ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
dcode:jtbd-prd-frame
Use when defining a feature, writing a PRD, or scoping work - reframes requirements around the user's job instead of the feature or team that owns it. Use before design or development begins.
majiayu000/claude-skill-registry 163
-
skill-validation-gf3
Skill Validation GF(3) - SLAVE (-1)
majiayu000/claude-skill-registry 163
-
gh-issue-fixer
GitHub Issue を修正するスキル。
以下の状況で使用:
(1) ユーザーが「Issue #XX を修正して」と依頼した時
(2) ユーザーが明示的に「/gh-issue-fixer」を実行した時
(3) GitHub Issue の対応を求められた時
majiayu000/claude-skill-registry 163
-
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
majiayu000/claude-skill-registry 163
-
stripe-webhook-validation
Fix for Stripe webhook signature validation failures in the payments app.
Use when: "Stripe webhook signature verification failed", "Invalid signature",
"No signatures found matching the expected signature", webhook 400 errors.
Only loads when working in apps/payments/.
majiayu000/claude-skill-registry 163
-
project-form
Guide for creating form modules with FormBloc state management and Flutter widgets in app_form packages (project)
majiayu000/claude-skill-registry 163
-
face-alignment
Face alignment, landmark extraction, and quality gating. Use when debugging alignment issues, reviewing rejected faces, or tuning quality thresholds.
majiayu000/claude-skill-registry 163
-
cursor-privacy-settings
Configure Cursor privacy and data handling settings. Triggers on "cursor privacy",
"cursor data", "cursor security", "privacy mode", "cursor telemetry". Use when working with cursor privacy settings functionality. Trigger with phrases like "cursor privacy settings", "cursor settings", "cursor".
majiayu000/claude-skill-registry 163
-
langgraph-multi-agent
Multi-agent architectures with LangGraph. Use when building systems with multiple collaborating agents, implementing supervisor or swarm patterns, creating hierarchical agent workflows, or designing agent handoff mechanisms. Covers langgraph-supervisor, langgraph-swarm, agent-as-tool patterns, and context engineering for multi-agent systems.
majiayu000/claude-skill-registry 163
-
consult
Technical consultation without implementation. Use when the user invokes /consult or asks questions about the code or approach.
majiayu000/claude-skill-registry 163
-
acc-create-test-double
Generates test doubles (Mocks, Stubs, Fakes, Spies) for PHP 8.5. Creates appropriate double type based on testing needs with PHPUnit MockBuilder patterns.
majiayu000/claude-skill-registry 163
-
mount
Skill mounting — modify character and room behavior through overlay
majiayu000/claude-skill-registry 163
-
yatl-tasks
Track multi-session work with dependencies using yatl (Yet Another Task List). Use when work spans multiple sessions, has dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.
majiayu000/claude-skill-registry 163
-
news-summary
Concise, structured summaries of news articles (~30 sec read time). Captures key points, context, bias/gaps, and open questions. Use when user shares article URL or asks to summarize news content.
majiayu000/claude-skill-registry 163
-
partner-integration-kit
Toolkit for coordinating system integrators, OEM partners, and service vendors in manufacturing pursuits.
majiayu000/claude-skill-registry 163
-
guardrails-safety
Instrument safety checks, content filters, and guardrails for agent outputs
majiayu000/claude-skill-registry 163
-
postfx-effects
Post-processing visual effects including chromatic aberration, vignette, depth of field, film grain, color grading, and LUT support. Use when adding cinematic polish, retro aesthetics, camera simulation, or atmospheric effects to 3D scenes. Essential for mood, style, and visual storytelling.
majiayu000/claude-skill-registry 163
-
architecture-analyzer
Architecture analysis, violation detection, and pattern validation.
USE WHEN: reviewing code architecture, identifying violations,
verifying patterns, updating technical documentation.
Reference: docs/02-architecture/ARCHITECTURE.md
Examples:
<example>
Context: User wants to check if code follows architecture.
user: "Analyze if the payment module follows our architecture"
assistant: "I'll use architecture-analyzer to review against ARCHITECTURE.md."
<commentary>Architectural review is architecture-analyzer specialty.</commentary>
</example>
<example>
Context: Need to identify technical debt.
user: "Find architectural violations in the services layer"
assistant: "I'll use architecture-analyzer to scan for violations."
<commentary>Violation detection is architecture-analyzer responsibility.</commentary>
</example>
majiayu000/claude-skill-registry 163
-
terminal-commands-rule
Specifies expertise in suggesting wrangler commands within the terminal environment.
majiayu000/claude-skill-registry 163
-
extract-skill-from-conversation
This skill should be used when the user asks to 'extract a skill from a conversation', 'convert conversation to skill', 'create skill from chat history', 'generate skill from session', or mentions extracting reusable workflows from Claude Code conversations. Uses Fabric AI patterns to distill conversations into actionable skills.
majiayu000/claude-skill-registry 163
-
using-tmux
Control interactive CLI tools that require a real terminal via tmux send-keys. Use for git rebase -i, git add -p, vim, nano, Python/Node REPLs, or any command that hangs waiting for terminal input.
majiayu000/claude-skill-registry 163
-
stakeholders-org-design
Use when designing organizational structure (team topologies, Conway's Law alignment), mapping stakeholders by power-interest for change initiatives, defining team interface contracts (APIs, SLAs, decision rights, handoffs), assessing capability maturity (DORA, CMMC, agile maturity models), planning org restructures (functional to product teams, platform teams, shared services), or when user mentions "org design", "team structure", "stakeholder map", "team interfaces", "capability maturity", "Conway's Law", or "RACI".
majiayu000/claude-skill-registry 163
-
coding-agent
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
majiayu000/claude-skill-registry 163
-
assisting-reverse-engineering
Provides reverse engineering analysis support including function identification, data structure analysis, and behavior understanding. Use when analyzing unknown binaries, understanding program structure, or investigating binary behavior.
majiayu000/claude-skill-registry 163