narthur-skills

Plugin narthur-skills from marketplace narthur in narthur/skills. Commands read from the repo's manifest — 3 days ago.

Skills (28)

• architecture

  Baseline architecture tenets for structuring projects: deep modules, lean on framework convention, monorepos for code that changes together, a services layer around external dependencies, raw SQL over optional ORMs, functional style, no premature abstraction. Use whenever making a structural decisio

• cleanup-worktrees

  Clean up stale git worktrees in the current repo — any tool (Claude, Zenflow, Vibe Kanban, PR triage, etc.) — by checking which branches are merged, then prompting the user to delete them. Use when asked to clean up worktrees, prune old worktrees, or tidy up worktrees from any tool.

• local-llm

  Leverage local Ollama models (qwen2.5-coder) for the current task. Invoke when you want Claude Code to offload cheap, recoverable subtasks — bulk filtering/extraction/classification, or redacting secrets/PII before sending text externally — to a local model instead of doing them in-context.

• name-it

  Brainstorm and evaluate names for a product, company, or library against Daniel Reeves' nominology criteria, then check domain availability across many TLDs. Use when the user asks for naming help, says 'name it', 'help me name', 'naming brainstorm', or mentions 'nominology'.

• organize-files

  Organize a folder of files by surveying contents, grouping by type, and presenting a numbered list for user decisions. Use when asked to go through, triage, or organize a folder of files.

• playwright

  Browser automation using playwright-cli. Use when asked to open a browser, navigate to a URL, click elements, fill forms, take screenshots, scrape web content, or automate browser interactions.

• prod-uvis

  Find user-visible improvements (UVIs) deployed to production in the current git repo that are not hidden behind a feature flag. Use when asked to find recent improvements, list what's been deployed to prod, or review what's visible to users.

• actions-usage-report

  Analyze GitHub Actions usage for a GitHub org and identify ways to cut billable minutes. Estimates billable minutes per workflow (private repos only — public repos run free), ranks the biggest cost drivers, compares CI vs Copilot review, and recommends concrete efficiency fixes. Use when asked which

• dependabot-alerts

  Surface open Dependabot security alerts for the current GitHub repo, prioritized by severity and cross-referenced with any open Dependabot PRs. Use when asked to check Dependabot alerts, review security vulnerabilities, see what dependencies need patching, or triage what to address.

• drive-pr

  Drive a pull request to a mergeable state: base integrated, conflicts resolved, CI green, every review comment resolved. Use when the user wants to drive a PR forward, get it to green, make it mergeable, resolve PR comments, fix CI, or resolve merge conflicts — even if there is no feedback yet. Driv

• fix-ci

  Address failing CI checks for the PR associated with the currently-checked-out git branch. Use when asked to fix CI, address failing checks, fix the build, or investigate why CI is failing — including when checks fail to *start* (startup_failure, 0 jobs, 'workflow file issue'), which is often an acc

• grooming

  Groom project issues by reviewing the most stale (least recently touched) issues one at a time. Runs a priority-ordered series of checks on each issue, summarizes results, then walks the user through each failing check's fix one at a time for approval. Use when asked to groom issues, clean up the ba

• issue-blitz

  Go through open issues one-by-one, assess each for actionability, and spawn background agents to fix actionable ones in isolated worktrees with PRs. Use when asked to blitz through issues, batch-fix issues, or auto-resolve open issues.

• pr-triage

  Go through open pull requests and take actions to move them toward merge. Use when asked to triage PRs, go through open PRs, or manage PR workflow. Runs autonomously on the user's own PRs and returns only once no autonomous work remains.

• resolve-feedback

  Retrieve, classify, and resolve PR review feedback from humans and bots — inline threads, review summaries, and PR comments — and mark each one resolved or dismissed on GitHub. Use when asked to resolve PR feedback, address review comments, or handle reviewer threads. drive-pr and pr-triage delegate

• split-pr

  Safely split changes from the current branch into a separate pull request. Use when asked to "split this PR", "extract changes into a separate PR", "create a separate PR for X", or when a PR is too large and needs to be broken up.

• walk-pr

  Walk through a pull request diff hunk-by-hunk, requiring the user to explain each hunk in their own words before advancing. Use when the user wants to UNDERSTAND a diff: onboarding onto unfamiliar code, studying a teammate's PR, or relearning their own. This is a comprehension tool, NOT a code revie

• ascii-screenshot

  Turn colored terminal / ASCII output (charts, TUIs, CLI output, asciigraph, lipgloss/bubbletea views) into a PNG image — preserving ANSI colors — for embedding in PRs, issues, docs, or READMEs. Use when asked to screenshot a TUI/CLI, capture terminal output as an image, or "add a screenshot" of text

• surge-image-upload

  Upload local image(s) to a public surge.sh URL and embed them in GitHub PRs/issues or any markdown — no browser required. Fallback only: for GitHub issue/PR bodies and comments, `gh --attach` (gh >= 2.99) uploads images and videos directly, so use this skill only when that is unavailable (GHES, a Gi

• trim-video

  Trim long idle/static periods in a screen recording (or any video) down to a max duration using ffmpeg scene detection. Use when asked to trim idle periods, remove dead air, or shorten a video recording.

• ui-mockups

  Produce low-fi UI wireframes/mockups as HTML/CSS, render them to a PNG, and (optionally) host the image and embed it in a GitHub issue/PR. Use when asked to mock up a screen/flow, wireframe a feature, sketch a UI, or attach visual mockups to an issue. Match the target app's real design idiom (theme

• bitter-lesson

  Audit my Claude Code skills for staleness and over-engineering against current model and harness capabilities, then propose deletions, simplifications, and fixes. Use when asked to run a bitter-lesson pass, audit my skills, find over-engineered or stale scaffolding, check what the harness now does n

• create-skill

  Scaffold a new Claude Code skill (personal or project-specific). Use when asked to create a skill, add a skill, or build a new slash command.

• refine-skill

  Review and improve an existing Claude Code skill. Use when asked to refine a skill, improve a skill, review a skill, or clean up a skill.

• update-project-skills

  Review the current conversation for frictions and problems, then update or create project skills to prevent them in the future. Use when finishing a task, after hitting repeated issues, or when asked to improve project skills.

• code-analysis

  Run every applicable automated analyzer against a repo — static tools that read the source (linters, SAST, secrets) plus dynamic ones that drive the running app (pa11y accessibility audits) — detecting languages/configs, running the curated CodeRabbit-weighted set (installed or ephemerally via npx/u

• review-loop

  Pre-push multi-agent code review loop with auto-fix, finding scores, and per-repo learnings. The reviewer for this setup. Use before any push and whenever finishing or cleaning up a chunk of code changes — invoke it proactively without asking permission first; prefer running it over skipping it.

• scannable

  Make any document readable at a glance, for use under pressure (mid-call, mid-incident, mid-task), in any format — Claude artifacts, HTML, PDF, Markdown/Obsidian, PowerPoint/slides, Word/Google Docs, email, chat, terminal output. Use when writing or revising a cheatsheet, glance sheet, crib sheet, r

Similar plugins