By sametbrr
Claude Code plugin that audits and fixes a GitHub account end-to-end — profile fields, profile README, repo descriptions, topics and project READMEs, interactively and per chosen scope.
Reads the authenticated GitHub user and reports missing or weak profile fields and social accounts against the bio standard. Read-only — never invents values.
Evaluates a GitHub repo description against the description standard and proposes a corrected one from its README, package metadata and language. Read-only — proposes, never writes.
Checks whether a GitHub repo has a README and reports missing or weak sections against the readme-standard. Read-only — reports, defers generation to the readme-standard skill.
Evaluates a GitHub repo's topics against the tags standard and proposes a canonical add/remove set based on its family, language and dependencies. Read-only — proposes, never writes.
Claude Code skill that produces a read-only GitHub account health report — missing profile fields, repo descriptions, topics and READMEs across a chosen scope (public/private/all) or a single repo. Writes nothing.
Claude Code skill that fills and standardizes GitHub repo descriptions and topics — single repo or batch across a chosen scope, with per-repo confirmation.
Claude Code skill that sets up or cleans a GitHub account end-to-end — interactively audits and fixes profile fields, profile README, repo descriptions, topics and project READMEs.
Claude Code skill that fills GitHub account profile fields — name, bio, company, location, blog and social accounts — via the GitHub API, asking for any missing value without inventing one.
Claude Code skill that generates and maintains the GitHub profile README (login/login repo) as README.md plus a Turkish mirror, built from live account data.
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin that audits and fixes a GitHub account end-to-end — profile fields, profile README, repo descriptions, topics and project READMEs, interactively and per chosen scope.
Point it at any authenticated GitHub account. It scans the account top to bottom, reports what's missing or off-standard, and fixes it interactively — asking where it can't infer, proposing where it can. Works on the whole account or a single repo.
Skills
gh-onboard — interactive end-to-end orchestrator (audit → fix, stage by stage)gh-audit — read-only account health report (writes nothing)profile-bio — fill account fields (name, bio, company, location, blog, social) via the APIprofile-readme — generate/maintain the <login>/<login> profile README + Turkish mirrorgh-normalize — fill and standardize repo descriptions and topics (single repo or batch)readme-standard — enforce a consistent README.md + README.tr.md structurerelease-workflow — install a project-type-aware auto-release GitHub Actions workflow (single local repo)Agents (read-only analyzers): account-analyzer, description-analyzer, tag-analyzer, readme-analyzer
Standards (canonical rules): STANDARDS/{description,tags,profile-bio,profile-readme}.md
--scope public|private|all — which repos to operate on (asks if omitted)--repo owner/name or the current directory's remote — single-repo modeprofile-bio, profile-readme) act on the account onceFirst run requests full scope once: gh auth login --web -s repo,read:org,user.
After that you only pick public/private/all per run.
Read before write. Every outward-facing change (repo edit, PATCH /user, push) is confirmed.
Identity values are never invented — missing fields are asked, not guessed.
MIT
npx claudepluginhub sametbrr/github-managerPersonal LLM-managed wiki: ingest sources, cross-reference pages, query with citations, and lint your markdown knowledge base
Turns any rough request into a structured, domain-aware expert prompt with an 8-gate quality review
Save conversation checkpoints as markdown files and resume them later with full context
Full programmatic access to Google NotebookLM: notebooks, sources, podcasts, videos, quizzes, flashcards and more
Daily Turkish HTML radar report of trending and talked-about projects, with a persistent watchlist
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.