representing-information
claudeDecide what to show, how much, and in what form when presenting data, ontologies, processes or qualitative findings to a particular audience — the judgment behind a visualisation, not the rendering of one.
1 skill
Claude Code and Codex plugins their authors filed under "productivity". All categories.
Decide what to show, how much, and in what form when presenting data, ontologies, processes or qualitative findings to a particular audience — the judgment behind a visualisation, not the rendering of one.
1 skill
レビュー指摘を適用する。依頼が機械的に安全な編集を承認しているとき、またはファイルを変更せずに具体的な編集候補を求めているときに使う。
1 skill
業務要求を既存のスキーマやSQLに照らしてモデル化し、一貫したデータモデル、必要に応じたDBML、データ設計、エンティティ関係、スキーマ整合性についての根拠付きの指摘を作る必要があるときに使う。
1 skill
観測可能な確認項目、期待状態、アクセス可能な描画済みページ、許可された操作が依頼で示されているとき、実装済みUIを検証する。
1 skill
Sends macOS notifications when Claude Code needs permission to execute commands
hooks
Analyze coding patterns and get personalized learning resources
1 skill
Publish HTML or Markdown documents to share.eregistrations.dev and get shareable URLs. Commands: /share <file>, /share list.
1 skill
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like \"map this codebase\", \"document this architecture\", \"onboard me to this repo\", or \"create codebase docs\". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.
1 skill
Use this skill when building AI agents that call external tools, implementing policy-based access controls, adding semantic intent classification, creating trust scoring systems, building audit trails, or enforcing rate limits and content filters on agents.
1 skill
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects transcripts.
1 skill
Grades a Claude Code session against the 7-dimension vibe-coding rubric; outputs scored JSON + Bahasa Indonesia coaching. v0.7.x: skoring jadi deterministik penuh — seluruh perhitungan nilai pindah ke scripts/validate.py (`--score`), subagent grader hanya mengembalikan misses + saran, plus 25 counter anti-cheap-ritual dan applicability clamp untuk sesi tanpa kerja substantif. v0.6.0 (anti-gaming): bobot rubrik direbalance (15/15/15/18/20/12/5); misses WAJIB ≥2 per sesi → total_score maks 98; score caps deterministik dari work_evidence (sesi pendek/tanpa friksi tertangani dibatasi); deteksi prompt sintetis dari first_user_prompt; scripts/validate.py jadi gerbang mekanis wajib sebelum upload; first_user_prompt dikirim ke leaderboard untuk audit; hard reject transcript non-Claude-Code. v0.5.0: dimensi delegation menilai orkestrasi skill & subagent secara terukur (D1 subagent / D2 skill / D3 MCP) dari sinyal ground-truth (toolUseResult, attributionSkill) yang sukar dipalsukan; sesi tanpa skill+subagent ≤6/15; digest.py emit tool_usage+signal_availability (→ raw_payload, tanpa perubahan BE); laundering compact ditutup; calibration anchor + evidence-first di prompt grader. v0.4.1: file sementara /tmp per-transkrip (fix baca digest basi lintas sesi). v0.4.0: prompt_analysis dikirim, plus usage_totals/type_counts/grademe_version. v0.3.0: mandatory live-session grading, digest.py preprocessing, session_name + compacted, endpoint venturo.pro.
1 skill
Bundles the offshore MCP server. Forwards refused prompts to a local abliterated model (Ollama, LM Studio, vLLM, or any OpenAI-compatible endpoint) and returns the unrestricted reply.
1 MCP server
A /reload-claude-md command that re-reads the in-effect CLAUDE.md memory files from disk and re-anchors the session to their current content, so mid-session edits take effect without a restart. Claude Code loads CLAUDE.md only at session start and has no native reload; this fills that gap. Read-only and user-invoked.
1 command
Brings your Canva designs and comments into AgntUX so you see what needs your attention.
1 skill
DocuSign e-signature workflow in your AgntUX knowledge store.
1 skill
Bring your Dropbox files into your AgntUX knowledge store, and act on them — share, organize, request — right from triage.
1 skill
Personalized, behavior-aware analysis of where your Claude Code (Max/Pro) usage-limit tokens go, with ranked, low-effort ways to use fewer — computed entirely from your local session logs. Python measures; Claude concludes.
1 skill
Automatically link published content (articles, posts) back to project rows in a Notion database.
1 skill
Query a Notion database or page from any script. Reads a token from config; DB/page IDs via env vars.
1 skill
Install and update Legion, wire Codex/Cursor/opencode bridges, verify Pi readiness, manage Hermes's native skill-discovery link, and make Legion the repository-default workflow without replacing existing instructions. Ships `legion-setup`, `legion-init`, and native harness setup commands; daily refresh/self-learning is opt-in.
1 skill
Makes the agent prove an output works before calling it done: scope the check from the user's words, verify on the real surface and environment (never tests, CI, health checks or localhost alone), screenshot it, use it (click, submit, run, open every page), read the evidence critically, and report each item as ✓/✗/?, in a strict tool order (real Chrome, in-app browser, headless Playwright, computer use), with a tool-traps guide, a rationalization table and red flags.
1 skill
Simplified Technical Language for LLM agents: one skill that keeps reports, plans, design documents, and instructions free of invented jargon and easy to read, in any language.
1 skill
Take a tracked issue from wherever it lives — Linear, GitHub Issues, or an in-repo document — through implementation, a pull request, and a self-driving review-and-rectify loop, stopping at a verified ready-to-merge state. It merges only under --merge, and only a clean PR. The reviewer is local, Cursor, OpenCode, or Codex. Use when the user asks to ship, land, or implement an issue end to end, to shepherd or babysit a pull request through review, to keep resolving review comments until a PR is clean, or invokes "/forge" or "/ship-issue". With --hitl, the run splits the work into an approved plan. Each tranche waits uncommitted for the user's review, and the run fixes what they flag before asking to commit. Review findings get the same gate: the user agrees each proposed resolution before any edit, then signs off the fixes before any commit.
1 skill
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
1 skill
GitHub's hosted MCP server (repos, issues, PRs, Actions). Opt-in per machine.
1 MCP server
Interactive HTML Gantt + token/cost report for Claude Code & Codex sessions
1 skill
Plane.so project management workflow for looking up, listing, creating, and updating work items through the Plane REST API.
1 skill
Write a structured handoff document so a fresh agent can resume long-running work without losing context.
1 skill
Google Calendar — create, list, update, delete events
1 skill
Google Drive organizer — audit, triage inbox, split PDF, rename, move
1 skill