Reasoning Guard
codexDetect suspicious shallow reasoning turns and add Codex hook guardrails.
1 skill · hooks
Claude Code and Codex plugins their authors filed under "productivity". All categories.
Detect suspicious shallow reasoning turns and add Codex hook guardrails.
1 skill · hooks
Secure, read-only access to the SCG Library from Codex.
1 skill · 1 MCP server
Hallym University reports and forms: select a document family, write Markdown, produce editable HWPX, and reuse personal templates.
2 skills
Cross-multiplexer pane control: open, send, read, focus, and close panes over tmux, herdr, wezterm, and more.
2 skills
Give every pull request a readable description: a short brief, Input to Functions to Output diagrams, and a ranked list of files to review first. Includes a gate that blocks descriptions without them.
1 skill · 1 agent
DidaCLI workflows plus the official Dida365 MCP server
1 skill · 1 MCP server
Plan-anchored drift self-check: shared skill + per-host cadence hook, installable as one unit.
1 skill · hooks
Observation-vs-conjecture discipline: claims carry their evidence and a named falsifier; only verified claims become facts or closures. Shared skill + per-host hooks.
1 skill · hooks
Persist-or-quit signal: counts repeated attempts on the same file, command or error and effort since the user last spoke, and nudges only when a threshold is crossed. Shared skill + per-host hooks. Never blocks.
1 skill · hooks
Turn a Claude project or a folder into a learning harness for one subject. Lesson sessions probe your edge, plan a minimal dependency tree, and teach one checked reasoning step at a time; Practice sessions train retrieval with a hint ladder; Field sessions grade an artifact you produce against a pre-committed rubric. A knowledge graph, an append-only ledger and a frontier record carry it across sessions. Adapted from learnharness.
2 skills
Valendata for AI coding agents: the Valendata MCP server (sign in through the browser) and a skill that teaches the agent to find, clone, run, create and schedule Valendata skills and workflows.
1 skill · 1 MCP server
Pressure-test a product idea before you build it. Produces a Build, Test first, or Do not build decision report.
1 skill
Outside-in TDD in small steps, simple design, clean code, plain and literal domain language.
1 skill
Scans your machine and interviews you to build a portable profile, giving any AI coding agent instant context about who you are.
1 skill
Build and maintain a persistent LLM-powered wiki/knowledge base. Ingest sources, build interlinked pages, query with citations.
1 skill
Search and inspect DexThemes through the canonical remote MCP service.
1 MCP server
Essential answers first, with focused detail on request
1 skill
Watch a video (local path, public URL, or Jira issue key). Downloads with yt-dlp or Atlassian REST, extracts keyframes with ffmpeg, transcribes with local faster-whisper or hosted Groq/OpenAI Whisper, produces a paste-ready report.md.
1 skill
A Claude Code plugin that turns rough ideas into structured prompts. Provides /orbit-prompt for explicit prompt review and silent session diagnostics for 8 inefficiency patterns.
1 skill
从主题或旧稿生成原生可编辑的 4:3 千禧年风格 PPT;L1/L2/L3 三档年代感,并内置事实审校与内容冻结门禁。构建器需要 Python 3.10+、Pillow 与 python-pptx。
1 skill
Compare two insurance quotes for the same insured side by side
1 skill
Create client-ready personal lines insurance proposals from quote packages and advisor preferences
1 skill
QA companion to consolidate-memory: beta-tests the "dream" skill itself. A deterministic invariant oracle + a judgment-lens skill (/dream-beta-test) that finds defects, regressions, and dishonest reports in the consolidation skill — honest by construction (confirmed vs suspected kept separate). Includes a maintainer continuous-QA pre-push gate with a frozen self-test canary + a deterministic orchestrator contract (latest.json) for autonomous release self-heal.
1 skill
Transform scripts into Apple-inspired HTML presentations with animations, color psychology, and lead magnet CTAs
1 skill
Product discovery and requirements analysis specialist. Conducts stakeholder interviews, market research, problem discovery, and creates product briefs.
1 skill
Read the Qur'an while your agent takes its turn. Local-first, offline, no account.
hooks
A personal control plane for managing Codex and Claude Code environments.
1 skill
uwuclxdy's subagent definitions.
hooks
SlackBuzz CLI integration — send messages, DMs, search, reactions, and status from Claude Code
1 skill
Lint an agent's final prose and ask it to rewrite before stopping.
hooks