Engineering
98,234 rows, by stacks then stars
tingwei628twdev/ralph-enhanced/skills/ralph Skill
0★ repo使用 Ralph 自動化 agent loop 模式來實作功能、建構專案或執行多步驟開發任務。當使用者說「用 ralph 實作」、「幫我建一個 ralph loop」、「自動跑 claude code 完成任務」、「建立 PRD 讓 agent 自動做」、「我想用 ralph 模式」、「設定 ralph 跑這個專案」時,一定要使用此 skill。也適用於任何需要把大型任務拆成多個 user stories、讓 Claude Code 或 Amp 反覆迭代執行直到完成的場景。即使使用者只說「幫我自動實作這個功能」或「讓 AI 自己把這個做完」,也應該觸發此 skill。
mercedesperezcapilla-gif/claude-skills/skills/automation-opportunity-finder Skill
0★ repoHelps professionals identify practical AI automation Quick Wins through guided discovery, workflow analysis, role-based suggestions and industry-specific patterns. Designed for people who do not know where to start with AI automation. Returns prioritised opportunities, implementation guidance and governance signals.
sxntixgo/claude-code-skills-for-security/demo/skills/security-best-practices Skill
no license0★ repoReviews a repository for common security best-practice violations and writes a short report. Use when the user asks for a security best-practices review.
Hosseinkm89/figma-skills/auto-layout-refactor Skill
0★ repoConverts flat Figma frames built with absolute (free-form) positioning into proper auto-layout structures, in place. Triggers when the user describes a legacy or messy Figma file where layers were dragged into position instead of stacked — phrasings like "this file has no auto-layout", "everything is absolutely positioned", "refactor this screen to auto-layout", "auto-layout this page", "convert these frames to auto-layout", "clean up this old Figma file", "the layout is flat / has no structure", "add auto-layout to these frames", "wrap these into auto-layout", "fix this legacy layout", or "auto-layoutify". Also trigger when a designer opens an old design and asks for help making it editable, responsive, or maintainable. Do NOT trigger for creating new layouts from scratch (use figma-generate-design) or for component construction (use figma-generate-library).
cportka/claude-plugins/plugins/repo-bootstrap/skills/repo-bootstrap Skill
0★ repoSet up a repository to use Claude Code plugins from the portka-tools marketplace, especially for Claude Code on the web. Use when the user wants to onboard a repo to a marketplace/plugin, enable a plugin in a specific repo, scaffold .claude/settings.json (+ optional CI) for ephemeral web sessions, or asks for the Portka standard / to standardize how Claude works in a repo.
merge-api/merge-unified-skills/skills/implementing-post-connection Skill
0★ repoGuide an AI coding agent through the full post-connection experience — settings page, sync status visibility, relinking, integration configuration, custom fields, and category-specific data scope filtering. Use after completing Merge Link setup to build the ongoing integration management experience or settings UI.
leadupofficial/leadup-claude-skills/leadup-ai-feature-planner Skill
0★ repoPlan a single, useful AI feature for a LeadUp website, SaaS, admin panel, CRM, mobile app, or automation workflow with goal, user flow, model recommendation, prompt and data design, cost risk, privacy risk, fallback behavior, logging and observability plan, and a test plan. Designed so AI features ship safely and stay profitable for Indian SMB SaaS and global products. Use when the user says "AI feature", "add AI", "make app intelligent", "AI chatbot", "AI report", "AI assistant", or "automation AI".
kuro0107/madamisu-skills/plugins/madamisu/skills/config Skill
0★ repoマダミスの制作方針を決める。元資料(フォルダまたは.md)を入力に要件定義とヒアリング(Q1-13)を行い output/_config.md を生成する。既存の _config.md があれば「そのまま使う/設定し直す」を選べる。/madamisu:config 起動時、または madamisu:scenario から呼ばれる。
tabgab/opp_repl-skill/opp-repl-chart-tests Skill
no license0★ repoDetect visual regressions in result-analysis charts. run_chart_tests renders charts from current results and compares them pixel-wise against baseline images stored in the project's media_folder. Requires the `chart` extra (matplotlib + numpy). Load when analysis plots are part of your deliverable and must stay stable.
Diegocortes15/playwright-ia-automation-framework-saucedemo/.claude/skills/playwright-cli Skill
no license0★ repoAutomate browser interactions, test web pages and work with Playwright tests.
The same file is in 3 other repositories
ezos26/claude-skills/skills/debug Skill
0★ repoSystematic debugging methodology. Use when something is broken, a test fails unexpectedly, a regression appears, or behavior doesn't match expectations. Replaces "just try stuff" with structured hypothesis-driven investigation. Usage /debug [description of the problem]
OmarEltak/legacy-prod-survival-kit/skills/bilingual-exec-report Skill
0★ repoUse when the user (typically a solo engineer who has just completed a major engineering effort) needs to communicate that work to a non-technical executive. Generates a Microsoft Word file (English + Arabic, properly RTL) with proven framings; the industry-context table, the van analogy, respectful predecessor acknowledgement, and the closing hook. Reset boss expectations gently. Especially valuable when the boss compares the engineer unfavourably to a previous developer.
kakarot-oncloud/claude-dev-skills/skills/bug-report-formatter Skill
0★ repoTurns vague or chaotic bug descriptions into structured, reproducible bug reports with steps, expected vs actual behavior, environment, and severity. Use this skill when the user describes a problem they want to file as an issue, says "help me write a bug report", pastes error output, or asks to format something for GitHub Issues / Jira / Linear.
dimi-id/manager-kung-fu/skills/performance-review Skill
0★ repoAssists engineering managers and directors in drafting, evaluating, and delivering performance reviews for ICs and Managers. Use when the user asks to "write a performance review", "prepare for calibration", "evaluate a draft", "synthesize 360 feedback", "check for bias", "roleplay delivery", "build a promotion case", "resolve disputed evaluations", "structure a PIP", or mentions "performance review", "review cycle", or "calibration session".
eroveda/blueprint-skills/skills/generate-architecture-doc Skill
0★ repoGenerates ARCHITECTURE.md following IEEE 15289 standards. Use when documenting a new or existing project's technical architecture. Do NOT use for user-facing docs (use generate-user-guide) or API docs (use generate-api-catalog). Trigger with "generate architecture doc", "document the architecture", or "create ARCHITECTURE.md".
koloskus/jotbook/skills/jotbook-init Skill
0★ repoInitialize a jotbook in the current project — writes a starter `.claude/jotbook.local.md` settings file, scaffolds the directory structure, and optionally amends `.gitignore`.
chris-co-creators-ai/soulcreator/de Skill
0★ repoZu verwenden, wenn ein KI-Agent seine eigene stabile Identität in ein Projekt schreiben muss. Liest vorhandenen Speicher, Konversationsverlauf und frühere Identitätsdateien; schreibt dann eine dreischichtige Architektur (constraint spine, expression, mission integration) in CLAUDE.md oder AGENTS.md. Fragt um Erlaubnis, bevor eine bestehende Identitätsdatei überschrieben wird.
Marcdaou/claude-qa-suite/qa-suite/skills/e2e-testing Skill
0★ repoWrite and run TypeScript end-to-end browser tests with Playwright that exercise real user journeys — signup/login, search, the booking flow, and Stripe checkout → confirmation. Use this skill whenever the user wants an e2e test, a browser test, to test a full flow "end to end", to catch regressions before deploy, or to verify the live site still works after a change. Trigger even on casual asks like "make sure booking still works in the browser" or "test the checkout flow".
reasonless-throne486/sast-skills/sast-files/.agents/skills/sast-businesslogic Skill
0★ repoDetect business logic vulnerabilities in a codebase using a three-phase approach: threat modeling (domain analysis and attack scenarios), batched verify (check exploitable gaps in parallel subagents, 3 scenarios each), and merge (consolidate batch results). Covers price manipulation, workflow bypass, limit violations, race conditions, reward abuse, etc. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/businesslogic-results.md. Use when asked to find business logic, logic flaws, or abuse-of-function bugs.
SKaiNET-developers/SKaiNET-coding-skills/skainet-consumer-skills/skills/skainet-consumer-setup Skill
0★ repoUse when adding SKaiNET as a library dependency to your Gradle project (KMP, JVM, or Android) — adding `sk.ainet:skainet-bom` to the version catalog, picking which `sk.ainet.core:skainet-*` artifacts the project needs (inference vs. training vs. format-specific I/O), or troubleshooting "I added SKaiNET but X doesn't resolve". Trigger tokens include `sk.ainet:skainet-bom`, `sk.ainet.core:skainet-`, `platform("sk.ainet:skainet-bom")`, `implementation(libs.skainet.*)`, "add SKaiNET to my project". Do NOT fire when editing build scripts INSIDE the SKaiNET repo itself (that's the contributor `gradle-multimodule` skill).
calvin-iyer/android-skills/plugins/android-skills/skills/android-go-live-checklist Skill
0★ repoGenerates and manages a Play Store launch checklist (`go-live-checklist.md`) for Android apps and games. Performs Android project detection, web research on current Play Console publishing requirements, deep codebase analysis for pending work and manual setup items (IAP products, Firebase rules, signing config, ProGuard, privacy policy, etc.), and produces a severity-ranked checklist. Also walks the user through items one at a time and tracks status. USE THIS SKILL whenever the user mentions Play Store launch, going live, publishing an Android app, release readiness, launch checklist, pre-launch audit, "what's left before we ship to Play Store", "am I ready to publish", or asks for a walkthrough/recreation/update of the go-live checklist. Trigger even if user does not say "checklist" explicitly, as long as the intent is Play Store launch readiness for an Android app/game.
puukis/lstack/skills/architect Skill
0★ repoSystem design before any code is written — invoked via /architect; produces ADRs and ARCHITECTURE.md
ak-ship/fullstack-agent-skills/skills/browser-qa Skill
0★ repoDrive a real browser (Playwright) to validate user flows end-to-end — click buttons, fill forms, assert on rendered output, screenshot the moment a step breaks. Use when the user says "test this flow", "run the e2e tests", "verify the signup works", "qa my app", "does the checkout work", or asks Claude to confirm a UI change actually behaves correctly in a browser. Closes the gap between "code compiles" and "user flow works".
Adversis/skills/skills/security-persona Skill
no license0★ repoProduces a factual security posture document (docs/security-posture.md) and engineering roadmap by reading the codebase and any prior skill output. Asks 3–5 code-adjacent questions for things the code cannot fully answer. Run after lint-baseline and threat-model for best results.
brandhaug/skills/write-agents-md Skill
no license0★ repoWrite and maintain AGENTS.md (or CLAUDE.md) files as an Intent Layer — a hierarchy of small, dense context files at semantic boundaries that auto-load as architectural context for agents. Use when the user wants to write, create, generate, scaffold, seed, sync, or prune AGENTS.md / CLAUDE.md files, agent context files, intent nodes, intent layer, or architectural memory for agents; or mentions "AGENTS.md hierarchy", "intent layer", "intent nodes", "agent context", "T-shaped context", "dark room problem". Supports two workflows — `build` (initial capture, leaf-first with SME interview) and `sync` (reconcile affected nodes after code changes — proposing additions, modifications, AND removals of stale content).
husnain067/codebase-knowledge-skills/codebase-error-handling Skill
0★ repoDocument the error handling, logging, and observability setup of a codebase — what error types exist, how errors propagate (thrown vs returned vs Result types), what logger is used and how, what observability tooling is integrated (Sentry, Datadog, OpenTelemetry), and how errors surface to the user. Use this skill when the user asks "how does error handling work here", "document the error patterns", "what's the logging setup", "explain the error flow", "how are errors reported", "what's the observability stack", or any variant focused on errors and logging rather than full architecture. The output is a single Markdown file capturing error type hierarchy, propagation conventions, logging library and format, observability tools, user-facing error surfaces (HTTP responses, SnackBars, dialogs, CLI exit codes), and recurring error-handling patterns — each documented with REAL examples copied from the actual codebase. This skill is narrow by design and produces ONLY the error handling reference. It does not cover architecture, naming, testing, or domain vocabulary — point the user to the relevant sister skill if they need those.
slogsdon/skills-workflows/skills/agents-md-generator Skill
0★ repoGenerate or update an AGENTS.md / CLAUDE.md / context file for a repo. Use when the user says "set up CLAUDE.md", "generate AGENTS.md", "write a context file for this repo", "document this codebase for AI agents", or when a fresh repo has none. Also use when an existing context file has gone stale and needs a rewrite from current source. Do NOT use for editing project-specific README or contributor docs.
Skillpack forge demo release notes
guorunjie/skillpack-forge-demo/.claude/skills/skillpack-forge-demo-release-notes Skill
0★ repoUse when updating the tiny release-note helper in this fixture.
cynthiaschomp/Claude-Project-Management-Skill-Ecosystem/pm-project-kickoff Skill
0★ repoUse this skill whenever a new client project needs to be set up in project management. Triggers on: "new project", "onboard client", "set up project", "scaffold project", "new client project", "kick off", "kickoff", "start the project", "client signed", "contract signed", or any situation where a client has committed to work and tasks need to be created. This skill scaffolds the full project phase structure, sets the scope_doc baseline, sends a welcome email, and ensures nothing falls through the cracks at the start of an engagement. ALWAYS use this skill before writing any project creation logic or task scaffolding code.
Methasit-Pun/ts-ddd-clean-architecture/.claude/skills/agent-sort Skill
0★ repoBuild an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
The same file is in 3 other repositories
juncoding/nextjs-trpc-prisma-starter/skills/nts-add-cache Skill
0★ repoRetrofit Redis caching into an existing project scaffolded with nextjs-trpc-prisma-starter. Use this when the user wants to add Redis, add a cache layer, speed up frequent reads, share cache across processes, or any 'add caching to this project' request. Adds ioredis, a docker-compose redis service, a typed cache helper at src/server/lib/cache.ts, REDIS_URL env, and updates CLAUDE.md to reflect the new dependency. Refuses to run on projects that don't have the scaffolded structure.
anoop04singh/scaffold-skill/.tmp-package/scaffold Skill
no license0★ repoConvert a research paper into an implementation-first engineering roadmap and starter code scaffold. Use when the user provides a CS, blockchain, cryptography, distributed systems, or ML paper and wants to build from it.
Rockfish-Data/tacklebox/skills/inject-scenarios Skill
0★ repoInject synthetic scenarios (spike, outage, ramp, shift) into a time-series dataset using the Rockfish labs scenarios service. Use when a user wants to perturb a baseline time series for ML robustness testing, root-cause-analysis drills, or anomaly-detection evaluation — and optionally generate Q&A test cases from the perturbation. Trigger on phrases like "inject an anomaly", "add a spike to this series", "simulate an outage", "scenario injection", or mentions of `rockfish.labs.scenarios`.
Shankulkarni/RN-Lib-Claude/plugins/rn-lib-claude/skills/ci Skill
no license0★ repoUse when setting up CI/CD for a React Native library — GitHub Actions workflows for PR checks, automated publish on changeset merge, NPM_TOKEN setup, and caching strategies.
Hook12aaa/craft-gate/skills/using-craftsmanship-test Skill
no license0★ repoBootstrap context for the Craftsmanship Test plugin. Auto-loaded at session start. Defers all gating to the project-type detector and craftsmanship-test:craft-gate skill. Not a runtime-triggered skill — use craftsmanship-test:craft-gate for the actual gate.
unitedideas/claude-skills-foundry/skills/find-ai-jobs Skill
0★ repoSearch AI Dev Jobs (aidevboard.com) for AI, ML, and LLM engineering roles. Invoke when the user asks about AI/ML jobs, LLM engineer roles, AI research positions, or wants to find companies hiring in AI. Supports filters for remote/hybrid/onsite, location, level, and salary floor.
mustafayilmazart/kesif-claude-skills/skills/claude-plugins-marketplace Skill
0★ repoClaude Code'u tam bir dev ekibine dönüştüren 6 plugin yönetimi - Planning, Design, Code Review, Security, Memory, Team Coordination. Kullanıcı "claude plugin, dev team, claude takım, planlama ajanı" dediğinde tetiklenir.
The same file is in 1 other repository
gnomatix/steering/.agent/skills/audit-rule Skill
no license0★ repoAudit a behavioral RULE document — AGENTS.md, GEMINI.md, .agent/rules/*.md, CLAUDE.md, .cursorrules, .cursor/rules/*.mdc, .kiro/steering/*.md, system prompt, or any always-on agent rule. Catches behavior-vs-surface failures, embedded biases, escape hatches, and other ways the rule can be technically followed while violating its intent. Use when reviewing or revising any document that prescribes always-on or auto-included agent behavior. SKIP for invocable skill files (use audit-skill) or multi-step workflow documents (use audit-workflow).
tejasashinde/agent-skill-kit/cron-job-generator Skill
0★ repoConverts natural language scheduling requests into correct cron expressions, validates feasibility, explains schedules in simple terms. Handles standard cron limitations, suggests alternatives for irregular intervals, complex logic or event-driven triggers.
lxyang20131208-star/x-algorithm-skills/skills/x-hook Skill
0★ repoWrite or rewrite the first line (hook) of an X (Twitter) post. Use when the user has content, an idea, or a finished post and wants a stronger opening, asks "make this hook better", "how should I start this tweet", "my posts get no engagement", or wants scroll-stopping first lines. Returns ranked hook variants with reasoning.
fabioc-aloha/Alex_ACT_Edition/.github/skills/agent-review Skill
0★ repoAudits a candidate agent (.agent.md) against five gates (spec compliance, content quality, scope fit, safety, currency & coherence) plus Gate 6 (tool allowlist minimality). Use when reviewing a new agent draft before commit, evaluating a Mall agent or store agent for adoption, or re-auditing existing agents on a periodic cadence.
slayerman420/mimiq/skills/mimiq-memory Skill
no license0★ repoPersistent memory and feedback system for Mimiq. Stores all scrapes, style fingerprints, audits, ghostwritten posts, and user feedback in a local database at ~/.claude/mimiq-memory/. Links multiple social media profiles to a single user identity. ALWAYS trigger this skill at the START of every Mimiq session to load existing memory, and at the END of every session to save new data. Trigger on: "remember this", "save my fingerprint", "log this post", "show my history", "what did you find last time", "rate this post", "give feedback", "what posts have I written", "show my past audits", "update my profile", "which profiles are mine", "link my accounts", "show community insights", "opt into sharing", or any reference to past Mimiq sessions. Also trigger automatically after voice-capture, content-audit, or post-strategist completes — always save results without being asked.
yukihirop/nagi/.claude/skills/add-agent-hooks-open-code Skill
0★ repoAdd agent-hooks plugin for Open Code containers. Sends tool execution and session start notifications to chat channels. Triggers on "add open code hooks", "enable open code hooks", "setup open code hooks".
BTN101/claude-skill-pack/skills/engineering/backend-patterns Skill
0★ repoBackend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
The same file is in 3 other repositories
vdk888/bubble-skills/deepseek-brain Skill
0★ repoSwitch a Claude Code agent (Mac CLI, VPS systemd, or launchd) from Anthropic to DeepSeek as the LLM backend. Use when you want to run Claude Code with DeepSeek while keeping the full harness (tools, files, skills, channels). Covers the reasoning-effort proxy, model routing, channels fix, and rollback.
Roblox admin tools observability
AshExplained/roblox-skills/roblox-admin-tools-observability Skill
0★ repoDesign Roblox admin tools and observability systems. Use for safe grant/revoke tools, moderation commands, audit logs, live diagnostics, economy inspection, player support, operational dashboards, and abuse-resistant admin workflows.
sanjibani/mcp-skills-pack/skills/mcp-error-decoder Skill
0★ repoTranslates raw MCP error strings (HTTP 429 with Retry-After, 5xx with request-id, isError=true envelopes, GraphQL errors[]) into actionable diagnoses for the user. Use when an MCP tool call failed and you need to decide whether to retry, ask the user, or surface a fix. Triggers on phrases like "decode this error", "what does this MCP error mean", "is this retryable", "5xx", "rate limit", "GraphQL error".
SkillMedev/api-integration-engineering/skills/api-design Skill
0★ repoDesigns REST API surfaces - resource naming, HTTP method and status-code semantics, error shapes, pagination, and filtering - and delivers an endpoint spec a consumer can build against without asking questions. Use when someone asks "how should I name this endpoint", "what status code should this return", "should this be PUT or PATCH", "how do I paginate this list", or is reviewing an API before it ships to external consumers. Do NOT use for planning breaking-change rollouts and deprecation windows - use api-versioning-strategist instead; for GraphQL type and resolver design - use graphql-schema instead; for generating client SDKs from an existing spec - use api-client-generator instead; for designing inbound webhook endpoints - use webhook-receiver-hardener instead.
The same file is in 3 other repositories
vermapragya/analytics-skill/skills/ab-test-design Skill
0★ repoDesigns A/B tests with power analysis, minimum detectable effect (MDE), sample size estimation, randomization unit selection, guardrail definition, and a pre-registration checklist. Use when the user mentions experiment design, A/B test setup, power analysis, sample size, MDE, pre-registration, randomization, or asks "how should I run this experiment."
Srltas/claude-skills/cmt-manual Skill
0★ repoLook up CUBRID Migration Toolkit (CMT) behavior in the official online manual at www.cubrid.org/cmt_manual: source database support (Oracle, MySQL, MariaDB, MSSQL, Informix, Tibero, and more), data type mapping, migration wizard steps, console/CLI mode, reports, and configuration. Use when migrating a database to CUBRID and you need to verify what CMT supports, how a source type maps to CUBRID, or how a CMT option or console command works. For CUBRID engine SQL/JDBC questions, use the cubrid-manual skill instead. Triggers on phrases like 'CMT', 'CUBRID Migration Toolkit', 'migrate X to CUBRID', 'CMT type mapping', 'how does CMT handle', 'CMT console mode'.
Punpun1643/claude-skills/excalidraw Skill
no license0★ repoGenerate architecture diagrams as .excalidraw files from codebase analysis, with optional PNG/SVG export. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, generate excalidraw files, export excalidraw diagrams to PNG or SVG, or convert .excalidraw files to image formats.
Swellshinider/janitor/integrations/codex/skills/manager Skill
0★ repoUse when the codebase is structurally hard to navigate: oversized files or classes that should be split into cohesive modules, or a flat or misplaced directory layout that should be regrouped by feature or responsibility. Behavior-preserving structural refactor only: split files and move them into a cleaner layout, with import rewrites and re-export shims keeping callers unchanged. Run when the user says "this module is a mess", "split this giant file", "reorganize these folders", "group these files by feature", or "restructure this directory". Not for in-place dead-code removal or deduplication (that is the cleaner skill), nor for new features, bug fixes, or behavior changes.
NeuralMedic-DE/claude-skills/dbt-data-quality-gate Skill
0★ repoEnforce data quality, testing, contracts, and PII governance in a dbt project, gated by checks that actually run over dbt's compiled artifacts (target/manifest.json, target/run_results.json) — both plain JSON, so the gate is stdlib-only Python with no warehouse connection. Use when the user wants to add a data-quality CI gate, require tests/descriptions/owners on dbt models, enforce data contracts, check source freshness, find untagged PII columns, set a minimum test count or test pass-rate, or harden a data pipeline before merge. Triggers: "dbt", "data quality", "data contracts", "PII", "data tests", "freshness", "data pipeline gate".
jaballer/react-claude-skills/react-api-consumer Skill
0★ repoBuilding a React frontend against an external REST API — TanStack Query setup, the standard fetch wrapper with typed errors, loading/error/empty/refetching states, paginated lists with keepPreviousData, optimistic updates, retry policy, query keys, Vite dev proxy for CORS, normalizing third-party API quirks (boxed values, inconsistent envelopes, missing filters), the "verify the response shape with curl before typing it" rule. Use whenever a React app talks to a remote API — public REST, internal microservice, headless CMS, third-party SaaS. Triggers on "API", "REST", "fetch", "TanStack Query", "react-query", "SWR", "CORS", "headless CMS", "data fetching", "loading state", "pagination", "optimistic update", "retry", "error boundary", "stale-while-revalidate", "endpoint".
SkillMedev/performance-marketing/skills/ad-creative-testing Skill
0★ repoDesigns a disciplined ad creative testing system with hooks, isolated variables, and statistical rigor. Use when setting up a testing pipeline or when creative performance is declining.
The same file is in 1 other repository
Source command megaminx eval v
Erlemar/cayley-puzzles/.agents/skills/source-command-megaminx-eval-v Skill
no license0★ repoStrat-5 acceptance gate for a megaminx V model. Runs 51-pid stratified eval at beam 65k, compares to m05 baseline (50/51 / mean 89.4), reports pass/fail.
TheAkshitS/skills/skills/external-model Skill
0★ repoGet input from a different AI model (GPT-5, Gemini, Claude variants, or any model reachable via opencode/cursor-agent/kiro-cli) on a question, plan, or piece of code. Trigger this whenever the user wants another model's take, opinion, or judgment — "what would GPT-5/Gemini/another model say/think", "is this safe/right, get another opinion", "ask another model to check/review/weigh in", wants to delegate or run a prompt through cursor/opencode/kiro, wants to pick the best model for a task and run it, or wants to switch/set the default external-model CLI. Applies even without naming a CLI or model, and even when the ask is implicit ("before I ship this", "am I sure about this approach") rather than an explicit request for a "second opinion." Not for — re-running the user's own code/tests, asking Claude itself to reconsider, or general questions about what a CLI tool is/does.
Yuki001/nes-skills/skills/fceux-lua Skill
no license0★ repoWrite and run FCEUX Lua scripts for NES ROM automation — screenshots, PPU memory dumps, automated input, code execution tracing, and API discovery. Use when the user wants to automate FCEUX, capture ROM data, dump CHR/nametable/palette, trace code execution, or script NES emulation tasks. Triggers on mentions of FCEUX, Lua scripting for NES, ROM analysis automation, ppu.readbyte, memory.registerexec, gui.savescreenshotas, joypad.set.
whobat/AI-Agent-skills/skills/ax-retail/ax2012-sql-performance Skill
0★ repoDiagnose performance problems in Microsoft Dynamics AX 2012 (incl. R3) and its SQL Server databases — the AX transaction database, the model store, and the Retail channel database. The bundled script collects a read-only DMV snapshot (top queries, waits, blocking, deadlocks, missing/unused indexes, fragmentation, stale stats, config) as JSON; the agent interprets it through an AX lens — known bloat tables (InventSumLogTTS, batch history, database log, AIF logs), AX-specific SQL configuration (RCSI expected ON, TF4136, MAXDOP guidance), AOT-owned indexes, batch server load, and Retail CDX sync health. Use when the user reports AX/Dynamics AX slowness, slow posting or MRP, a slow Retail channel database, batch jobs piling up, or wants a health check of an AX 2012 SQL Server. Do NOT use for generic (non-AX) SQL Servers — that is sqlserver-perf-triage. Requires PowerShell 7+ and VIEW SERVER STATE.
argent-gnome/sdlc-skills/skills/house-orchestrator Skill
0★ repoThe house SDLC conductor — the long-lived session that drives a slice end-to-end. Use at the START of a development session to pick up the active slice, sequence the loop, dispatch house-builder subagents to build, run the gates, and reconcile. Building and reviewing run in dispatched subagents; the orchestrator sequences and gates but never edits code itself. Do NOT use for one-off questions, debugging, or non-build chat.