claude

sejas-ai-code-skills

Spec-driven development skills that leverage AI to optimize daily coding workflows and improve productivity.

0 on GitHubupdated 6 months agocode_general
/

Plugin sejas-ai-code-skills from marketplace cascade-code-general-misc-3 in joshuarweaver/cascade-code-general-misc-3. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (36)

  • ai-prs

    List all open PRs targeting the Studio AI command with draft status, approval state, and requested reviewers

  • ai-radar

    Use when Antonio wants to catch up on frontier AI — "what's new in AI", "AI radar", "what is karpathy working on", "AI trends", "research digest", "what should I learn next", "where to invest learning time", or /ai-radar.

  • blog-post

    This skill should be used when the user asks to "write a blog post", "draft a blog post", "create a blog post", "write an article about", or wants to produce a markdown blog post on any topic. Outputs to ~/claude.nosync/posts/.

  • brainstorming-names

    Use when the user wants to name or rename something — a product, feature, brand, project, command, or company — or asks to "brainstorm names", "find a better name", "naming ideas", or invokes /brainstorming-names.

  • commit

    Write a commit message and create a git commit. Use when the user wants to commit changes, asks for a commit message, or says "commit this" or "make a commit".

  • context-window-statusline

    This skill should be used when the user asks to "set up a status line", "configure the footer", "show context window usage", "add a statusline", "visualize context window", "customize the Claude Code footer", or wants to display token counts, cost, or session metrics in the Claude Code terminal foot

  • create-agents-md

    Use when the user asks to create AGENTS.md, generate agent instructions for a repository, set up CLAUDE.md, or wants to document project conventions for coding agents. Also use when user says "create agents md", "setup agent docs", or "initialize repo for agents".

  • design-review

    Designer's-eye QA of a running UI — screenshots it at real breakpoints, then reports spacing, hierarchy, alignment, contrast, state and motion defects ranked by severity, with the CSS/component fix for each. Use when asked to "design review", "review the UI", "does this look right", "make this look

  • explain

    Search the codebase for function source code and explain it like for a junior developer

  • explore-exploit

    Use when a task has a large solution space and a measurable quality signal and the goal is to generate many candidates and select the best — naming/branding, UX/UI variants, marketing copy, code optimization, prompt tuning. Triggers: "brainstorm and pick the best", "explore and exploit", "simulated

  • first-time-contributors

    Use when checking whether recently merged PRs in a GitHub repository include first-time contributors — e.g. "who merged their first PR", "new contributors last week", crediting/celebrating a new contributor, or drafting a shout-out tweet/post. Works on the current repo or any given owner/repo list.

  • id-photo-sheet

    Use when the user needs ID/passport/carnet photos (foto carnet, foto de carné, DNI, visa) at an exact mm size (e.g. 23x32, 26x32, 35x45 mm) tiled on photo paper (10x15 cm / A6, 13x18, A4) as a print-ready PDF, from a phone selfie or portrait photo.

  • mac-cleanup

    This skill should be used when the user asks to "clean up my Mac", "free disk space", "my disk is full", "what's taking up space", "reclaim storage", "offload files", or wants to dedupe/archive backups and media to remote storage. Provides a scan → categorize → offload/clean → reclaim workflow with

  • make-pdf

    Turn a markdown file into a publication-quality PDF — cover page, clickable table of contents with page numbers, running headers, page numbers, curly quotes, syntax-highlighted code, optional DRAFT watermark. Use when asked to "make a PDF", "export to PDF", "turn this markdown into a PDF", or "gener

  • og-inspect

    Inspect a URL's Open Graph and Twitter Card metadata and render a styled HTML page showing how the link unfurls on Facebook, X/Twitter, LinkedIn, Slack/Discord, and Tumblr. Also prints a JSON summary to stdout. Use when the user asks to "preview a link", "check OG tags", "inspect Open Graph", "see h

  • pr-leaderboard

    Use when asked to analyze, rank, or explore merged PRs in a GitHub repo — "who merged what this week", "PR leaderboard", "rank contributors", "top authors", "PRs merged since X", weekly/monthly merge activity — for the current repo or any owner/repo.

  • pr-review

    List PRs awaiting your review, checkout the branch, run linter, and generate a structured code review document.

  • presentation

    Generate a Marp presentation from an intent's spec. Use when the user wants to create slides for an intent or asks to make a presentation.

  • question
  • quick-pr-review

    This skill should be used when the user asks to "quick review a PR", "fast pr review", "review this PR without checkout", "review PR diff", "review PR #123", or provides a GitHub PR URL for lightweight review without checking out the branch. Reads PR description, comments, and review threads, fetche

  • react-doctor

    Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.

  • release-notes

    Use when writing or polishing release notes for a version from a list of merged PRs (e.g. RELEASE-NOTES.txt, CHANGELOG). Produces concise, user-facing, thematically grouped notes where every line covers one coherent change and every PR is cited exactly once, with scripted verification.

  • review-queue

    Use when Antonio asks which PRs are still open and waiting for his review, wants a merge-confidence table from his saved review docs, or says "review queue", "rate my open PRs", "which PRs can I merge", "what's open in the repo", or invokes /review-queue.

  • review-sweep

    Use when Antonio wants to review every PR waiting for his review — "review sweep", "sweep my review queue", "trigger review agents for my PRs", "which PRs need review and review them", or /review-sweep. Also when re-checking a queue already reviewed to catch new or updated PRs.

  • score

    Use when the user asks to rate, score, judge, critique with a number, or "how good is" an artifact — a live website/UI, a markdown draft (blog post, README, plan, docs), or code/a diff — or invokes /score, or sets up an iterate-until-score-N feedback loop (e.g. with /goal "repeat until 9/10").

  • standup

    Create or update today's work standup file. Pulls PR activity from a GitHub Enterprise host (via context-a8c MCP) and github.com (via gh CLI), deduplicates across sources and sections, preserves existing content. Use when the user says "update my standup", "today standup", "fill my standup", or invo

  • start-issue

    Start work on a Linear issue end-to-end — create a worktree, fetch issue context from Linear, implement the fix, then commit, push, and open a draft PR. Use when the user says "start issue", "work on STU-1234", "create a worktree and fix <Linear link>", "start a worktree for this ticket", or gives a

  • studio-debug

    Debug WordPress Studio local sites — inspect SQLite database, check logs, troubleshoot plugins/themes, and diagnose common issues in the Studio local environment.

  • sync-skills

    Sync recently edited skills (`~/.claude/skills/<name>/`) and workflows (`~/.claude/workflows/<name>.js`) to a public skills repo. Reads the dirty-marker written by the `skill-dirty-marker.sh` PostToolUse hook, sanitizes secrets and personal identifiers, copies files to the repo, scans the staged dif

  • teach

    Act as a wise, effective teacher who makes the user deeply understand the current coding session — the problem, the solution, and the broader context. Use when the user says "teach me", "make sure I understand this", "walk me through what we did", "/teach", or wants to internalize a change, bug fix,

  • today

    Show enriched daily activity from Claude Code sessions — branches, PRs, Linear issues, and what you worked on. Use when the user wants to see what they did today, review their daily work, or get a summary of their sessions.

  • todo

    This skill should be used when the user asks to "add a todo", "add a task", "remind me to", "add to things", "create a todo", "save a task", "todo", or wants to add items to their Things 3 task manager.

  • travel-routes

    Use when user wants to extract travel routes from Apple Photos geolocation (via osxphotos), build interactive maps, list visited cities, or prepare data for summer vacation blog posts and year-in-review summaries. Triggers "travel route", "trip map", "what cities did I visit", "vacation recap", "/tr

  • unworktree

    Use when the user wants to undo, absorb, collapse, or reverse a git worktree — "undo worktree", "absorb worktree", "move worktree branch back to main repo", "remove worktree and checkout in main", "get rid of this worktree", or finish work in a ~/worktrees.nosync worktree and continue it in the main

  • worktree

    Create a new git worktree from origin/trunk in ~/worktrees.nosync and copy node_modules. Use when the user wants to "create a worktree", "new worktree", "start a worktree branch", or needs an isolated working directory for a feature branch.

  • yolo-guardian

    Use when the user is on guardian/on-call rotation duty and asks for a "guardian check", "daily guardian", "guardian duties", "triage the queues", "guardian handoff", or invokes /yolo-guardian. Runs the daily monitoring checklist (Slack pings, Linear triage, Dependabot PRs, Buildkite builds, Sentry i

MCP servers (1)

  • playwright

    runs: npx -y @playwright/mcp@latest

View source on GitHub

More from joshuarweaver/cascade-code-general-misc-3

All 149 plugins →

Community-curated, human-vetted skills for AI coding and agent tools. Focused on practical, production-ready skill implementations.

200 skills

0

CFN Loop skill for unified error handling, batching, and structured logging across agent failures with categorization and recovery.

169 skills · 9 agents

0

Search and discover Claude Code skills and MCP servers from marketplaces and GitHub. Use to find tools for specific tasks or explore available integrations before building custom solutions.

160 skills

0

Collection of Claude Code plugins tailored for streamlining software development and engineering processes.

85 skills

0

Pre-built SWE workflows for Claude Code covering development patterns, testing strategies, and engineering best practices for software projects.

32 skills · 40 agents

0

Supercharged plugin collection with 109 components: 22 agents, 32 commands, 55 skills across 13 modular plugins. Includes deep reasoning, autonomous dev loops, DDD architecture, git automation, and design system enforcement.

66 skills

0

Similar plugins

AI-powered codebase understanding — analyze, visualize, and explain any project

9 skills · 10 agents · hooks

Egonex-AI/Understand-Anything 92,410

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

humanizer

claude

Rewrite AI-sounding text so it reads like the writer without changing what it says.

1 skill

blader/humanizer 68,461

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

llm-finetuning

claudecodex

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents

wshobson/agents 42,461

Maintain sejas-ai-code-skills?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins149 plugins