tomwangowa/agent-skills

2Stars on the repository
45Mods indexed here, across every type
7d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

ai-weekly-insight

01

tomwangowa/agent-skills

Skill Claude CodeCodex

A reporting workflow for analysing AI news for the TrendLife AI Taskforce. It produces daily, weekly, or monthly reports prepared for sharing with others.

not rated 2 7d ago A 65 tokens

arxiv-digest

02

tomwangowa/agent-skills

Skill Claude CodeCodex

A research assistant for finding and explaining AI papers on arXiv, an online repository where researchers share scientific papers. It produces detailed summaries intended for engineers and AI taskforce meetings.

not rated 2 7d ago A 86 tokens

tomwangowa/agent-skills

Skill Claude CodeCodex

Systematically extract explicit and implicit assumptions from technical documents, design plans, or feasibility assessments. Classifies each assumption by visibility (explicit/implicit), verification status (verified/unverified/falsified), recommended verification method, and risk impact. Use when reviewing any…

not rated 2 7d ago A 75 tokens

brainstorming

04

tomwangowa/agent-skills

Skill Claude CodeCodex

Use when Codex needs to turn a vague idea into an approved design before implementation, or when a user wants to grill / stress-test a plan or idea (triggers: grill, 烤, stress-test). Apply to new features, architecture changes, refactoring, and workflow design. Interview one decision at a time with a recommendation…

not rated 2 7d ago A 84 tokens

tomwangowa/agent-skills

Skill Claude CodeCodex

Use this skill when the user is designing a Claude Code workflow, choosing between mechanisms (hook/skill/subagent/MCP/CLAUDE.md), or packaging automation for team distribution. Also triggered by the /sos slash command.

not rated 2 7d ago A 54 tokens

code-review-claude

06

tomwangowa/agent-skills

Skill Claude CodeCodex

Use when Claude Code receives a code-review request, 'review', 'code review', 'quick review', 'native review', or a fast code check. Runs native (< 30 s) line-by-line analysis with adversarial pass, assumptions list, syntax-checker-verified syntax findings, and an optional ready-to-apply Refactored Patch. In Codex…

not rated 2 7d ago A 88 tokens

code-review-codex

07

tomwangowa/agent-skills

Skill Claude CodeCodex

A structured local code-review workflow for Codex, the coding agent, that checks changes before they are committed.

not rated 2 7d ago A 112 tokens

code-review-gemini

08

tomwangowa/agent-skills

Skill Claude CodeCodex

Use when a legacy Gemini review invocation needs a migration response. Explain the retirement; do not invoke Gemini or send code externally. Route generic review to code-review-claude in Claude Code or code-review-codex in Codex.

not rated 2 7d ago A 53 tokens

code-story-teller

09

tomwangowa/agent-skills

Skill Claude CodeCodex

Analyze git history to tell the story of how code evolved. Use this Skill when the user asks to understand code history, explain evolution, show file timeline, or understand design decisions behind code.

not rated 2 7d ago A 43 tokens

codebase-audit

10

tomwangowa/agent-skills

Skill Claude CodeCodex

Claims-first codebase audit that extracts documentation claims and verifies them against code. Use when asked to "audit", "verify docs match code", "check if README claims are true", or "validate documentation accuracy". Falsification-first approach.

not rated 2 7d ago A 53 tokens

completion-gate

11

tomwangowa/agent-skills

Skill Claude CodeCodex

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.

not rated 2 7d ago B 42 tokens

critical-research

12

tomwangowa/agent-skills

Skill Claude CodeCodex

Falsification-first research skill that actively seeks counter-evidence before supporting evidence to eliminate cognitive biases and ensure rigorous, objective conclusions.

not rated 2 7d ago A 30 tokens

deai-voice-rewrite

13

tomwangowa/agent-skills

Skill Claude CodeCodex

A writing aid for rewriting your own public content in plainer language and in your personal voice. It is intended for presentations, blog posts, newsletters, social posts, and sharing slides.

not rated 2 7d ago A 0 tokens

deep-reading

14

tomwangowa/agent-skills

Skill Claude CodeCodex

Systematic knowledge extraction from document sets. Identifies core mental models, expert disagreements, knowledge gaps, and teachable frameworks. Use when given documents/URLs/notes to deeply understand, not just summarize. Triggered by "deep read", "help me understand this", "extract insights", "what are the key…

not rated 2 7d ago A 79 tokens

git-status-tui

15

tomwangowa/agent-skills

Skill Claude CodeCodex

A visual panel that summarizes the current state of a Git repository, including its branch, changes, stashes, and ongoing operations.

not rated 2 7d ago A 116 tokens

handoff

16

tomwangowa/agent-skills

Skill Claude CodeCodex

A session handoff document for recording unfinished work, current state, assumptions, risks, and the next step in a Git repository.

not rated 2 7d ago A 145 tokens

tomwangowa/agent-skills

Skill Claude CodeCodex

Generate interactive presentation from an outline or brief. Creates markdown-based presentations (Marp/Slidev/reveal.js) or standalone HTML presentations. Use when user asks to create slides, make a presentation, or generate a deck from an outline.

not rated 2 7d ago A 53 tokens

md-translate

18

tomwangowa/agent-skills

Skill Claude CodeCodex

Translate markdown files to English and Traditional Chinese. Automatically detects source language and generates both -en.md and -zh.md versions. Preserves markdown formatting, code blocks, frontmatter, and links.

not rated 2 7d ago A 43 tokens

micro-poc-validator

19

tomwangowa/agent-skills

Skill Claude CodeCodex

Empirically validate technical assumptions through minimal code experiments (5-30 min spikes). Use when a tech-feasibility assessment or design document contains claims that can be proven or disproven by running actual code. Triggered by "validate this assumption", "can X actually do Y?", "prove it with code", or…

not rated 2 7d ago A 74 tokens

narrative-auditor

20

tomwangowa/agent-skills

Skill Claude CodeCodex

Audit external narratives (articles, posts, marketing copy) against primary sources, or speak on behalf of the user as their AI proxy. Use when asked to "fact-check", "verify this article", "audit this claim", "help me respond", "speak for me", or "supplement context".

not rated 2 7d ago A 69 tokens

newsletter-digest

21

tomwangowa/agent-skills

Skill Claude CodeCodex

Use when user asks to organize newsletters, digest emails, summarize subscriptions, or mentions .eml files, newsletter folder, or email digest. Reads all .eml files from a folder, groups by topic, and produces a structured digest.

not rated 2 7d ago A 52 tokens

pptx-to-md

22

tomwangowa/agent-skills

Skill Claude CodeCodex

Convert PPTX (PowerPoint) or other Office documents (DOCX, XLSX, PDF) to Markdown using the markitdown library. Use when the user wants to extract text content from a presentation or document into Markdown format, convert slides to readable notes, or batch-convert a folder of Office files. Triggers on requests like…

not rated 2 7d ago A 101 tokens

pr-review-assistant

23

tomwangowa/agent-skills

Skill Claude CodeCodex

Use when the user asks to review a pull request, analyze PR changes, check code quality in a PR, or provide structured PR feedback.

not rated 2 7d ago A 33 tokens

tomwangowa/agent-skills

Skill Claude CodeCodex

Use before creating presentations — transforms a topic or rough outline into a complete Slide Plan with narrative strategy, audience analysis, and per-slide detail. Auto-chains to interactive-presentation-generator for production.

not rated 2 7d ago A 43 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: