Automation
Task automation and scripting
prompt-personagem
by marioluciofjr
Gera automaticamente prompts detalhados de personagens para inteligência artificial. Utilizando listas pré-definidas de atributos, o script cria descrições únicas combinando gênero, idade, tom de pele, penteado e poses variadas. Use esta skill SEMPRE que o usuário invocar o gatilho "/personagem", independentemente de qualquer outro contexto da conversa.
bash-linux
by xenitV1
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
plan-writing
by xenitV1
Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
clean-code
by xenitV1
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
create-script-template
by b-open-io
This skill should be used when the user asks to "create a script template", "add a new template to ts-templates", "create a BitCom template", "build an OP_RETURN template", or mentions creating templates for protocols like SIGMA, AIP, MAP, BAP, B. Guides creation of @bsv/sdk ScriptTemplate implementations.
continuous-improvement
by naimkatiman
"Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute, verify, reflect, learn, iterate. On-demand or weekly analysis to save tokens. Supports multi-agent parallel analysis."
writing-plans
by christopher-buss
Use when you have a spec or requirements for a multi-step task, before touching code
review-script-template
by b-open-io
This skill should be used when the user asks to "review a script template", "audit a template", "check template implementation", "validate ts-templates code", or mentions reviewing BitCom templates like AIP, MAP, SIGMA, BAP. Validates ScriptTemplate implementations against best practices.
requesting-code-review
by lv416e
"Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding タスク完了時、主要機能の実装時、またはマージ前に作業が要件を満たしているか検証する際に使用 - superpowers:code-reviewerサブエージェントをディスパッチし、計画や要件に対して実装をレビュー"
validate-bsv-script
by b-open-io
This skill should be used when the user asks to "validate BSV script", "analyze locking script", "parse unlocking script", "check script opcodes", or needs to validate and analyze Bitcoin scripts using @bsv/sdk.
example-skill
by tondevrel
Example skill template. Replace this description with keywords and triggers for your actual skill. This description determines when the skill auto-loads based on conversation context.
dask-optimization
by tondevrel
Advanced sub-skill for Dask focused on distributed system performance, memory management, and task graph optimization. Covers cluster tuning, efficient serialization, data skew mitigation, and dashboard-driven debugging.
hydration-safe-inputs
by ethanniser
Fix React hydration issues where user input typed before hydration gets wiped/cleared when React takes over. Use when (1) users report input fields clearing on page load, (2) working with SSR/SSG React apps (Next.js, Remix, Astro) that have controlled inputs, (3) auditing forms for hydration safety, or (4) building new forms in statically rendered React apps.
vn-payroll
by arisng
Calculates Net Income, Personal Income Tax (PIT), and Social Insurance (BHXH) based on Vietnam's progressive tax brackets.
orchestrator
by wyattowalsh
Build and deploy parallel execution via subagent waves, agent teams, and multi-wave pipelines. Use when the Decomposition Gate identifies 2+ independent actions or when spawning teams. NOT for single-action tasks or non-parallel work.
json-hygiene-agent
by richfrem
JSON Hygiene Agent. Detects duplicate keys in JSON configuration files that might be silently ignored by standard parsers. Auto-invoked for JSON audits or manifest validation. V2 includes L5 Delegated Constraint Verification.
solidity-deploy
by 0xlayerghost
"[AUTO-INVOKE] MUST be invoked BEFORE deploying contracts or writing deployment scripts (*.s.sol). Covers pre-flight checks, forge script commands, post-deployment validation, and verification. Trigger: any task involving forge script, contract deployment, or block explorer verification."
using-superpowers
by izyanrajwani
Meta-skill enforcing skill discovery and invocation discipline through mandatory workflows. Use when starting any conversation to check for relevant skills before any response, ensuring skill-first workflow before proceeding.
env-helper
by richfrem
Resolves shared ecosystem environment constants (HuggingFace credentials, dataset repo IDs, project root path) for any plugin without depending on internal shared libraries. V2 enforces Token Leakage constraints.
dev-workflow
by lodekeeper
Multi-agent development workflow for complex Lodestar features. Use for any task requiring architecture planning, implementation, and review. Covers spec design with gpt-advisor, implementation via Codex CLI or Claude CLI, review with sub-agents, and PR creation.
instruction-creator
by arisng
'Create and manage high-quality custom instruction files for GitHub Copilot. Use when you need to define new project-specific guidelines, workflows, or coding standards in the instructions/ directory.'
md-issue-writer
by arisng
Skill for creating and drafting markdown-based issue documents in the specified format, including bugs, features, RFCs, ADRs, tasks, retrospectives, etc. Use when you need to document software issues, features, decisions, or work items in .docs/issues/ or _docs/issues/ folders. This is distinct from the beads issue tracker system.
executing-plans
by izyanrajwani
Disciplined plan execution for implementation tasks. Use when executing a saved implementation plan, following step-by-step instructions from a plan document.
adk-expert
by danistrebel
An expert AI developer with in-depth knowledge about the Agent Development Kit (ADK) SDK.