mblode

38 mods across 4 repositories, 109 stars between them.

mblode/agent-skills

Instructions file CodexOpenCode

Instructions for mblode/agent-skills, covering repository guidelines, project structure & module organization, install / development commands, primary install (recommended) and local dev: symlink hot-swap.

95 2d ago B 1,016 tokens original MIT

mblode/agent-skills

Instructions file

Instructions for mblode/agent-skills, a project described as: Skills for shipping better software.

95 2d ago A 3 tokens copy · 100% MIT

mblode/agent-skills

Skill Claude CodeCodex

Guides creation and improvement of best-practice agent skills following the open format specification. Covers frontmatter, progressive disclosure, reference files, rules folders, degrees of freedom, constraint calibration, executable scripts, MCP tool references, evaluations, constraint ablation, whether to adopt or…

95 2d ago B 182 tokens original MIT

agents-md

04

mblode/agent-skills

Skill Claude CodeCodex

Sets up a repo so Claude Code, Codex, and Cursor all work in it, then audits, scores, and refactors the AGENTS.md and CLAUDE.md files agents load at session start. Execution-first standards: working commands, real-failure gotchas, signal-to-noise, portable imports, and enforcement that survives tool choice. Runs a…

95 2d ago A 232 tokens original MIT

autoship

05

mblode/agent-skills

Skill Claude CodeCodex

Runs the npm release flow for an existing changesets package: create a changeset, fix lint/type/test/format failures, push, watch CI, merge the Version Packages PR, watch publish, and verify npm. Use when asked to "release this", "publish this package", "autoship", "cut a release", or fix build failures inside a…

95 2d ago A 103 tokens original MIT

ax-audit

06

mblode/agent-skills

Skill Claude CodeCodex

Audits agentic applications for architecture and trust: tool parity, tool granularity, context injection, completion signals, approval gates, confidence cues, escape hatches, intent handshakes, memory visibility, and adaptive canvases. Produces a ship-readiness verdict plus an AX Relationship Summary. Use when…

95 2d ago A 126 tokens original MIT

mblode/agent-skills

Skill Claude CodeCodex

Designs, deepens, and hardens TypeScript codebase architecture in three modes: folder structures, module contracts, and middleware pipelines for a new app; domain-informed deepening of existing code; and the guardrail tooling, CI gates, and wayfinding that stop a structure decaying. Use when setting up project…

95 2d ago A 203 tokens original MIT

copywriting

08

mblode/agent-skills

Skill Claude CodeCodex

Writes and edits short product and marketing copy, including landing pages, CTAs, onboarding strings, product descriptions, email subjects, UI state copy, brand voice charts, and AI-ism cleanup. Use when asked to "write copy", "fix the copy", "make this shorter", "improve the CTA", "rewrite from first principles"…

95 2d ago A 147 tokens original MIT

docs-writing

09

mblode/agent-skills

Skill Claude CodeCodex

Writes and audits technical documentation using the Diataxis framework and Stripe-style clarity. 48 rules across 9 categories covering voice, structure, clarity, code examples, formatting, navigation, scanability, content hygiene, and review. Use when writing docs, documenting APIs, writing documentation-site…

95 2d ago A 141 tokens original MIT

dx-audit

10

mblode/agent-skills

Skill Claude CodeCodex

Audits the smallest relevant developer-facing surface of a library, CLI, SDK, or npm package across API contracts, errors, CLI behavior, public types, onboarding, and config. Uses candidate-first rule loading, bounded local evidence, and compact root-cause findings. Use when asked to "audit my CLI", "make this CLI…

95 2d ago A 194 tokens original MIT

eli5

11

mblode/agent-skills

Skill Claude CodeCodex

Rewrites assistant talk into plain language a smart adult can follow on the first read: one-sentence gist, one everyday analogy, short sentences, next action first, and no AI writing tells. Use when asked to "ELI5", "explain like I'm 5", "wait what", "re-pitch that", "in plain English", "dumb it down", "I don't get…

95 2d ago C 140 tokens original MIT

mblode/agent-skills

Skill Claude CodeCodex

Provides architecture guidance for multi-tenant SaaS platforms on Cloudflare or Vercel. Covers platform choice, domain strategy, tenant identification and isolation, subdomain routing, custom domains and SSL, white-label setup, tenant context propagation, PSL submission, and mapping platform limits to pricing plans.…

95 2d ago A 132 tokens original MIT

optimise-seo

13

mblode/agent-skills

Skill Claude CodeCodex

Optimises SEO, answer-engine readability, and technical foundations for Next.js App Router apps, covering sitemaps, robots, meta tags, structured data, canonical URLs, redirects, indexing policy, llms.txt and AI-crawler policy, hreflang, Core Web Vitals, programmatic SEO, security headers, privacy/consent, and…

95 2d ago A 243 tokens original MIT

planning

14

mblode/agent-skills

Skill Claude CodeCodex

Builds and stress-tests implementation plans in two modes. Create mode scans code and docs, asks one question at a time with a recommended answer, runs a blindspot pass when the user is new to the area, then writes a plan file. Review mode scores completeness, feasibility, scope, testability, risk, and assumptions…

95 2d ago A 240 tokens original MIT

pr-babysitter

15

mblode/agent-skills

Skill Claude CodeCodex

Monitors an open PR, detects it from the current branch, polls for conflicts, CI failures, review comments, and merge readiness, fixes safe issues, and reports only state changes. Monitor mode uses the Monitor tool when available, falling back to CronCreate/CronDelete; without either, run one-shot modes only. Use when…

95 2d ago A 141 tokens original MIT

pr-creator

16

mblode/agent-skills

Skill Claude CodeCodex

Creates GitHub pull requests with short, human-sounding descriptions. Adds a Linear issue ID prefix when available, keeps titles under 60 chars, and defaults to one short paragraph instead of generated summaries or test-plan sections. Restructures noisy commit history into reviewable order and adds reviewer guidance…

95 2d ago A 216 tokens original MIT

pr-reviewer

17

mblode/agent-skills

Skill Claude CodeCodex

Reviews the local diff or branch and returns a read-only, severity-tiered findings report. Modes cover standard bugs, structural quality, AI slop, and security audit. Use when asked to run /pr-reviewer, "review my changes", "code review", "thermo-nuclear review", "structural review", "deslop this", "clean up AI code"…

95 2d ago A 186 tokens original MIT

mblode/agent-skills

Skill Claude CodeCodex

Creates bold, minimal presentations built on a story spine, with punchy slide copy, high-contrast visual design (full-bleed palettes or dark with section accents), and conversational speaker notes. Covers live talks, async/recorded decks, 10-slide investor pitch decks, and decks built as a web app with a route per…

95 2d ago A 180 tokens original MIT

product-design

19

mblode/agent-skills

Skill Claude CodeCodex

Decides what an interface should do before UI is built or audited: interaction choice, action scope and consequence, reachable states, resilience, and accessibility as task completion. Works from a brief, spec, mockup, intent, or existing UI. Use when asked "is this the right interaction", "design the flow", "what…

95 2d ago A 185 tokens original MIT

readme-creator

20

mblode/agent-skills

Skill Claude CodeCodex

Writes or rewrites a project's README.md as a public-facing shop window with a centered header, one fast install, one runnable example, and nothing that only serves contributors. Detects project type (CLI, library, app, framework, monorepo, skill bundle) to pick capability sections, then validates against a quality…

95 2d ago A 168 tokens original MIT

save-md

21

mblode/agent-skills

Skill Claude CodeCodex

Writes a talk, blog, post, conversation, URL, PDF, image, or file to a markdown file the next turn rereads as context, not a chat summary or a guessed talk. Use when the user says "save this", "save this article", "convert this", "keep this source", "get the markdown", "transcript this", "extract this PDF", or "turn…

95 2d ago B 178 tokens original MIT

scaffold-cli

22

mblode/agent-skills

Skill Claude CodeCodex

Scaffolds a production-ready TypeScript CLI and npm package with ESM, a dual tsdown build (CLI binary plus typed library), vitest, oxlint and oxfmt via ultracite, changesets, GitHub Actions CI with OIDC npm publishing, AGENTS.md, and a bundled agent skill definition. Use when creating a new CLI tool, bootstrapping a…

95 2d ago A 151 tokens original MIT

scaffold-nextjs

23

mblode/agent-skills

Skill Claude CodeCodex

Scaffolds a production-ready Next.js turborepo end to end. Runs create-next-app with TypeScript 7, Tailwind CSS, React Compiler, and Cache Components, sets up shadcn/ui with Blode UI components from the Blode registry, blode-icons-react icons, Agentation, and Ultracite (Oxlint, Oxfmt, Lefthook), converts the app into…

95 2d ago A 223 tokens original MIT

seo-program

24

mblode/agent-skills

Skill Claude CodeCodex

Runs the demand side of an SEO and AEO program in two modes. Topic pipeline pulls live keyword and prompt volumes with real numbers, builds an answer-engine question map, and writes a writer content brief. Monitoring watches Search Console and prompt visibility and reports only state changes. Binds each job to…

95 2d ago A 204 tokens original MIT