend-engineering-edho-ferdian. Framework guides: NestJS and Ruby on Rails (service/form/query objects, Hotwire, Rails ...ai-agentsrustgoVotes: 0GitHub stars: 5
Billing Ops Edho FerdianADiagnosing and handling billing/subscription operations — classifying customer billing incidents (duplicate subscriptions, multi-seat vs accidental duplicate, failed checkout, missing self-serve controls, broken product), separating customer impact from code-backed product truth, and routing pricing/entitlement claims through verification before they're repeated. Diagnosis-only for financial actions: refunds, credits, and cancellations require the user's explicit go-ahead before execution. Tr...ai-agentsgocode-reviewVotes: 0GitHub stars: 5
Build Fix Edho FerdianADiagnose and fix build, compile, dependency, and runtime-startup failures with minimal surgical diffs — never refactors, never architectural changes, always verified green. Auto-detects the stack from project files (JS/TS, Python/Django, Go, Rust, PHP/Laravel, Java/Spring, Quarkus, Kotlin, Swift, React Native, Flutter, Android, .NET, C++, PyTorch, ArkTS, Perl, Ruby, and more) and loads the matching diagnostic lens. Use whenever a build, compile, analyze, or startup step fails, or the user say...developmentjavascripttypescriptVotes: 0GitHub stars: 5
Click Path Audit Edho FerdianATrace every user-facing touchpoint (button, toggle, form submit) through its full state-change sequence to find defects that reading code line by line cannot see: handlers whose calls silently undo each other, async races, stale closures, and effects that reset the very state the button just set. Use when a control "does nothing" despite the handler existing and not crashing, after refactoring a shared state store (Zustand/Redux/context/ signals), or before release on critical flows. Trigger ...ai-agentsreacttestingVotes: 0GitHub stars: 5
Code Quality Tooling Edho FerdianASet up and configure the automated code-quality gate around a project — Biome or ESLint+Prettier, Husky Git hooks (pre-commit/pre-push), and lint-staged for JS/TS, plus the equivalent tooling for other stacks (Ruff/pre-commit for Python, golangci-lint/lefthook for Go, rustfmt/clippy for Rust). This is authoring/setup guidance for wiring the gate itself, not the code style rules it enforces or the commit-message format it may check. Trigger phrases: "setup ESLint", "setup Biome", "tambah Prett...ai-agentsjavascripttypescriptVotes: 0GitHub stars: 5
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Code Review Edho FerdianASenior-engineer code review across five domains — Code Quality, Security, Performance, Blueprint/Spec Consistency, and Test Quality — plus conditional lenses auto-detected from scope (database, accessibility, RAG, ML, healthcare, agent/LLM — see Phase 0 below for the full list). Produces an evidence-backed findings report with confidence-labeled severities and an adaptive fix. Use whenever the user wants code reviewed, audited, or checked before merge/deploy: "review this", "audit", "cek kode...ai-agentspythonrustVotes: 0GitHub stars: 5
Code Simplification Edho FerdianABehavior-preserving refactoring workflow that actively rewrites code for clarity — extracting overlong functions, flattening deep nesting, consolidating duplicated logic, AND removing over-engineered "just in case" abstractions — always gated on a passing test suite (or a characterization test written first) so behavior never changes. Use whenever the user wants code actually SIMPLIFIED or REFACTORED, not just reviewed: "sederhanakan kode ini", "refactor biar lebih rapi", "reduce complexity",...ai-agentspythonrustVotes: 0GitHub stars: 5
Communications Triage Edho FerdianAChannel-agnostic framework for triaging incoming messages (email, chat, Slack, LINE, Messenger, or any other channel) into four priority tiers, drafting replies that stay within a strict human-approval gate, and tracking whether a sent reply's promises actually get followed through on. Use when the user wants to build or apply a message-triage workflow, says "triase pesan", "atur inbox", "bantu balas email/chat", "klasifikasikan pesan masuk", "draft balasan", or asks how to keep track of prom...ai-agentsrustgoVotes: 0GitHub stars: 5
Config Hygiene Edho FerdianAPeriodic garbage collection for Edho's own Claude Code environment (`~/.claude`): find redundant, stale, orphaned, or context-expensive items across skills, memory, hooks, permissions, MCP servers, automations and caches, then walk them one by one with a human confirmation and an undo path. Includes the ECC decommissioning track — the concrete checklist for removing the ECC install once its native replacement exists. Use when the user says "bersihin config", "~/.claude berantakan", "kebanyaka...ai-agentsrustgoVotes: 0GitHub stars: 5
Container Ops Edho FerdianAContainer setup, docker-compose design, multi-stage build optimization, and debugging guidance. Security-specific container concerns live in security-review-edho-ferdian instead. Trigger phrases: "setup Docker untuk project ini", "docker-compose untuk dev environment", "container ini lambat/besar", "debug container yang crash".ai-agentsdockerdebuggingVotes: 0GitHub stars: 5
Counterparty Comms Edho FerdianAContract for an agent that talks to external counterparties (customers, suppliers, partners) in shared channels, group chats, DMs, or email: who it may speak to and when (audience classification, mention gating, silent observation, no leakage of internal context), and what it may send (every outbound draft filed for operator approval against an exact text hash, stale approvals unable to release rewritten text, one dispatch per approval with a delivery ledger). Use when building or reviewing a...ai-agentsrustgoVotes: 0GitHub stars: 5
Data Layer Patterns Edho FerdianADesign and setup guidance for the data layer — Postgres schema design, Prisma ORM patterns, Redis caching/queue patterns, and cross-ORM migration strategy (expand-contract). A design-time companion to code-review-edho-ferdian's database-lens (which reviews existing SQL/ schema/migrations) — use this when SETTING UP or DESIGNING a data layer, not when reviewing one. Trigger phrases: "desain schema untuk X", "setup Prisma/Redis", "bagaimana strategi migration yang aman", "cache invalidation str...ai-agentsjavasqlVotes: 0GitHub stars: 5
Dead Code Cleanup Edho FerdianAStaged dead-code removal workflow — detect (stack-appropriate tooling: knip/depcheck/ts-prune, vulture/deptry, cargo-udeps, deadcode, ...), classify by removal risk (SAFE/CAREFUL/RISKY), cross-check every "unused" hit against Salak's repo-graph.json reverse-dependency data when available, then delete in ordered categories (deps → exports → files → duplicates) running the test suite between each category. Use this whenever the user wants dead code, unused exports, unused dependencies, or dupli...ai-agentspythonrustVotes: 0GitHub stars: 5
Deployment Ops Edho FerdianAGetting a build to production and keeping it healthy — release strategy (rolling / blue-green / canary), CI/CD pipeline gates, health checks and Kubernetes probes, environment config and rollback, a production-readiness ship/block verdict, operator dashboards, and post-deploy watching. Starts where container-ops-edho-ferdian stops (image built, compose working). Trigger phrases: "deploy ini gimana", "bikin pipeline CI/CD", "rollback", "manifest kubernetes", "siap rilis belum", "pantau setelah...ai-agentsdockerkubernetesVotes: 0GitHub stars: 5
Desktop E2e Edho FerdianAEnd-to-end testing for Windows native desktop applications (WPF, WinForms, Win32/MFC, Qt 5/6) using pywinauto over the Windows UI Automation API. The native-automation driver that e2e-testing-edho-ferdian's Phase 0 detects as option 4 but has no content behind — journey mapping and the Page Object Model come from there; the pywinauto mechanics live here. Use when the target is a desktop .exe rather than a browser page, when a desktop GUI test suite is being set up or is flaky, or when adding ...ai-agentspythongoVotes: 0GitHub stars: 5
Dev Kickoff Edho FerdianAKickoff and execute a development project from ANY specification or planning documents (PRD, SRS, WBS, tech spec, RFC, ADRs, and more — see the Phase 0 role table below for the full list). Classifies docs by role, cross-validates them, extracts a binding Project Decision Register, generates an Execution Context Pack plus a project-fit agent roster, then builds task-by-task through a seven-stage PLAN→TEST→IMPLEMENT→REVIEW→ VERIFY→REMEMBER→IMPROVE loop — auto-invoking this ecosystem's other ski...ai-agentsrustgoVotes: 0GitHub stars: 5
Docs Sync Edho FerdianAKeep USER-FACING documentation honest against the current codebase — README, docs/CODEMAPS/*, architecture-as-markdown, public API docs. Generates/refreshes codemaps and validates doc freshness (every path exists, every link resolves, every code snippet matches reality, timestamps are current). Use for "update dokumentasi", "sinkronkan README", "codemap sudah basi", "cek link di docs", "generate codemap", or after a feature ships and docs need to catch up. Does NOT do dependency-graph generat...ai-agentsrustgoVotes: 0GitHub stars: 5
E2e Testing Edho FerdianAEnd-to-end testing for critical user journeys — the visual/browser-level layer that dev-kickoff-edho-ferdian's TEST stage explicitly defers to. Maps critical flows before writing any test, auto-detects whichever E2E driver is actually available at runtime (see Phase 0 below for the priority order) rather than requiring one specific tool, builds tests with the Page Object Model pattern, quarantines flaky tests instead of blocking or ignoring them, and captures failure artifacts. Use when the u...ai-agentsrusttestingVotes: 0GitHub stars: 5
Frontend Engineering Edho FerdianAAuthoring and configuration guidance for building React/Next.js frontend applications well from the start — component composition, UX/interaction recipes, Vite config, HeroUI setup, and AI-slop detection (see the Reference files table below for the full breakdown). A companion to language-code-review-edho-ferdian (which reviews code after it's written) — use this when DESIGNING or WRITING new frontend code, not when reviewing existing code. Trigger phrases: "bagaimana cara structure component...ai-agentsgoreactVotes: 0GitHub stars: 5
Gan Harness Edho FerdianARapid, adversarial-loop prototyping and design iteration: a Plan → Generate → Evaluate cycle where a generator builds a live app and an evaluator drives it in a real browser, scores it against a weighted design rubric, and feeds fixes back until a quality threshold is crossed (see the Plan phase section below for exactly how scope is sourced, never invented from a one-line prompt). Use when the user wants fast UI/prototype iteration with automated design critique, says "gan-harness", "loop ge...ai-agentsgoreactVotes: 0GitHub stars: 5
Git And Release Ops Edho FerdianAGit and forge workflow — branching strategy selection, conventional commit format, merge versus rebase, conflict resolution, PR readiness and triage, issue/backlog classification, CI failure triage, and release/changelog cutting. Trigger phrases: "strategi branch", "format commit", "rebase atau merge", "PR ini siap merge belum", "triase issue", "bikin release", "CI merah".ai-agentsgitVotes: 0GitHub stars: 5
Language Code Review Edho FerdianALanguage- and framework-specific code review lenses layered on top of the general four-domain review in code-review-edho-ferdian — idioms, framework security misconfigurations, ORM/query correctness, performance traps, and testing conventions, auto-detected across ~20 stacks (React, Python, Go, Java/Spring, Ruby, and more — see the reference table below for the full list). Use whenever a review touches a specific language/framework and the generic checklist isn't enough — "review kode Go/Pyth...developmentpythonrustVotes: 0GitHub stars: 5
Legal Ops Edho FerdianAReproducible agreement paperwork for a solo operator or small team: build review drafts of a master/framework agreement (NDA, referral or sourcing fee, non-circumvention, master services) from one template plus a small JSON spec per counterparty, add deals later by Schedule A notice within the executed agreement's authority, and prepare e-signature envelopes by browser automation with calibrated numeric field placement and a hard save-as-draft gate. Not legal advice — output is always a DRAFT...ai-agentsrustgoVotes: 0GitHub stars: 5
Marketing Edho FerdianACampaign/positioning strategy, brand-voice definition, landing-page and email copywriting patterns, and a lightweight competitive/market- positioning framework — scoped for a solo developer marketing their own open-source tools or side projects, not a full marketing agency replacement. Use when the user wants to plan a launch, write landing-page or email copy, define a brand voice, or position a product against competitors; whenever they say "marketing", "positioning", "brand voice", "landing...ai-agentsrustgoVotes: 0GitHub stars: 5
Networking Ops Edho FerdianANetworking skill covering five modes — config review, network design (homelab or enterprise/multi-site), read-only OSI-layer diagnosis, device operations/change windows (Cisco IOS-flavoured), and homelab build-out (see the Mode detection table below for the full breakdown and which mode fits). Use whenever the user pastes a config to review ("cek config Cisco ini"), wants a network designed ("rancang jaringan homelab"), is troubleshooting connectivity/DNS/routing symptoms ("kenapa internet la...ai-agentsgotestingVotes: 0GitHub stars: 5
Opensource Release Edho FerdianAFork, sanitize, and package a project for open-source release in three phases — extract secrets into .env.example rather than deleting them, run an independent adversarial audit that never trusts the fork phase's own report (PASS/FAIL/PASS-WITH-WARNINGS, hard-gates packaging on FAIL), then generate CLAUDE.md/README/LICENSE/CONTRIBUTING/issue-templates. Use when the user wants to open-source a project, says "mau open-source-kan ini", "siapkan repo ini buat publik", "audit sebelum rilis publik"...ai-agentsrustgoVotes: 0GitHub stars: 5
Performance Audit Edho FerdianAMeasure-then-fix performance workflow — runs real profiling/measurement tooling (Lighthouse, bundle analyzers, heap-snapshot diffing, Node/browser profilers, DB EXPLAIN) to get a baseline, diagnoses against Core Web Vitals budgets and algorithmic-complexity patterns, applies a fix, then re-measures the delta against the budget. Use this whenever the user wants a performance problem actually diagnosed and fixed with real numbers — "app terasa lambat", "kenapa lemot", "optimize performance", "r...ai-agentspythongoVotes: 0GitHub stars: 5
Research Ops Edho FerdianBEvidence-first research workflow — classify what kind of research the question actually needs, take the lightest evidence path that answers it, synthesize multiple sources into a cited report, and label every claim by evidence type (sourced fact / user-supplied / inference / recommendation) so a reader can tell what is proven from what is guessed. Use whenever the user says "riset", "cari tahu", "cek fakta", "bandingkan X vs Y", "apa yang terbaru soal", "research this", "deep dive", "investig...ai-agentsrustgoVotes: 0GitHub stars: 5
Safe Execution Edho FerdianBMechanical gates around agent execution, as a complement to this ecosystem's reasoning gates: a pre-action fact-forcing gate that demands concrete investigation before the first edit to a file, a destructive- command guard, a write-scope freeze for autonomous or parallel agent runs, and a stop-gate that blocks "done" until the memory files were actually touched. Use when running agents autonomously or in parallel, when working against production, or when the user says "jangan sampai kehapus",...ai-agentsgoshellVotes: 0GitHub stars: 5
Security Review Edho FerdianASingle source of truth for security review criteria across the Edho Ferdian ecosystem — general OWASP-style checklist (SEC-01..19), plus stack-specific and domain-specific security items (see the reference list at the bottom of this file for the full stack/domain coverage). Runs STANDALONE for a security-only pass ("cek keamanan kode ini", "security audit", "find vulnerabilities") OR as the delegated depth layer for Domain 2 (SEC) of code-review-edho-ferdian's full review. Every other skill i...ai-agentspythongoVotes: 0GitHub stars: 5
Seo Audit Edho FerdianATechnical + on-page SEO audit workflow — crawl/gather site signals, check them against a real technical-SEO checklist (crawlability, indexability, structured data, meta tags, sitemap/robots.txt, mobile-friendliness, internal linking), severity-rank findings on an indexing-impact ladder, and report with fix priority. Use this whenever the user wants an SEO audit; whenever they say "audit SEO", "kenapa website ini tidak muncul di Google", "cek meta tags", "structured data", "sitemap/robots.txt"...ai-agentsgonextjsVotes: 0GitHub stars: 5
Skill Audit Edho FerdianAAudit this ecosystem's own `skills/` directory for staleness, redundancy, broken cross-references, and description-quality problems — increasingly important as this ecosystem grows past a dozen interlinked skills. Use when the user says "audit skill saya", "cek skill yang sudah dibuat", "ada yang redundan gak", "skill mana yang basi", or periodically after a batch of new skills is added. Scope is this repo's own `skills/` content and quality only — NOT the `~/.claude` environment/config (that...ai-agentsgotestingVotes: 0GitHub stars: 5
Skill Authoring Edho FerdianADiscipline for creating and governing this ecosystem's own skills: search before building (local → marketplace → GitHub → web, with a security vet on anything external), write to a quality bar, measure whether a skill is actually obeyed rather than assuming it, promote recurring cross-skill principles up into rules, and package a finished skill into `dist/*.skill` for manual upload. Use when the user says "bikin skill baru", "ada skill buat X gak", "fork skill ini", "skill gue kepake gak sih"...ai-agentspythonrustVotes: 0GitHub stars: 5
Spec Mining Edho FerdianAExtract behavioral specifications from an existing codebase that has no written spec — mining a brownfield repo into a flat list of Requirements (WHEN/THEN) and Invariants (always-true), each anchored to the exact code location that enforces it, grounded in Salak's dependency graph when installed. Groups the codebase into capabilities first, then mines with a bounded sample-and-expand read strategy (see Phase 1/2 below for the mechanics) — never reading a whole module blindly. Use when enteri...ai-agentsrustexpressVotes: 0GitHub stars: 5
System Design Edho FerdianAMid-project architectural decision-making — Architecture Decision Records (ADRs), structured trade-off analysis, non-functional-requirements review, and scaling-tier planning for an existing system. Use for "desain arsitektur", "keputusan teknis besar", "bikin ADR", "trade-off antara X dan Y", "should I refactor this to microservices/monolith/event-driven", a scaling or capacity question, or any task from dev-kickoff-edho-ferdian that surfaces an uncovered ARCHITECTURE decision mid-project (n...ai-agentsrustgoVotes: 0GitHub stars: 5
Test Authoring Edho FerdianAGuidance for WRITING unit and component tests well — React/Testing Library, Python/pytest, Go, and Vue, plus stack-agnostic regression-test patterns. A companion to code-review-edho-ferdian's test-quality-lens (which judges tests after they're written) and dev-kickoff-edho-ferdian's TEST stage (which mandates writing a failing test first but doesn't teach test-writing craft). Trigger phrases: "tulis test untuk component ini", "bagaimana test hook ini", "test yang bagus untuk fitur X", "tulis ...ai-agentspythongoVotes: 0GitHub stars: 5
Video Style Edho FerdianACapture the look and pacing of reference videos as measurements, then reproduce them: distill references into a style pack (colour grade per luminance zone baked to a 3D LUT, cut rhythm as a shot-length distribution, overlay plates, hero stills, a grounded text spec), then generate or gather footage, grade it to the pack, cut it at the measured cadence, composite overlays, and verify the result numerically before handing an editable timeline to Resolve or another NLE. Use when the user says "...ai-agentsgoapiVotes: 0GitHub stars: 5
Agent Delegation Edho FerdianARealize this ecosystem's named agent roster (agents/*/AGENT.md in the edho-ferdian ecosystem) inside Hermes, which has no static per-agent file format of its own. Use this whenever a task calls for delegating to one of the named roles below via Hermes' delegate_task tool, instead of writing an ad-hoc delegation prompt from scratch.developmentpythonrustVotes: 0GitHub stars: 5