sametbrr

Claude Code skill that installs a project-type-aware auto-release GitHub Actions workflow (.github/workflows/release.yml) into a repo — reads the version from SKILL.md / package.json / *.csproj / pyproject.toml / VERSION and cuts a tag plus GitHub release on every version bump. Manually invoked, single local repo, never commits.

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.

Enforces a consistent README.md + README.tr.md structure across projects. Use when: - "readme oluştur" / "create readme" / "yeni readme" → Create mode: generates both README.md and README.tr.md from scratch - "readme kontrol et" / "audit readme" / "readme'yi incele" → Audit mode: prints a checklist report, writes no files - "readme düzelt" / "fix readme" / "readme standardize et" / "readme'yi güncelle" → Fix mode: rewrites existing README(s) to match the standard - "tr readme güncelle" / "sync tr readme" / "türkçe readme güncelle" → TR Sync mode: regenerates README.tr.md only from current README.md Supports Turkish and English triggers. Reads package.json / .csproj / pyproject.toml / SKILL.md to auto-detect project type, name, version, and description for badge generation. Standard: README.md is English-only with a TR reference link; README.tr.md is a full Turkish mirror with identical badges and untranslated code blocks.

Build, maintain, and query a personal LLM-managed wiki — a markdown knowledge base where the LLM owns all writing, cross-referencing, and bookkeeping while the user curates sources. Use this skill when the user wants to (1) bootstrap a new wiki, second brain, or research notebook; (2) ingest a new source (article, PDF, paper, transcript) and update relevant entity/concept pages, the index, and log; (3) query an existing wiki and synthesize an answer with citations, filing it back if useful; (4) update the wiki when a new source supersedes a claim across multiple pages (diff-before-write sweep); (5) lint the wiki for orphan pages, broken links, index drift, or stub pages — auto-dated reports. Trigger this when the user mentions a "second brain", "research wiki", "knowledge base", or "Memex", or asks Claude to track sources across sessions. Bundles four idempotent scripts and enforces the bookkeeping discipline that makes wikis compound rather than rot.

Architects any user input (in any language) into a structured, domain-aware expert prompt — classifies the domain, selects the right prompting patterns, drafts a refined English prompt, runs an 8-gate self-review, and optionally executes the deliverable. Use this skill whenever the user wants to turn a rough idea or request into a professionally engineered prompt, especially when the input involves strategy, UX, product, marketing, technical writing, business analysis, or any specialized domain. Trigger this skill when the user says things like "prompt yaz", "refine my prompt", "turn this into an expert prompt", "domain analizi yap", "strateji hazırla", "plan oluştur", or provides a task description in any language and wants it elevated into a structured, actionable expert-level output. Always use this skill when the request involves multi-step domain classification + prompt generation + optional execution.

Enforces a consistent README.md + README.tr.md structure across projects. Use when: - "readme oluştur" / "create readme" / "yeni readme" → Create mode: generates both README.md and README.tr.md from scratch - "readme kontrol et" / "audit readme" / "readme'yi incele" → Audit mode: prints a checklist report, writes no files - "readme düzelt" / "fix readme" / "readme standardize et" / "readme'yi güncelle" → Fix mode: rewrites existing README(s) to match the standard - "tr readme güncelle" / "sync tr readme" / "türkçe readme güncelle" → TR Sync mode: regenerates README.tr.md only from current README.md Supports Turkish and English triggers. Reads package.json / .csproj / pyproject.toml / SKILL.md to auto-detect project type, name, version, and description for badge generation. Standard: README.md is English-only with a TR reference link; README.tr.md is a full Turkish mirror with identical badges and untranslated code blocks.

Günlük trend & topluluk keşif radarı. Use this skill whenever the user asks to run the "Project Radar" (or just "the radar"), produce a daily report of trending and talked-about useful projects, scan GitHub trending, or summarize what's being discussed across GitHub, Hacker News, Product Hunt, newsletters and social — output is a standalone Turkish HTML report in the project's signature design. Surfaces practically useful projects (open-source repos, apps, devtools); AI/LLM tooling is prominent but real-world usefulness is the filter. Triggers: "project radar çalıştır", "proje radarı", "radar çalıştır", "github trending raporu", "bugün ne konuşuluyor", "run the radar". Also manages a persistent WATCHLIST: "<repo>'yu watchliste ekle" / "add <repo> to watchlist" writes a medium-depth detail report (Markdown + HTML); "watchlist'i getir" / "show watchlist" lists entries with file references. Discovery-only: NEVER clones, installs, builds, or runs candidate repos.

Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X", "install notebooklm", "add notebooklm to cowork"

Saves conversation checkpoints ("look again" entries) as .md files and resumes them later with full context. SAVE mode: when the user says "look again", "tekrar bak", "bunu kaydet tekrar bakacağım", or "save this for later", capture a structured context snapshot (decisions, rejected alternatives, next steps), the final plan, and the last request/response verbatim into ~/.claude/look-again/ (Claude Code) or a downloadable file (Claude.ai). RECALL mode: when the user says "tekrar bakacaklarım nelerdi", "look again list", "kaldığımız yerden devam et", "continue where we left off", or asks about saved checkpoints, list entries with short summaries and/or reopen one to continue the work with preserved context and consistent terminology. Always use this skill for any mention of saving conversation state to revisit later, or resuming a previously saved topic — even if the user doesn't say "look again" literally.