when-automating-workflows-use-hooks-automation
について
このスキルは、明確なトリガー、検証、ロールバックを考慮したオーケストレーションを備え、開発者がワークフローフックを安全に自動化することを支援します。テレメトリとリトライロジックを含む、事前/事後フックおよびウェブフックを実装するための構造化されたアプローチを提供します。自動化されたコールバックを介してシステムを作成、更新、または連結する際にご利用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/DNYoussef/context-cascadegit clone https://github.com/DNYoussef/context-cascade.git ~/.claude/skills/when-automating-workflows-use-hooks-automationこのコマンドをClaude Codeにコピー＆ペーストしてスキルをインストールします
ドキュメント
STANDARD OPERATING PROCEDURE
Purpose
Design and maintain hook-based automations (pre/post hooks, webhooks) with explicit constraints, monitoring, and confidence-aware delivery.
Trigger Conditions
- Positive: creating/updating hooks, chaining systems via callbacks, adding validation to hook payloads, retry/backoff tuning, telemetry for hook events.
- Negative: manual single runs, prompt-only edits (route to prompt-architect), or new skill weaving (route to skill-forge).
Guardrails
- Skill-Forge structure-first: keep
SKILL.md,examples/,tests/in place; addresources//references/or log remediation tasks. - Prompt-Architect hygiene: capture HARD/SOFT/INFERRED constraints (auth, rate limits, payload schema), ensure English-only output, and declare ceilings.
- Hook safety: validate signatures, enforce idempotency, set timeouts/backoff, and define circuit breakers; honor registry-only agents and latency budgets.
- Adversarial validation: fuzz payloads, test retries, replay, and timeout scenarios; capture evidence.
- MCP tagging: store hook playbooks under WHO=
hooks-automation-{session}and WHY=skill-execution.
Execution Playbook
- Intent & constraints: define hook purpose, endpoints, SLAs, and compliance; confirm inferred requirements.
- Design: map triggers to actions, schema validation, auth methods, and telemetry.
- Safety nets: configure retries/backoff, idempotency keys, and failure isolation with rollback.
- Validation loop: fuzz and negative tests, replay/timeout drills, and timing checks; log evidence.
- Rollout: stage deployment, monitor early signals, and prepare rollback.
- Delivery: summarize design, evidence, risks, and confidence ceiling.
Output Format
- Hook intent, triggers, endpoints, and schemas.
- Auth/idempotency controls, retries/backoff, and rollback plan.
- Validation evidence (fuzz, replay, timeout) and risk register.
- Confidence:
X.XX (ceiling: TYPE Y.YY) - rationale.
Validation Checklist
- Structure-first assets present or ticketed; examples/tests reflect hook cases.
- Auth, retries, and rollback validated; registry and hooks within latency budgets.
- Adversarial/COV runs logged with MCP tags; confidence ceiling declared; English-only output.
Completion Definition
Hook automation is complete when validations pass, monitoring is in place, risks are owned, and evidence is persisted with MCP tags.
Confidence: 0.70 (ceiling: inference 0.70) - Hook automation doc rebuilt with skill-forge scaffolding and prompt-architect confidence and constraint discipline.
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
Algorithmic Art Generation
メタThis skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.