claude-skills

agent
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

Collection of Claude Code and Claude Desktop skills for developer workflows, automation, and productivity

README.md

Claude Skills

Personal collection of Claude Code skills for developer workflows.

Quick Start

To use these skills, copy them to your ~/.claude/skills/ directory:

# Clone and copy all skills
git clone [email protected]:mostafa-drz/claude-skills.git
cp -r claude-skills/code/* ~/.claude/skills/

# Or copy a single skill
cp -r claude-skills/code/whats-next ~/.claude/skills/

Skills Catalog

Claude Code (50)

Skill What it does Side effects
/address-pr-comments Fetches unresolved PR comments, categorizes them (must-fix, suggestion, question, nit), proposes fixes or replies for each, and executes approved actions. Yes
/address-pr-feedback Comprehensively addresses PR feedback by fetching all comments, deploying parallel agents for critical analysis of each suggestion, making implementation decisions, then systematically implementing fixes with incremental commits and browser validation. Yes
/audit-skills Audits all personal Claude skills against the SKILLS_GUIDE.md manifest, latest official Claude skills documentation, and best practices. Yes
/audit-ui-e2e Runs a beginner-mind end-to-end UI audit of any running app — local dev server, staging, production, or a specific URL. Yes
/build-incremental Implements code in progressive, verified increments — auto-detects the project's toolchain, builds each unit, runs checks (typecheck, lint, test), fixes errors, and commits with semantic messages. Yes
  /build-until-agreed Builds toward a goal agreed up front, then has independent read-only auditors judge whether it is actually met — looping build → blind audit → verify → fix until the harness passes, no verified blocking finding remains, and more than half of the auditors agree the goal is met. Yes
/capture-screens Automatically navigates a web app using Playwright MCP and captures context-aware named screenshots at each product feature state. Yes
  /chunk-pr Analyzes a large pull request (or branch, or commit range) and proposes a sequence of smaller, logically-grouped, merge-safe PRs following review best practices — dependency first, one concern per PR, mergeable in order. Yes
  /clean-copy Cleans terminal-formatted text and copies it to the macOS clipboard via pbcopy, formatted for the target platform (Gmail, Slack, LinkedIn, plain, markdown). Yes
/compliance-audit Audits codebases against compliance frameworks (SOC2, HIPAA, PCI-DSS, GDPR, ISO27001, etc.) using parallel agents per subdirectory/sub-repo. Yes
/create-pr Creates a well-structured pull request with product-focused summary, change highlights, and test steps. Yes
/creative-studio Makes brand-consistent creative assets end to end from a one-line brief: images, voiceovers, short vertical videos with burned-in captions (Reels, TikTok, Shorts), Instagram carousels, social cards, blog heroes and slide decks. Yes
/daily-brief Surfaces recent updates relevant to you from GitHub, Linear, Slack, and other configured sources — PR reviews, new assignments, ticket changes, mentions, and CI failures. No
  /docs-doctor Audits a repository's documentation for unused docs, wrong details, missing coverage, inaccurate data, broken structure, and writing best-practices. Yes
  /emotional-recap Reviews the user's past Claude Code conversations from a wellbeing perspective — sentiment, tone, emotional arc, recurring patterns — and generates a supportive, science-grounded report in both Markdown and HTML. Yes
/enrich-message Enriches a draft message with code references, Linear tickets, GitHub links, and factual data from the codebase and all available integrations. Yes
/exploration-to-spec Converts an exploration conversation (architecture discussions, codebase analysis, design decisions) into a structured technical specification document. Yes
  /extract-skill Scans the current conversation for patterns worth turning into a reusable skill or memory rule — feedback you've given Claude, workflows you've walked through, corrections, best practices, recurring setups. Yes
/get-up-to-speed Reviews the latest git history, branch state, Linear ticket, and open work to build a concise situational summary. No
/git-cleanup Identifies and removes stale git branches, orphaned remote branches, and unused worktrees. Yes
/guide-from-screenshots Generates polished markdown guides from a directory of screenshots and a narrative. Yes
/investigate-ci Investigates GitHub Actions workflow failures for any repo. No
/next-steps Generates a stakeholder-aligned next-steps checklist for a multi-stakeholder project from the current conversation and connected context. Yes
/organize-screenshots Scans a folder for recent screenshots, visually classifies which ones are relevant to current work, and organizes them into a target directory with descriptive filenames. Yes
/post-pr-for-review Generates a contextual Slack message for posting a PR to the team's review channel. Yes
/post-ticket-summary Posts a structured implementation summary comment to a Linear issue — what was built, key decisions, reuse patterns, and how to test. Yes
/project-updates Drafts Linear project status updates for each project the user leads, following the Done / In Progress / Next / Blockers template. Yes
/publish-skills Publishes personal Claude skills to a GitHub repository for sharing. Yes
/release-notes Generates brief, truth-based release notes for a release PR (typically main → prod) by listing each squash-merged PR, a one-paragraph summary drawn from each PR body, and the linked issue-tracker tickets (Linear, Jira, GitHub Issues, Asana, ClickUp, Shortcut, Plane, etc. Yes
  /remarkable-memory Turns handwritten reMarkable notes into a queryable semantic memory. Yes
/repo-timeline Analyzes a repository or branch and generates a meaningful, engineer-friendly timeline of changes — grouping commits into logical units with short and detailed descriptions, using git history, changelogs, GitHub PRs, and Linear tickets. No
/respond-to-message Crafts a response to a pasted message (LinkedIn, Slack, Gmail, Teams, etc.) in the user's configured tone and voice. Yes
  /screenshots-memory Turns scattered screenshots into a queryable, git-versioned memory. Yes
  /shop-research Researches products across Amazon, Google Shopping, and relevant specialty sites using the Claude-in-Chrome browser extension. Yes
  /should-i-buy Helps the user decide on a purchase by taking the product links they're considering, asking a couple of sharp clarifying questions about their needs and circumstances, then opening each link in real Chrome via the Claude-in-Chrome extension to extract price, specs, ratings, reviews, return policy, and shipping. Yes
  /sitemap-audit Audits a website's SEO discoverability by cross-referencing the codebase with live production. No
/skill-creator Creates new Claude Code skills interactively, enforcing every convention in SKILLS_GUIDE.md plus the learning, configurability, and feedback patterns used by the best in-tree skills (svg-art, should-i-buy, step-through). Yes
/slack-to-ticket Creates a Linear issue from a pasted Slack thread. Yes
/smoke-test Traces and verifies that something works end-to-end in any environment. Yes
/step-through Walks the user through a long enumerated response (numbered findings, audit list, refactor plan, bug list, PR review, recommendations, action items) one item at a time. Yes
/svg-art Generates artistic SVGs directly as code — minimal line icons, geometric marks, generative patterns, or hand-drawn compositions — and assembles a modern 2026 HTML gallery preview. Yes
/sync-branch Merges one branch into another with conflict handling. Yes
/thread-to-action Parses a pasted thread (Slack, email, GitHub, Teams), analyzes it against current git, Linear, and session context, and suggests actionable next steps — then executes them with confirmation. Yes
  /triage-board Generates a structured triage artifact from the current conversation's findings — a self-contained Desktop folder with a JSON Schema, schema-conformant report.json, prose markdown, and a single-file HTML viewer. Yes
/ui-test Runs UI tests described in plain English by driving real Chrome via the Claude-in-Chrome extension. Yes
/ux-interview Plays the role of a real user in an interview-style usability test. Yes
/weather Checks the current weather for the user's location using live online data. Yes
/whats-next Suggests the 3 most impactful next actions based on full developer context — git, Linear, PRs, and current conversation. Yes
/workday-summary Summarizes work done today into timesheet-ready bullet points. Yes
/workflow-advisor Analyzes recent Claude Code conversations and local Claude state (skills, settings, memory files, CLAUDE.md), researches the latest Claude Code features and best practices online, and suggests one workflow improvement at a time with reasoning and a concrete action item. Yes

Claude Desktop (11)

Skill What it does Side effects
/day-timeline Builds an evidence-based, reference-linked timeline of a single workday by merging every connected source — calendar, email, Slack and other chat, issue trackers, docs, and Claude Code sessions — into one chronological view, rendered as both Markdown and an elegant minimal HTML page. Yes
/inbox-catchup Scans all connected communication channels — Gmail, Slack, Calendar, and any available integrations — then produces a prioritized catchup briefing. Yes
  /learn-today Builds a daily deck of 3-5 learning picks (videos, articles, podcasts) for your work, business and life goals, with why and summary, learning from your feedback. Yes
  /make-it-itinerary Turns an existing travel conversation into a day-by-day trip itinerary. No
  /make-it-runbook Turns the current conversation into a trackable, phase-by-phase runbook: a page with a checkbox per step, a progress bar, amber bars for forced waits, notes for warnings, and copyable literal values (commands, DNS records, amounts). No
  /one-thing-today Picks the ONE thing to focus on today, for work, personal life or any area, from connected apps and memory, with why and a first step. Yes
  /remarkable-memory Turns handwritten reMarkable notes into a queryable semantic memory, on Claude Desktop. Yes
/research-assistant Researches a topic systematically and produces a structured briefing. No
  /take-care-of-my-plant Identifies a plant from a photo, builds a care profile, and keeps its watering, feeding and repotting history in a store the user already has — Filesystem, Google Drive, or Notion. Yes
  /which-chart Recommends the right chart for your data and use case: reads data or screenshots, asks up to 3 questions, then gives one pick and alternatives drawn from your rows. No
  /which-to-buy Compares 2-5 products side by side on one page: specs, prices, visual differences, and a pick for what matters to you. Yes

Each row links to that skill's SKILL.md, which is the authoritative description —
this table is generated from it by make catalog, so the two can never disagree.

Contributing to this repo

The frontmatter in each SKILL.md is the single source of truth — the catalog above and
skills.json (which mostafa.xyz renders from) are both generated from it. Put a skill's
trigger and tags in its frontmatter metadata: map; everything else is derived. After
adding or editing a skill:

make catalog   # regenerate the README table and skills.json
make check     # verify both are current and every frontmatter parses

You rarely need to run either by hand. Three layers keep it in sync, deterministically:

layer when what it does
PostToolUse hook Claude edits any SKILL.md runs make catalog immediately
Stop hook end of every Claude turn runs make check, silent unless something is off
GitHub Actions every push and PR the backstop — fails the build

The hooks live in .claude/settings.json and apply to anyone working in this repo.

Conventions live in the design guide, which covers what the
official docs don't: our house patterns, the
rules for skills that touch a user's files, and the constraints that fail at runtime
rather than at review.

License

MIT

Yorumlar (0)

Sonuc bulunamadi