Self-messaging capability. Invoke this skill when you need to reframe your approach mid-task, break complex work into deliberate phases, or restart your reasoning with a fresh…
Use this skill before submitting code for review or merging a pull request. Covers a pre-merge checklist of common mistakes to catch.
Implement feedback loops where the harness checks its own work before declaring a task complete. Use this skill whenever the user mentions self verification, feedback loop, output…
This skill should be used when the user asks to "self review", "review my changes", "review this diff", "check this before I commit", or "review your own work", and proactively…
Merge alerts describing the same underlying issue despite different source IDs or wording, into a single incident.
Audits the generated HTML for semantic correctness — checks for a single h1, correct heading hierarchy, presence of landmark regions (main, nav, footer, aside), and document…
AST-based semantic conflict prediction for multi-agent coding environments. Uses tree-sitter to parse code into ASTs, extract symbol-level claims, build dependency graphs, and…
Group semantically similar log lines using embeddings despite differences in timestamps and variable fields, to collapse an incident's log volume.
Interpret a web page in conformance with the profile it declares about itself. Use when a page has a rel="profile" declaration, or when the user asks to read a URL by a declared…
This skill should be used when the user asks to "control a Mac app", "click a button in an app", "inspect a native app window", "type into a macOS application", "take a screenshot…
This skill should be used when the user asks to "install Semantouch", "set up macOS computer use", "fix Semantouch permissions", "debug a permission_denied error", "run semantouch…
Generate or update the THIRD-PARTY-LICENSES.md file for the Semaphore UI repository. Use this skill whenever the user asks to create, update, regenerate, audit, or refresh…
Plan and authorize a provider-neutral message or campaign send; this skill never delivers, so use a provider adapter for the actual send and its delivery evidence.
Guides developers through sending (disbursing) funds to a merchant via the Payroc Funding API — including checking available balance before disbursement and creating, tracking,…
Send a message to the user in a conversation. You MUST use this skill to reply in an existing conversation, start a new conversation, or proactively reach out.
Use this skill whenever asked to prepare, review, or classify transactions for a Senegal VAT (TVA) return. Standard rate 18%, reduced 10% (tourism). WAEMU member.
Use this skill after multiverse-analysis and before self-review. Identifies which parameters and assumptions, if changed within plausible ranges, would move the answer enough to…
This skill enables Claude to analyze the sentiment of text data. It identifies the emotional tone expressed in text, classifying it as positive, negative, or neutral.
Translate every `[SENTINELLA] ...` order received in the Captain's tmux into the correct action (throttle level, spawn/kill, freeze, soft-pause, resume).
Use this skill whenever asked to prepare, review, or advise on a Serbia VAT (PDV) return or any PDV-related classification.
MANDATORY tool selection protocol for Serena LSP tools vs Claude Code built-in tools. ALWAYS use when your tools list includes any mcp__serena__* tools.
Find blind spots that implementers miss through independent, layered verification. Use when the user has finished implementing a feature or fix and wants thorough verification…
Use this skill whenever the user asks to review, proofread, or check a sermon, sermon slides, or any church presentation (e.g. .pptx, .pdf, .docx).
Analyze 1-15 keywords to decode true search intent from the live SERP — not the keyword text alone. For each keyword, returns intent classification (informational,…
This skill should be used when the user asks about "Server Actions", "form handling in Next.js", "mutations", "useFormState", "useFormStatus", "revalidatePath", "revalidateTag",…
Read-only SRE triage of the Linux host this skill runs on. Discovers running containers and services dynamically, investigates common failure scenarios, and emits a struc — from…
Use this skill when working with Autotask Service Calls - creating, scheduling, updating, or completing service calls linked to tickets.
审查服务类合同（咨询/设计/IT/代理等）。 覆盖：服务范围定义、交付标准、验收条款、知识产权归属、保密、违约责任、合同变更与终止。 适用情形：用户说"审一下这份服务合同"、"咨询合同有什么坑"、"IT服务合同怎么审"。
This skill should be used when the user asks about "service layer pattern", "when to use service layer", "business logic layer", "application service", "transaction script", or…
Calculate real-time error budgets and availability metrics against defined infrastructure targets. Use this skill whenever the user mentions slo, sli, error budget, burn rate,…
Determine whether a customer location falls within a merchant's service isochrone for immediate fulfillment and pricing.
Build AI Agent definitions and Agentic Workflows for ServiceNow's AI Agent Studio using the Fluent SDK.
Programmatically EXECUTE existing flows, subflows, and actions from server-side scripts using sn_fd.FlowAPI.
Manipulate form field state using g_form APIs — no server calls required. Covers field value get/set, mandatory/read-only/hidden control, inline validation and error messages,…
Use this skill when working with PagerDuty services -- service catalog, service configuration, integrations, dependencies, maintenance windows, and service health monitoring.
Project state awareness and session recovery for GSD-managed projects. Use this skill whenever: starting a new work session, resuming after a break, the user asks "where did we…
Core behavioral guidelines and interaction patterns for the agent. This skill provides the foundation for how the agent should communicate and behave across all interactions.
This skill should be used when the user asks to "close session", "end session", "session closing", "/closing", "wrap up", "/wrap", "document learnings", "what should I commit", or…
Use this skill whenever the user says "harvest learnings", "anything worth remembering?", "what should I save?", "before I go...", or any variation of asking whether there are…
This skill should be used when inspecting, analyzing, or querying Claude Code session logs. Use when users ask about session history, want to find sessions, analyze context usage,…
Use this skill when the user asks to "analyze my sessions", "show session stats", "how productive was I", "session health", "what did I accomplish", "review my history", "how am I…
This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intelligence Infrastructure (RII) components.
This skill should be used when the user asks about "session learning", "learn from session", "improve future sessions", "session reflection", "session metrics", "session…
This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message.
Use when the user asks about THIS Claude Code session's token, cost, or runtime metrics — cost so far, tokens burned, runtime/elapsed/working time, per-model split…
Create KPI docs, compensation structures, screening questions, and hiring templates for any contractor role.
This skill should be used when the user asks to "set my lineup", "start him for me", "swap him into my flex", "update my lineup on Yahoo", "fix my lineup before kickoff", "apply…
Use this skill to install and verify Compose HotSwan end to end so a developer goes from zero to working sub-second hot reload on a real device or emulator in one session.
Plan authority to settle a known invoice under a spend-bounded grant; this skill never moves money, and an approved downstream spend runner must execute payment.
This skill should be used when the user needs to perform year-end closing adjustments (決算整理), review financial statements (決算書), compute depreciation, or review their trial…
This skill stress-tests a proposed settlement position before an offer goes out or comes back: the assumptions it depends on, your leverage and the opponent’s, the evidential…
Load, prepare, and apply quality control (QC) to single-cell RNA-seq data using Seurat. Performs data loading, QC filtering, normalization, and multi-sample integration.
职场性骚扰投诉处理相关法律问题咨询。 覆盖：性骚扰法律定义与认定标准、用人单位预防义务、投诉受理与调查程序、证据保全、处罚与救济措施。 适用情形：用户说"遇到职场性骚扰怎么办"、"公司遭遇性骚扰投诉怎么处理"、"性骚扰调查流程"。
Sync repos under repos/ to latest remote commits. Use this skill to initialize or update all SF repo clones.
> Use this skill whenever asked about Singapore CPF MediSave contributions for self-employed persons (SEPs).
> Use this skill whenever asked about Singapore income tax for self-employed individuals. Trigger on phrases like \"how much tax do I pay in Singapore\", \"Form B\", \"Form B1\",…
Use this skill when users ask about form validation in SGDS, hasFeedback prop, constraint validation, custom validation, noValidate, setInvalid, form submission, or reading…
This skill should be used when the user asks to "write a fragment shader", "make a GLSL gradient/noise/plasma background", "create an image transition (dissolve, displacement,…
This skill should be used when working with Shadertoy shaders, GLSL fragment shaders, or creating procedural graphics for the web.
Calculate structure heights from satellite shadows using licensed sun-angle and orbital ephemeris data.