Cloudflare deployment hard constraints. MUST authenticate via scoped API Token in CLOUDFLARE_API_TOKEN env var (loaded from git-ignored .env), MUST bypass HTTP proxy on every Cloudflare API call (curl --noproxy '*', wrangler with NO_PROXY="*" no_proxy="*"), MUST extract account ID from /zones?name=<domain> when token lacks Account:Read and persist as CLOUDFLARE_ACCOUNT_ID. NEVER run `wrangler login` (OAuth breaks behind proxies/VPN), NEVER let a Cloudflare request traverse the local ClashX/HTTP proxy, NEVER commit credentials. Activates on any wrangler command, api.cloudflare.com call, or CLOUDFLARE_* env edit. MUST read SKILL.md BEFORE running wrangler commands, calling Cloudflare API, or editing CLOUDFLARE_* env vars.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "cloudflare-deploy-rules" with this command: npx skills add motiful/skillsmp-motiful-motiful-cloudflare-deploy-rules
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Generate and improve README files using a 3-tier layout strategy, GitHub-native formatting patterns, badge guidance, and a state-driven workflow. Use when the user says "write a README", "generate a README", "create a README", "improve this README", "review my README", "make my README better", "add badges", or "fix my README layout".
Rule-skill protocol — hard constraints delivered as dynamically-loaded skills with -rules suffix. MUST treat any skill named *-rules as MUST-level hard constraints (load-before-act, not advisory). When authoring new hard constraints, prefer rule-skill form over traditional rule files (unless universal-and-short). Existing -rules skills: raise loading priority, enforce strict compliance, proactively load when trigger scenarios match. Installation activates global protocol across Claude Code, Codex, Cursor, Windsurf, OpenClaw via scripts/install-meta-rule.sh — one meta-rule covers all -rules skills (current and future). Use when: writing MUST/NEVER boundaries for AI agents, evaluating whether a constraint should be a rule-skill, or modernizing legacy rule files. MUST read SKILL.md BEFORE creating any constraint skill.
Validate, fix, and publish skills as GitHub repos. Structures workflow skills for execution fidelity. Registers skills across platforms via symlinks and guides first-use onboarding. Use when the user says "create a skill", "forge a skill", "review this skill repo", "audit this skill", "audit all my skills", "audit this project", "clean up my skills", "check my skill", "publish this skill", "push this to GitHub", "structure my workflow skill", or points to a project directory with mixed skills and rules. Forge: discover → classify → validate → fix → local ready. Nothing found → onboard user, scaffold, then same pipeline. Publish to GitHub when requested (Step 4).
Progress file hard constraints. MUST maintain exactly one progress root per project per the location matrix, valid frontmatter with absolute dates on every progress doc, NN- numeric prefix only for time-ordered children in progress/ and research/ trees (never skill references), archive when files exceed ~200 lines preserving content verbatim, relative paths in all cross-file references. NEVER place progress under .claude/, maintain two progress files with mutual references, use relative dates, duplicate child content into parent, summarize archived content, or discard completed history. Activates on any progress file edit, migration, or new-session handoff. MUST read SKILL.md BEFORE editing, creating, moving, or archiving any progress or research tree file.