Best SKILL.md Files for Aider

Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

カスタムタスクでコーディングエージェント（Claude Code、Aider、Codex など）をヘッドツーヘッドで比較し、合格率、コスト、時間、一貫性のメトリクスを測定します

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.

编码代理（Claude Code、Aider、Codex等）在自定义任务上的直接比较，包含通过率、成本、时间和一致性指标

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".

The Paperclip way of converting a plan into executable tasks. Use whenever you are asked to plan, scope, or break down work inside a Paperclip company. Industry-agnostic guidance on how to translate a plan into assigned issues with the right specialty, dependencies, and parallelization so Paperclip's executor can pick up the work — it does not prescribe a plan format. Pair with the `paperclip` skill, which covers the mechanics of writing the plan document and reassigning the issue.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

Automate Repairshopr tasks via Rube MCP (Composio). Always search tools first for current schemas.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

Use this skill whenever the user wants to build scroll animations, scroll effects, parallax, scroll-triggered reveals, pinned sections, horizontal scroll, text animations, or any motion tied to scroll position — in vanilla JS, React, or Next.js. Covers GSAP ScrollTrigger (pinning, scrubbing, snapping, timelines, horizontal scroll, ScrollSmoother, matchMedia) and Framer Motion / Motion v12 (useScroll, useTransform, useSpring, whileInView, variants). Use this skill even if the user just says "animate on scroll", "fade in as I scroll", "make it scroll like Apple", "parallax effect", "sticky section", "scroll progress bar", or "entrance animation". Also triggers for Copilot prompt patterns for GSAP or Framer Motion code generation. Pairs with the premium-frontend-ui skill for creative philosophy and design-level polish.

Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.

Skill for using the command-line tool pdftk (PDFtk Server) for working with PDF files. Use when asked to merge PDFs, split PDFs, rotate pages, encrypt or decrypt PDFs, fill PDF forms, apply watermarks, stamp overlays, extract metadata, burst documents into pages, repair corrupted PDFs, attach or extract files, or perform any PDF manipulation from the command line.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Validate and auto-repair YAML frontmatter on brain pages. Catches malformed pages before they enter the brain (missing closing ---, nested quotes, slug mismatches, null bytes, empty frontmatter, YAML parse failures). Wraps the `gbrain frontmatter` CLI for agent-driven workflows.

Use when a Head of Ops, Knowledge Manager, or TPM-Internal needs to author, validate, or clean up company SOPs and internal runbooks (procurement intake, vendor offboarding, incident-comms cascade, employee onboarding) — including 5W2H completeness checks (Who-What-When-Where-Why-How-HowMuch), cross-link and orphan-page validation across a sprawling Notion/Confluence/Obsidian wiki, KB ingestion + hygiene reporting, and runbook step verification (named owner, expected duration, observable success signal, rollback path, escalation contact). Pairs Ishikawa's 5W2H method, Gawande's *The Checklist Manifesto*, ISO 9001, ITIL v4, and Google SRE Workbook runbook discipline with deterministic stdlib-only Python tools that score completeness, detect anti-patterns, and emit prioritized cleanup lists (e.g., "validate this runbook before it goes into rotation", "audit our Confluence wiki for stale and orphaned SOPs").

Use when a Head of People Ops, BizOps lead, or Internal Communications owner needs to draft and sequence an internal-only change-management communication — a re-org announcement, a tool rollout, a policy change, a leadership transition, a layoff, an acquisition close, or an internal product launch — and the audience is employees (not customers). Pairs Prosci ADKAR and Kotter's 8-step change model with deterministic stdlib-only Python tools to produce a sequenced touchpoint calendar, a Kotter-compliant primary announcement, an audience-segmented FAQ, and manager cascade talking points; industry-tuned via --profile {tech-startup, scaleup, enterprise, public-company, non-profit}. Triggers on "all-hands announcement", "change comms", "rollout comms", "re-org announcement", "manager talking points", "layoff comms".

Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being worked, and quantify the gap between processing time and total elapsed time. Pairs Lean / Six Sigma / Theory-of-Constraints canon with deterministic stdlib-only Python tools to produce a process map, a ranked bottleneck list (with severity + root-cause hypothesis), and a cycle-time analysis (P50, P90, value-add ratio, Little's-Law throughput). Distinct from sales-pipeline, system-reliability (SLO), and strategic-OKR work — this is tactical process documentation for internal operations.

Pi-compatible PUA high-agency governance skill. Use for explicit PUA/PIP requests, repeated failures, passive/giving-up behavior, user frustration, or unverified completion. Pair with /pua-on extension command when persistent pressure is desired.

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.

Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Telegram channel.

Manage Discord channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Discord channel.

Manage iMessage channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the iMessage channel.

--- name: advanced-evaluation description: This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment. --- # Advanced Evaluation This skill covers production-grade techniques for evaluating LLM outputs using LLMs as judges. It synthesizes research from academic papers, industry practices, and practical implementation experience into actionab

Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Use when the user asks to fix, debug, or make a specific feature/module/area work end-to-end. Triggers: 'make X work', 'fix the Y feature', 'the Z module is broken', 'focus on [area]'. Not for quick single-bug fixes — this is for systematic deep-dive repair across all files and dependencies.

Choose presentation-ready color palettes and font pairings for PPT/design tasks. Use when users ask for visual theme choices, brand-safe palettes, or font recommendations. Triggers include: 配色, 色板, 字体, color palette, font, PPT配色, 字体搭配.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.

Profound LLM citation tracker (extension). Time-series brand citation rates across ChatGPT, Perplexity, and other LLMs. Pairs with seo-seranking for triangulated AI visibility coverage.

Profound LLM citation tracker (extension). Time-series brand citation rates across ChatGPT, Perplexity, and other LLMs. Pairs with seo-seranking for triangulated AI visibility coverage.

Ahrefs API analyst (extension). Reads referring domains, backlinks, organic keywords, and content explorer data via the official @ahrefs/[email protected] server. Pairs with seo-backlinks for multi-source confidence weighting.

Ahrefs API analyst (extension). Reads referring domains, backlinks, organic keywords, and content explorer data via the official @ahrefs/[email protected] server. Pairs with seo-backlinks for multi-source confidence weighting.

Evaluate FX carry trade opportunities by combining spot rates, forward points, interest rate differentials, volatility surface analysis, and historical price trends. Use when analyzing carry trades, comparing FX forward curves, assessing carry-to-vol ratios, or evaluating currency pair opportunities.

Evaluate FX carry trade opportunities by combining spot rates, forward points, interest rate differentials, volatility surface analysis, and historical price trends. Use when analyzing carry trades, comparing FX forward curves, assessing carry-to-vol ratios, or evaluating currency pair opportunities.

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, choosing between Code node modes, or doing any custom data transformation in n8n. Always use this skill when a workflow needs a Code node — whether for data aggregation, filtering, API calls, format conversion, batch processing logic, or any custom JavaScript. Covers SplitInBatches loop patterns, cross-iteration data, pairedItem, and real-world production patterns. EXCEPTION — for the AI-agent-callable Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode, a tool attached to an AI Agent), use the n8n-code-tool skill instead; it has a different runtime contract.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, Microsoft Ads, and Apple Ads accounts via 6 parallel audit agents. Amazon Ads, cross-platform attribution, and server-side tracking are covered by their standalone sub-skills (ads-amazon, ads-attribution, ads-server-side-tracking) — Wave 3 will add their paired agents so they can dispatch in parallel here. Generates health score per platform and aggregate score (0-100). Use when user says audit, full ad check, analyze my ads, account health check, paid media audit, paid advertising audit, ad spend audit, advertising audit, or PPC audit.

Review pull requests for the awesome-agentic-patterns repository. Use when asked to validate a PR, assess whether a contribution fits the repo, inspect pattern submissions under patterns/, check merge readiness, repair a small submission issue on top of a contributor branch, draft a polite contributor comment, or apply the repository's pattern-first and non-promotional contribution policy to a GitHub pull request.

# Binance Event Contract Full Data Fetcher ## 1. Scenario Definition - **Trigger Timing**: Auto-run every minute after Agent startup; also supports manual trigger via `/binance-fetch-data`; runs 24/7, aligned with Binance 7×24 trading hours - **Core Intent**: Provide 100% accurate, delay-free Binance official native data for the 3-tier resonance strategy; reject all third-party data sources - **Context**: Targets only BTCUSDT & ETHUSDT pairs; covers only 10min/30min/60min Event Contract cycles;

Audit and fix all skills in the workspace for compliance with skill-creator requirements. Use when asked to "refine skills", "audit skills", "check skill quality", or "fix non-compliant skills". Exhaustively searches the entire workspace (not just skills/) to find every SKILL.md, then audits and repairs each one.

Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).

# Auto Repair Shop Operations Complete operational reference for independent auto repair shops. Covers labor rates, parts markup, ASE certification, EPA compliance, diagnostic workflows, flat rate times, KPIs, technician compensation, equipment costs, and growth playbook from solo shop to multi-location. ## When to Use - Setting labor rates by region and service type - Calculating parts markup strategy - Planning ASE certification for technicians - Ensuring EPA/OSHA compliance - Tracking shop

Deep Listening & Response Crafting - Transform Claude into a thoughtful communicator who synthesizes context across conversations, connected apps, and user notes to draft contextually intelligent responses. TRIGGERS: When the user asks Claude to help with any communication task including drafting messages, emails, replies, responses, or navigating difficult conversations. Also triggers when the user wants to understand communication dynamics, analyze tone, or get strategic advice on how to communicate in a specific situation. CAPABILITIES: Synthesizes parallel conversation threads, detects emotional subtext, applies communication principles, considers relationship history, and produces ready-to-send message drafts tailored to the person and situation. --- # Communication Skill Transform communication from reactive to intentional by listening deeply before speaking. ## Core Workflow Every communication task follows this process: ``` 1. GATHER → Collect all relevant context 2. LISTEN → Understand what's really happening 3. CONSIDER → Apply principles and psychology 4. CRAFT → Draft the response 5. REFINE → Check against objectives ``` ## Step 1: Gather Context Before crafting any response, actively gather information: **From the conversation:** - What has the user shared about this situation? - Who is involved and what is their relationship to the user? - What's the communication channel (email, Slack, text, in-person)? **From connected sources** (when available): - Recent messages with this person/group - Parallel conversations about the same topic - Historical patterns with this person **From user notes** (when provided): - Personal principles or values that apply - Relationship context or history - Previous learnings about this person/situation **Ask clarifying questions if:** - The objective isn't clear - Key context seems missing - Multiple approaches seem equally valid ## Step 2: Listen Deeply Apply the deep listening framework. See [listening-framework.md](references/listening-framework.md). Process in layers: 1. **Surface**: What was explicitly said? 2. **Context**: What's the surrounding story? 3. **Subtext**: What emotions and needs are beneath the words? 4. **Patterns**: What history informs this moment? Key questions: - What does this person actually need (vs. what they're asking)? - What's the emotional temperature? - What hasn't been said that matters? - What parallel threads connect to this? ## Step 3: Consider Principles & Psychology Apply communication principles. See [principles.md](references/principles.md). Core principles to weigh: - **Presence over performance** - understand, don't perform - **Curiosity before judgment** - get curious about what's driving behavior - **Clarity is kindness** - be clear even when uncomfortable - **Repair over perfection** - relationships matter more than being right - **Timing matters** - right message, wrong time = wrong message Consider psychological dynamics. See [psychology-patterns.md](references/psychology-patterns.md). Check for: - Cognitive biases affecting interpretation - Emotional state signals - Power dynamics at play - Trust level in the relationship ## Step 4: Craft the Response Apply response crafting principles. See [response-crafting.md](references/response-crafting.md). **Pre-draft checklist:** - [ ] What must this message accomplish? - [ ] What tone fits this person and situation? - [ ] What obstacles might prevent this landing well? - [ ] What structure serves the objective? **Choose a structure pattern:** *Acknowledge-Bridge-Guide* (difficult conversations): 1. Acknowledge their perspective genuinely 2. Bridge to shared understanding 3. Guide toward path forward *Context-Content-Call* (requests): 1. Brief relevant context 2. The actual content/request 3. Clear next step *Observation-Impact-Request* (feedback): 1. Specific, non-judgmental observation 2. How it affected outcomes 3. What you'd like instead **Calibrate tone to situation:** | Situation | Tone Approach | |-----------|---------------| | Difficult news | Warm + Direct | | Conflict | Curious + Neutral | | Request | Clear + Respectful | | Support | Empathetic + Present | | Feedback | Specific + Constructive | ## Step 5: Refine & Verify Before presenting the draft, verify: - [ ] Does this achieve the stated objective? - [ ] Does the tone match the relationship and situation? - [ ] Is it clear what the recipient should do/understand? - [ ] Does it respect the user's principles and values? - [ ] Is it appropriately concise? - [ ] Would I want to receive this message? ## Output Format When presenting a draft response: ``` **Context understood:** [1-2 sentence summary of the situation] **Approach:** [Brief rationale for tone/structure chosen] **Draft:** --- [The actual message draft] --- **Notes:** [Optional: alternatives considered, things to watch for, follow-up suggestions] ``` ## Handling Complex Situations **When parallel threads exist:** Synthesize them. Note where perspectives align/differ. Consider what each party knows. **When emotions are high:** Lead with acknowledgment. Don't problem-solve immediately. Create safety before substance. **When the relationship is strained:** Over-communicate intent. Avoid assumptions. Focus on repair over being right. **When stakes are high:** Take extra time. Consider unintended interpretations. When in doubt, ask the user for input. ## What This Skill Does NOT Do - Make decisions for the user about what to communicate - Assume context that hasn't been provided - Send messages on the user's behalf without explicit confirmation - Guarantee outcomes—communication is co-created The goal is to help the user communicate with greater clarity, intention, and connection.

# Binance Event Contract Full Data Fetcher ## 1. Scenario Definition - **Trigger Timing**: Auto-run every minute after Agent startup; also supports manual trigger via `/binance-fetch-data`; runs 24/7, aligned with Binance 7×24 trading hours - **Core Intent**: Provide 100% accurate, delay-free Binance official native data for the 3-tier resonance strategy; reject all third-party data sources - **Context**: Targets only BTCUSDT & ETHUSDT pairs; covers only 10min/30min/60min Event Contract cycles;