Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
gstack
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with
elements, verify page state, diff before/after actions, take annotated screenshots, check
responsive layouts, test forms and uploads, handle dialogs, and assert element states.
~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
user flow, or file a bug with evidence.
gstack also includes development workflow skills. When you notice the user is at
these stages, suggest the appropriate skill:
- Brainstorming a new idea → suggest /office-hours
- Reviewing a plan (strategy) → suggest /plan-ceo-review
- Reviewing a plan (architecture) → suggest /plan-eng-review
- Reviewing a plan (design) → suggest /plan-design-review
- Creating a design system → suggest /design-consultation
- Debugging errors → suggest /investigate
- Testing the app → suggest /qa
- Code review before merge → suggest /review
- Visual design audit → suggest /design-review
- Ready to deploy / create PR → suggest /ship
- Post-ship doc updates → suggest /document-release
- Weekly retrospective → suggest /retro
- Wanting a second opinion or adversarial code review → suggest /codex
- Working with production or live systems → suggest /careful
- Want to scope edits to one module/directory → suggest /freeze
- Maximum safety mode (destructive warnings + edit restrictions) → suggest /guard
- Removing edit restrictions → suggest /unfreeze
- Upgrading gstack to latest version → suggest /gstack-upgrade
If the user pushes back on skill suggestions ("stop suggesting things",
"I don't need suggestions", "too aggressive"):
1. Stop suggesting for the rest of this session
2. Run: gstack-config set proactive false
3. Say: "Got it — I'll stop suggesting skills. Just tell me to be proactive
again if you change your mind."
If the user says "be proactive again" or "turn on suggestions":
1. Run: gstack-config set proactive true
2. Say: "Proactive suggestions are back on."
majiayu000/claude-skill-registry 163
-
nanobanana-skill
Generate or edit images using Google Gemini API via nanobanana. Use when the user asks to create, generate, edit images with nanobanana, or mentions image generation/editing tasks.
majiayu000/claude-skill-registry 163
-
323-frameworks-spring-boot-testing-acceptance-tests
Use when you need to implement acceptance tests from a Gherkin .feature file for Spring Boot applications — including finding scenarios tagged @acceptance, implementing happy path tests with TestRestTemplate, @SpringBootTest, Testcontainers with @ServiceConnection for DB/Kafka, and WireMock for external REST stubs. Requires .feature file in context. Part of the skills-for-java project
majiayu000/claude-skill-registry 163
-
compliance-audit
Regulatory compliance auditing across GDPR, HIPAA, PCI DSS, SOC 2, and ISO frameworks with automated evidence collection and gap analysis. Use when conducting compliance assessments, preparing for certifications, or implementing regulatory controls.
majiayu000/claude-skill-registry 163
-
traefik-udp-cross-namespace
Fix Traefik v3 (Helm chart v39+) UDP entrypoints not working for cross-namespace
IngressRouteUDP resources. Use when: (1) Traefik pod listens on a UDP port internally
but the LoadBalancer service doesn't expose it, (2) IngressRouteUDP logs show
"udp service <namespace>/<service> is not in the parent resource namespace" error,
(3) DNS or other UDP traffic through Traefik times out despite correct IngressRouteUDP
config, (4) Custom entrypoints added to Traefik Helm values don't appear in the
Service ports. Requires two fixes: expose the port AND enable cross-namespace CRD refs.
majiayu000/claude-skill-registry 163
-
prompt-oprogramadorreal-optimus-claude
Crafts optimized, copy-ready prompts for any AI tool — LLMs, coding agents, image generators, workflow tools. Extracts intent, selects the right template, runs a diagnostic checklist, and delivers a token-efficient prompt. Accepts input in any language; English output by default. Use when writing, fixing, improving, or adapting a prompt for any AI tool.
majiayu000/claude-skill-registry 163
-
pr-merge-temporal
Merge multiple PRs into a temporal integration branch before merging to base, with ordered conflict resolution. Use when you want to validate a set of PRs together on a staging branch before advancing the base branch.
majiayu000/claude-skill-registry 163
-
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
majiayu000/claude-skill-registry 163
-
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
majiayu000/claude-skill-registry 163
-
three-tier-docs
Use after code changes. Syncs CLAUDE.md, CONTEXT.md, and docs/ai-context/ automatically.
majiayu000/claude-skill-registry 163
-
cocoindex-v1
This skill should be used when building data processing pipelines with CocoIndex v1, a Python library for incremental data transformation. Use when the task involves processing files/data into databases, creating vector embeddings, building knowledge graphs, ETL workflows, or any data pipeline requiring automatic change detection and incremental updates. CocoIndex v1 is Python-native (supports any Python types), has no DSL, and is currently under pre-release (version 1.0.0a1 or later).
majiayu000/claude-skill-registry 163
-
moai-platform-firebase-auth
Firebase Authentication specialist covering Google ecosystem, social auth, phone auth, and mobile-first patterns. Use when building Firebase-backed or Google ecosystem apps, implementing social login, or adding phone verification.
majiayu000/claude-skill-registry 163
-
find
Agent-assisted file enumeration. Converts natural language intent into explicit, auditable fd parameters and executes deterministic file discovery over disk.
majiayu000/claude-skill-registry 163
-
api-architect
Expert API designer for REST, GraphQL, gRPC architectures. Activate on: API design, REST API, GraphQL schema, gRPC service, OpenAPI, Swagger, API versioning, endpoint design, rate limiting, OAuth flow. NOT for: database schema (use data-pipeline-engineer), frontend consumption (use web-design-expert), deployment (use devops-automator).
majiayu000/claude-skill-registry 163
-
int / if / output
General SOP for common requests related to int, if, output.
majiayu000/claude-skill-registry 163
-
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
majiayu000/claude-skill-registry 163
-
infra-change
Plan and apply infrastructure code changes safely by reviewing the target manifests or Terraform, presenting the diff or plan, and verifying the result.
majiayu000/claude-skill-registry 163
-
esp32-workbench-integration
Integrates an ESP32 project with the Universal ESP32 Workbench. Adds firmware modules (UDP logging, WiFi provisioning, OTA, BLE command handling, strategic log messages), updates build config, then writes the Workbench operations, Testing, and Appendix chapters into the project's existing FSD. Triggers on "integrate workbench", "add workbench", "workbench integration", "set up project", "add testing", "add tester".
majiayu000/claude-skill-registry 163
-
investigate
Systematic debugging with root cause investigation. Four phases: investigate,
analyze, hypothesize, implement. Iron Law: no fixes without root cause.
Use when asked to "debug this", "fix this bug", "why is this broken",
"investigate this error", or "root cause analysis".
Proactively suggest when the user reports errors, unexpected behavior, or
is troubleshooting why something stopped working.
majiayu000/claude-skill-registry 163
-
mcp-builder-jp
Simplified Japanese MCP (Model Context Protocol) server builder skill covering project setup, Japanese API integrations (Chatwork, Backlog, freee, kintone), and development guidelines. Triggers on requests for MCPサーバー構築, MCP開発, MCPツール作成.
majiayu000/claude-skill-registry 163
-
variation-matrix
Generate all possible ad variations from modular components (hooks, bodies, CTAs) with prioritized testing order. Use when planning creative tests, maximizing existing assets, or building a systematic variation testing schedule.
majiayu000/claude-skill-registry 163
-
siem
Monitors and analyzes security events and logs for real-time threat detection and incident response.
majiayu000/claude-skill-registry 163
-
every-style-editor
This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.
majiayu000/claude-skill-registry 163
-
prd-generator
Gera PRD/Spec para o Ralph Loop atraves de perguntas iterativas.
Use quando: (1) Usuario pede "cria PRD", "cria spec", "documenta feature",
(2) Precisa estruturar requisitos antes de implementar,
(3) Quer rodar Ralph Loop mas nao tem spec pronta.
majiayu000/claude-skill-registry 163