design-docs
Create and maintain living per-system design docs at thoughts/*/design-docs/<system-slug>.md — Purpose, Glossary, numbered testable Invariants (normative for the code-reviewing Spec axis), Boundaries & Non-goals, Interfaces, Decision log, Amendment log. Use when the user says "create a design doc", "write down the invariants", "document the design/contract of X", or when researching/planning/one-shot finds a design doc for the touched system and needs the read-and-abide rules.
engineering-standards
Code-shape policy for ALL code that gets written or reviewed — the senior-engineer bar for minimal complexity. Use whenever you are about to write code, design a module or abstraction, draft a plan phase that shapes code, or review a diff; also when the user asks "is this over-engineered", "can this be simpler", or pushes back on complexity. Sibling of desplega:delegate-work (which picks WHO executes; this skill defines WHAT good output looks like).
improve-agents-md
Improve (or bootstrap) an AGENTS.md / CLAUDE.md file using `<important if>` conditional blocks so the agent actually attends to the right guidance at the right time. Use this skill whenever the user mentions AGENTS.md, CLAUDE.md, agent instructions, project rules for AI, "my claude config", onboarding docs for agents, or asks to tighten / shorten / audit / rewrite an existing one — even if they don't explicitly say the filename. Also use when the user complains that an agent keeps ignoring their project rules.
one-shot
Small-scope plan+implement in one session. Assess the prompt, optionally one bundled round of questions, maintain a lightweight yolo plan while implementing, verify, quick code review, commit. Use when the user invokes /one-shot, or asks to "just build/fix/add" something small without the full create-plan → implement-plan pipeline. Small means ≤ ~3 phases inside one subsystem — anything bigger escalates to /desplega:create-plan.
script-builder
Generate durable, re-runnable scripts from session intent — validation scripts (PASS/FAIL contract) AND gather/bulk scripts (many API/tool calls in code, one derived summary out). Supports TypeScript, Python, Bash with auto-detection, enforces context-optimal output, and auto-documents scripts in CLAUDE.md. Triggers on "turn this into a script", "I want to test/validate X end-to-end", "wrap this in a re-runnable script" — and, critically, whenever you are about to make (or just made) ~10+ similar tool/API calls or any bulk fan-out over a list: that mechanical middle belongs in a script, not in context.
step-running
Execute a single DAG step as an autonomous background sub-agent. Sibling of phase-running for DAG plans produced by v-planning. Reads a step-<n>.md file directly, atomically claims it via frontmatter status, runs the three-bucket Success Criteria, and reports back. Spawned by v-implementing or by /run-step.
tackle-gh-comments
Work through every review comment on a GitHub PR — fetch the threads, verify each claim against the code, fix what is real, then reply and mark each thread resolved before pushing. Use when the user says "tackle the PR comments", "address the review", "handle the bot comments", "check the comments on the PR", "resolve the review threads", or invokes /tackle-gh-comments. Project-agnostic; works in any repo with a GitHub remote.
v-implementing
Parallel DAG-plan implementation skill. Reads a v-planning plan directory (root.md + step-<n>.md files), topologically schedules ready steps, and fans them out as parallel sub-agents. Use whenever the user invokes /v-implement, points at a plan directory produced by /v-plan, or asks to "run the parallel plan", "implement the DAG", or "fan out the steps" — even without those exact words. For linear plans (single .md file), use `implementing` instead.
v-planning
Vertical / parallel implementation planning skill. Creates DAG-structured plan directories where each step is an independent, QA-able vertical slice that sub-agents can pick up and implement in parallel. Use whenever the user wants a plan that fans out (multiple independent features), invokes /v-plan, or asks for a "parallel plan", "DAG plan", "vertical plan", or "plan that can be parallelized" — even if they don't say those exact words. Prefer the linear `planning` skill for strictly sequential work.
feedback
Give Radically Candid feedback to the user — kind, clear, specific, and sincere — based on Kim Scott's framework (Care Personally × Challenge Directly). Use this whenever the user asks for your opinion, review, critique, or pushback on a plan, idea, code, writing, design, or decision; when the user invites honest disagreement ("tell me what you really think", "be honest", "poke holes in this", "am I missing something"); when something the user just said or did looks wrong and silence would be Ruinous Empathy; or when the user explicitly invokes /radical-candor:feedback. Prefer this skill over generic agreeable responses any time feedback would be more useful than validation. Default to a short headline reply and offer to expand — don't dump the full analysis unprompted.
cardano-cli-plutus-scripts-operator
Execute Plutus script transactions: script spends, datum/redeemer submission. Manual invoke only.
cardano-cli-plutus-scripts
Plutus script guidance: datums, redeemers, collateral, reference scripts. Templates only—use operator to execute.
cardano-cli-staking-operator
Execute staking operations: registration, delegation, rewards withdrawal. Manual invoke only.
cardano-cli-staking
Staking guidance: registration, delegation, rewards. Provides templates (no execution). Use operator skill to execute.
cardano-cli-transactions-operator
Execute transaction builds and submits. Manual invoke only—requires explicit confirmation before submit.
cardano-cli-transactions
Transaction guidance: build, sign, submit patterns. Provides templates (no execution). Use operator skill to execute.
cardano-cli-wallets-operator
Execute wallet operations: key generation, address building. Manual invoke only for safety.
cardano-cli-wallets
Wallet guidance: key generation, address building, UTxO queries. Provides templates and explanations (no execution).
cardano-devnet-in-a-box
One-command local rehearsal stack: cardano-node + hydra + ogmios + kupo. Docker-based, deterministic green/red testing.
cardano-mcp-balances
Read-only wallet state via cardano MCP: balances, addresses, and UTxOs. Requires a configured cardano MCP server.
cardano-mcp-identity
Retrieve ADAHandle identities ($handle) for the connected wallet via cardano MCP. Read-only.
cardano-mcp-staking
Query staking delegation status and available rewards via cardano MCP. Read-only, no delegation changes.
cardano-mcp-transactions
Sign and submit pre-built Cardano transactions via cardano MCP. High-risk: requires structured preview and explicit user confirmation.
cardano-protocol-params
Protocol parameters: fetch pparams, understand fees, min-UTxO, execution budgets. Read-only diagnostics.
hydra-head-operator
Execute Hydra operations: init, commit, open, close, fanout. Manual invoke only due to L1 state changes.
hydra-head-troubleshooter
Hydra troubleshooting: decision tree for common issues. Maps symptoms to fixes with verification steps.
hydra-head
Hydra Head guidance: setup, keys, peers, lifecycle. Best practices from hydra.family. Use operator skill for execution.
koios-agent-wallet
Quick setup of key-based Cardano agent wallets with MeshJS (MeshWallet) and KoiosProvider: generate wallet (no mnemonic), register stake address, and stake to a pool. Use when users ask to generate a wallet, register it, stake it, send transactions, or query wallet state via Koios.
meshjs-cardano
MeshJS patterns: tx building, wallet connectors, script interactions. TypeScript/JavaScript Cardano development.
plutus-v3-conway
Plutus V3 under Conway: unified context, governance scripts, V2→V3 migration. Conceptual and practical guidance.
aiken-dex-security-audit-operator
Operator skill: run local Aiken build/test commands and capture evidence for the audit. Manual invoke only.
aiken-smart-contracts
Aiken workflows: validators, building, blueprints, .plutus generation. Safe guidance for smart contract development.
cardano-cli-doctor
Diagnose cardano-cli: version, era-prefixed vs legacy syntax, network flags. Produces compatibility report.
cardano-cli-operator
Manual-only operator command for Cardano CLI: dispatches directly to OpenClaw Exec Tool (no model) so you can run deterministic, approval-gated cardano-cli commands (native or Docker fallback).
gitsite-content-manager
自动管理 GitSite 静态网站生成器项目的 blogs、books 和 pages 内容。当用户需要创建博客文章、书籍章节、书籍或静态页面时使用此 skill。该 skill 会自动创建正确的目录结构、生成带有完整 frontmatter 的 Markdown 模板文件，并提供内容管理的 Python 脚本。适用于使用 GitSite CLI 构建的静态网站项目。
notebooklm-ppt-designer
国际一流PPT设计架构师，将内容素材（讲稿/主题词/大纲）转化为可直接执行的PPT设计方案。适用于：(1) 根据演讲稿生成PPT设计提示词，(2) 将主题词扩展为完整PPT设计方案，(3) 为内容大纲选择最佳视觉形式，(4) 生成符合品牌视觉规范的设计参数，(5) 输出Gamma Pro等工具可用的生成指令。当用户提及"PPT设计"、"演示文稿"、"幻灯片"、"presentation"、"slides"、"设计方案"、"NotebookLM"、"Gamma"、"Keynote风格"等关键词时触发。
feishu-bitasks-manager
飞书多维表格管理工具。智能识别字段，自动适应不同的表头结构。支持获取记录列表、创建记录、更新记录状态。适用于各类飞书多维表格项目。
zotero-search
Search the user's local Zotero library, find related papers via Semantic Scholar, and discover citations/references. **Claude only** - this skill requires a local Zotero instance and access to a port on localhost. Use when the user asks to search their Zotero library, find papers on a topic, explore citations of a paper, or find related literature. Supports cross-referencing Semantic Scholar results against the local library.
bq-query-optimization
Use when writing BigQuery queries, optimizing query performance, analyzing execution plans, or avoiding common SQL gotchas. Covers parameterized queries, UDFs, scripting, window functions (QUALIFY, ROW_NUMBER, RANK, LEAD/LAG), JSON functions, ARRAY/STRUCT operations, BigQuery-specific features (EXCEPT, REPLACE, SAFE_*), CTE re-execution issues, NOT IN with NULLs, DML performance, Standard vs Legacy SQL, and performance best practices.
gcp-bq-table-management
Use when creating BigQuery tables, implementing partitioning or clustering, managing table schemas, or optimizing table structure. Covers time-based partitioning, range partitioning, clustering strategies, DDL commands, and table configuration.
gcp-cli-gotchas
Use when encountering gcloud or bq CLI formatting errors, quote escaping issues, command substitution problems, or when debugging CLI commands. Provides solutions for backtick usage, heredoc syntax, timestamp filters, parameter escaping, and multiline command formatting.
gemini-qa
Use Google Gemini CLI to answer questions about code, analyze files, or perform codebase exploration. Invoke this skill when the user asks to use Gemini, wants a second opinion from another AI, or wants to compare Claude's answer with Gemini's response.
hubspot-crm
Use when syncing contacts or lists to HubSpot CRM. Automatically uses HUBSPOT_API_TOKEN from environment.
n8n-workflow
Use when creating, deploying, or managing N8N workflows. Automatically uses N8N_HOST and N8N_API_KEY from environment.
playwright-browser
Use when capturing screenshots, automating browser interactions, or scraping web content. Covers Playwright Python API for page navigation, screenshots, element selection, form filling, and waiting strategies.
slack-webhook
Use when sending Slack alerts or notifications. Automatically uses the configured SLACK_WEBHOOK_URL from environment.
codex-qa
Use OpenAI Codex CLI to answer questions about code, analyze files, or perform read-only codebase exploration. Invoke this skill when the user asks to use Codex, wants a second opinion from another AI agent, or wants to compare Claude's answer with Codex's response.
data-export-formats
Use when exporting data for ad platforms (Google Ads, Meta) or working with project datasets. Documents exact CSV formats for Enhanced Conversions, Customer Match, and project data schemas.
gcp-bq-data-export
Use when exporting BigQuery data to Cloud Storage, extracting tables to CSV, JSON, Avro, or Parquet formats, or using EXPORT DATA statements. Covers bq extract command, format options, compression, and wildcard exports.
gcp-bq-data-loading
Use when loading data into BigQuery from CSV, JSON, Avro, Parquet files, Cloud Storage, or local files. Covers bq load command, source formats, schema detection, incremental loading, and handling parsing errors.
Page 649 of 1647 · 82342 results