Deploy code from the current directory to Railway using `railway up`.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Deploy code from the current directory to Railway using `railway up`.
Collects or updates the status for a backlog item. Use this skill to prompt for and validate backlog status as part of planning workflows. Supports interactive mode for user input.
>-
Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
>-
Senior Project Manager for Software, SaaS, and digital web/mobile applications. Use for strategic planning, portfolio management, stakeholder alignment, risk management, roadmap development, budget oversight, cross-functional team leadership, and executive reporting for software products.
Docker containerization best practices. Use when creating Dockerfiles or docker-compose configurations.
Create UX scenario outlines from Trigger Map through structured micro-steps
Assign task risk tier and change type with explicit rationale.
Verify visual alignment across sections. Check consistent left edges, centered elements, grid alignment.
Enforce stage-by-stage implementation for multi-step task briefs. Use when acting as the implementor to deliver one stage at a time, pausing for explicit user confirmation before proceeding unless the user requests all stages at once.
Shorthand for agora-collab in fix mode. Use when a user wants to collaborate on a bug fix with another agent in Agora.
When explicitly authorized, execute end-to-end with a phased plan in one run until Definition of Done is met.
Manage AI agent skills across projects — sync, validate, and maintain shared skill libraries.
Ingest external plans with conflict detection against project decisions before writing anything.
Ingest raw source files into the study repo wiki. Use when Codex needs to process a file from raw/, summarize the scope, update or create focused notes, add source frontmatter, move the source to raw/processed/, and append log.md.
Run a result-focused iterative loop with strict phase contracts, evaluation rules, and persistent state between sessions.
>-
Use when optimising context window usage in agents. The four zones of context management.
Use when choosing between multi-agent architecture patterns. Five patterns compared.
Use when choosing between RAG, fine-tuning, and prompting approaches. Decision tree for the right technique.
Use when choosing between coordination patterns for multi-agent systems. Stigmergic vs centralised comparison.
Use when understanding the mythological and philosophical foundation of AI safety. Ancient bee priestesses and AI.
Feed this agent a data file (appointment export, referral data, financial data) and it runs ALL relevant analyses automatically — no questions, pure insights. Produces a comprehensive operational intelligence report covering capacity, revenue, variation, demand patterns, workforce health, and anomalies. Use with 3+ months of appointment data for meaningful results.
Synthesise overnight incidents, today's capacity vs demand, provider availability, regulatory deadlines, and operational red flags into a structured 2-minute morning briefing. Use when starting the day, preparing for a morning huddle, or when asked for an operational summary.
Estimate immune and stromal cell composition from bulk RNA-seq using multiple algorithms. Wraps CIBERSORT, quanTIseq, EPIC, xCell, MCP-counter, TIMER, and ESTIMATE through the immunedeconv unified int
Navigate French real estate law for individuals — leases, mandatory diagnostics, tenant rights, co-ownership, energy renovation aids (MaPrimeRenov), and rental taxation.
Use this skill when working with Iron Claw. Triggers when user mentions Iron Claw or imports from it.
Use this skill when working with n8n. Triggers when user mentions n8n or imports from it.
Export a single-file HTML slide deck as individual PNG images — one per slide. Renders in headless Chrome with fullPage screenshot, then slices with Pillow. Use when the user wants slide images for social media, docs, or any use case that doesn't need PPTX.
Strategic session-end preservation. Captures decisions, discoveries, and state that the automatic hooks miss.
>
Run the DesignVault `/execute` lane from one approved implementation plan. Use when Codex needs to read a plan, run preflight, execute phases in order, verify results with the narrowest valid evidence, write back changed wiki truth, and finish with one execution log.
Create and upgrade agent skills for distribution across Claude Code, Codex, Gemini CLI, and OpenClaw. Every decision accounts for end users who receive the skill package, not just the author.
Audit and repair GitHub repository health with Ceratops defaults, using scripted live checks first for machine-checkable GitHub settings.
Ship local repository changes through GitHub and any relevant artifact registry with Ceratops defaults, using scripted live repo and PR checks before merge decisions.
Drive substantial tasks through staged contingent execution with Ceratops defaults. Use when Codex should diagnose first, prefer the simplest standard fix, advance only to the next justified stage, ask before complex or high-maintenance solutions, and finish with a risk-based closure pass.
Create a minimal copy-paste prompt for spinning a newly discovered side task into another thread. Use when Codex should ignore most of the original task and capture only the side task's origin, conclusion, current objective, minimal refs, and next step.
'Post-Deployment Healthcheck aller MOe-Services mit automatischer Statusauswertung und Rollback-Empfehlung'
Work with the contenteditable editor implementation. Use when modifying text input behavior, cursor handling, or undo/redo functionality.
Use AlgoKit Utils to interact with the Algorand blockchain from TypeScript or Python applications.
Контекстное логирование в Go с github.com/muonsoft/clog. Используй при добавлении логов, работе с контекстным логгером в internal/ и cmd/.
Hey Agent! Welcome to Among Us On-Chain. You're about to compete in a social deduction game where you'll play as either a **Crewmate** or an **Impostor**. Winners take the prize pool. Follow these ins
forge-symbol
>
Score an agent's creditworthiness using on-chain history and ML prediction. Returns credit score, risk tier, and recommended loan terms.
Remotely add a worker node to an existing k3s cluster — installs Tailscale, joins via k3s agent over DERP relay, updates config.
/*
Create and submit a PR with git-spice (stacked diffs). Use when the user wants to open or submit a PR, create a stacked PR, or mentions git-spice.
/*