allanbian1017

@allanbian1017 source repo

37 skills
0 followers
6 hours ago last updated

▌
Rca · allanbian1017
Structured, evidence-backed Root Cause Analysis for workflow quality issues. Enforces quantitative hypothesis testing before naming a root cause. Use whenever a workflow produces unexpected, degraded, or inconsistent output.

0
installs
▌
Yt2doc · allanbian1017 bundle
Transcribe and organize a YouTube video into a structured Markdown document using the local yt2doc CLI tool. Use this skill whenever the user provides a YouTube URL and asks to transcribe, summarize, organize, extract content from, or document a video. Triggers include phrases like "transcribe this video", "get the content of this YouTube video", "convert YouTube to text", "organize this video", "extract transcript from YouTube", "turn this video into a document", or any request involving a youtube.com or youtu.be URL where the goal is to get readable content from the video. Always prefer this skill over manual browser-based approaches when a YouTube URL is provided.

0
installs
▌
Insight · allanbian1017
Analyzes the current Antigravity conversation history to suggest workflow improvements, feature adoption, and AGENTS.md updates.

0
installs
▌
Write Prd · allanbian1017
Product Manager-mode requirement review that interactively drafts and iterates on product requirements with user approval.

0
installs
▌
Grill Me · allanbian1017 bundle
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Learns user preferences and rationale over time to calibrate future recommendations. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

0
installs
▌
Git Master · allanbian1017
MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.

0
installs
▌
Rubric Grader · allanbian1017 bundle
Score AI-generated suggestions against a 3-dimension rubric, check hard-vetos, and route to pending or filtered backlog. Run backtest accuracy analyses, and interactively maintain the blocklist and calibration metrics.

0
installs
▌
Review Work · allanbian1017
Reviews uncommitted code changes using a dynamic pipeline that scales from a single reviewer to parallel specialized reviewers (Bug Hunter, Rules Auditor) based on diff size.

0
installs
▌
Flow Tracer · allanbian1017 bundle
Trace an endpoint or function's complete code flow through the codebase and produce a structured documentation artifact with Mermaid sequence diagrams, infrastructure details (Redis keys, queues, DB tables), and abstract step-by-step flow descriptions. Use this skill whenever the user asks to "trace a flow", "document an endpoint", "show me the code flow for X", "how does X work end to end", "what happens when X is called", "map out the flow of X", "trace the call chain of X", or any request to understand, visualize, or document how a specific endpoint, handler, function, or feature flows through the codebase — even if they don't explicitly say "trace" or "flow".

0
installs
▌
Daily Workflow · allanbian1017 bundle
Chains the full content intelligence pipeline in optimal order: discover Delegate tasks, dispatch all content items as parallel full-lifecycle subagents, collect results, merge suggestions, run daily distillation, review suggestions. Use when the user says 'run my daily workflow', 'run daily', 'start my daily routine', or any request to run all content processing tasks in sequence.

0
installs
▌
Ingest Threads · allanbian1017 bundle
Fetch a Threads post and produce a summary report in the configured output language (defaulting to English), then mark the Google Task as completed. Use when the user provides a Threads URL to process, says 'process this Threads post', or when invoked by daily-workflow for tasks in the Delegate list.

0
installs
▌
Ingest Website · allanbian1017 bundle
Fetch a generic website URL and produce a summary report in the configured output language (defaulting to English) using the Jina Reader API, then mark the Google Task as completed. Use when the user provides a website URL to process, says 'ingest this article', 'summarize this page', 'process this website', or when invoked by daily-workflow for tasks in the Delegate list that are not Threads or YouTube URLs. Triggers include any http/https URL that is not threads.net, threads.com, youtube.com, or youtu.be.

0
installs
▌
Ingest Youtube · allanbian1017 bundle
Transcribe a YouTube video using yt2doc CLI and produce a summary report in the configured output language (defaulting to English), then mark the Google Task as completed. Use when the user provides a YouTube URL to transcribe, says 'transcribe this YouTube video', 'get the content of this YouTube video', or any request involving a youtube.com or youtu.be URL where the goal is readable content. Always prefer this skill over manual browser-based approaches.

0
installs
▌
Memory Engine · allanbian1017 bundle
A memory management and learning system for Antigravity. Use this skill whenever the user issues a memory command like save, reload, handoff, reflect, todo, learn, or any other memory-related commands. This skill enables the agent to store context across sessions, maintain a reflection diary, track cross-project tasks, and learn from mistakes.

0
installs
▌
Content Cleaner · allanbian1017 bundle
Extracts pure article text from a raw text file, HTML dump, or URL. Use this skill whenever the user asks to clean up content, remove ads/navigation from text, or extract the main article from a noisy source.

0
installs
▌
Content Summary · allanbian1017 bundle
Shared content summarisation and AI analysis pipeline. Provides reusable references for thesis-driven analysis quality rules, AI analysis with user-preference calibration, and suggestion logging. Referenced by ingest skills (ingest-newsletter, ingest-threads, ingest-youtube, ingest-website). Do not invoke this skill directly.

0
installs
▌
Daily Distiller · allanbian1017 bundle
Reviews today's reports in ./reports/ and generates a synthesized Knowledge Distillation document in reports/distillations/. Use this skill whenever the user asks to "summarize today's reports", "distill today's knowledge", "run daily distillation", or "update the knowledge distillation document". It ensures technical insights about AI Agents and Context Engineering are preserved and systematized.

0
installs
▌
Web To Markdown · allanbian1017 bundle
Converts any website URL into a clean Markdown file using the Jina Reader API. Use this skill whenever the user wants to convert a webpage to Markdown, save a website as Markdown, parse a URL into readable text, or extract content from a web page as Markdown. Triggers include 'convert this page to markdown', 'save this URL as markdown', 'parse this website', 'get markdown from URL', 'web to markdown', or any request to turn a web resource into a Markdown file. Prefer this skill over manual browser scraping when the goal is a Markdown file from a URL.

0
installs
▌
Evolution Log · allanbian1017 bundle
Generate, update, or audit an Evolution Log — a narrative document that tells the development history of a project through iterative problem-solving cycles (Problem → Options → Decision → Result → New Problem). Use this skill whenever the user says 'update my evolution log', 'generate evolution log', 'audit my evolution log', 'verify evolution log', 'check evolution log for missing files or commits', 'clean up evolution log', 'write the project history', 'document the development journey', 'update EvolutionLog', 'add recent changes to evolution log', 'chronicle the project evolution', or any request to create, maintain, or verify a narrative development history from git commits, RFCs, RCAs, ADRs, or other decision documents.

0
installs
▌
Implement Task · allanbian1017 bundle
Start the Autonomous AI Developer Pipeline sequence with a planned feature. Use this skill whenever the user types `/implement_task <feature_name>` or asks to implement a planned task end-to-end — picking the next pending task from the task list, writing tests, implementing code, running CI, and running a full code review loop until the PR is approved and merged. Trigger this skill for any request to execute a task that already has a plan and tasks list in place using the established agent pipeline.

0
installs
▌
Decision Sparring · allanbian1017 bundle
Stress-test decisions, break analysis paralysis, and overcome procrastination using 9 structured mental models (Bottleneck Analysis, Inverting the Question, New Information Test, Time-Value, Regret Minimization, Hell Yeah or No, Optionality, Documentary vs Horror, Future-Me). Trigger whenever the user says 'help me decide', 'stress-test my decision', 'I'm procrastinating on', 'I can't decide between X and Y', 'break my analysis paralysis', 'decision sparring', '9 mental models', '幫我決策', '猶豫不決', or asks for a structured decision audit.

0
installs
▌
Ingest Newsletter · allanbian1017 bundle
抓取未讀電子報並產出 Markdown 摘要報表（On-Demand Newsletter Summary）。使用 gws-gmail 技能讀取所有標記為 `label:newsletter is:unread` 的未讀信件，以批次方式逐封分析並依設定之輸出語言（預設為英文）產出 Markdown 摘要，儲存至 `./reports/Newsletter_YYYY_MM_DD/` 目錄，最後將信件標記為已讀並封存。當使用者說「幫我整理電子報」、「摘要電子報」、「處理未讀電子報」、「newsletter summary」、「讀取電子報」、「newsletter 摘要」，或任何需要從 Gmail 擷取並摘要電子報的情境，請務必使用此技能。

0
installs
▌
Study Github Repo · allanbian1017 bundle
Analyze a GitHub repository and generate a comprehensive study report covering architecture, design decisions, code quality, and repo health. Use this skill whenever the user provides a GitHub repo URL and wants to understand it deeply, says 'study this repo', 'analyze this GitHub project', 'what does this repo do', 'how is this repo designed', or any request to understand a GitHub repository's architecture, codebase, or engineering quality. Also use when the user wants a repo breakdown, code review, or architecture analysis of a GitHub project.

0
installs
▌
Request Feature · allanbian1017 bundle
Start the Autonomous AI Plan Pipeline sequence with a new idea. Use this skill whenever the user types `/request_feature <idea>` or asks to kick off a full feature development pipeline — from requirements writing through PRD, RFC design review, and task breakdown planning. This skill focuses EXCLUSIVELY on feature planning and MUST NOT perform any code implementation or modifications to source files beyond documentation. Trigger this skill for any request to take a feature idea through the full autonomous planning lifecycle using the established agent pipeline.

0
installs
▌
Fetch Threads Post · allanbian1017 bundle
Fetch all content from a Threads (threads.net / threads.com) post URL using agent-browser. Use when the user provides a Threads post URL and wants to extract the full post text, author info, media URLs, engagement metrics, and reply thread. Triggers: 'fetch this Threads post', 'scrape Threads', 'get content from Threads URL', 'extract Threads post', or any request involving a threads.net/threads.com post link.

0
installs
▌
Review Suggestions · allanbian1017 bundle
Review pending AI suggestions from processed reports. Presents unreviewed suggestions as an artifact, collects Accept/Reject feedback, and updates the user preference profile. Use when the user says 'review my suggestions', '幫我看建議', 'check my suggestions', 'review AI suggestions', or any request to review AI analysis recommendations.

0
installs
▌
Newsletter Summary · allanbian1017 bundle
抓取未讀電子報並產出 Markdown 摘要報表（On-Demand Newsletter Summary）。使用 gws-gmail 技能讀取所有標記為 `label:newsletter is:unread` 的未讀信件，以批次方式逐封分析並產出繁體中文 Markdown 摘要，儲存至 `./reports/Newsletter_YYYY_MM_DD/` 目錄，最後將信件標記為已讀並封存。當使用者說「幫我整理電子報」、「摘要電子報」、「處理未讀電子報」、「newsletter summary」、「讀取電子報」、「newsletter 摘要」，或任何需要從 Gmail 擷取並摘要電子報的情境，請務必使用此技能。

0
installs
▌
Investigate Issue · allanbian1017 bundle
Orchestrates the full issue resolution lifecycle: triage, root cause investigation, internal RCA review, human-approved RCA, TDD-driven fix, code review, and merge. Use when the user types `/investigate_issue <issue>` or asks to debug, investigate, or fix a reported bug end-to-end.

0
installs
▌
Devcontainer Bridge · allanbian1017
Execute CLI commands and technical workflows inside a project's dev-container, ensuring environment consistency with project-defined dependencies and tool versions. Use this skill whenever the workspace has a .devcontainer/ directory and the task requires running shell commands, build tools, test suites, or any CLI tools. Trigger even if the user doesn't say "container" — if they ask to run tests, execute a workflow, or use a project-specific CLI and a .devcontainer exists, bridge into the container first. This prevents "works on my machine" issues and ensures the right runtime versions are always used.

0
installs
▌
Tech Deconstructor · allanbian1017 bundle
Deconstruct any research paper, technical proposal, system architecture, or engineering concept into a structured 4-part analytical breakdown: Problem & Motivation, Candidate Options & Tradeoffs, Chosen Solution & Rationale, and Empirical Results. Trigger whenever the user asks to 'deconstruct this paper', 'analyze this technical concept like CodeNib', 'deep dive into [paper/RFC/architecture]', 'break down this technical proposal', or requests a structured 4-part breakdown (problem, options, solution, results) of a technical innovation.

0
installs
▌
Process Delegate Tasks · allanbian1017 bundle
Automatically process URL-based tasks from the Google Tasks 'Delegate' list. Supports Threads posts (threads.net / threads.com) and YouTube videos (youtube.com / youtu.be). Fetches content, generates a Traditional Chinese summary with verbatim raw content appended, saves a Markdown report, and marks the task as completed. Use this skill whenever the user says 'process my Delegate tasks', 'run my delegate workflow', 'summarize my task list', 'check my task list', or any request involving clearing the Delegate list — even if Threads or YouTube are not explicitly mentioned.

0
installs
▌
Incremental Implement · allanbian1017
Full PR lifecycle via isolated worktree, atomic commits, PR creation, and a strict verification loop (CI + review-work) until merged.

0
installs
▌
Agent Rules Reviewer · allanbian1017 bundle
Audit, streamline, and refactor agent steering documents (AGENTS.md, CLAUDE.md, .cursorrules). Eliminates redundancies, base-model knowledge bloat, and system prompt conflicts; applies Addy Osmani's 3-Tier Agent Rules Architecture (Always Do, Ask First, Never Do) and Attention Budget Governance to cut rule drift and minimize token consumption. Use whenever the user asks to "review AGENTS.md", "audit AGENTS.md", "clean up AGENTS.md", "refactor AGENTS.md", "apply 3-tier rules", "audit CLAUDE.md", "optimize agent rules", "review my agent instructions", or mentions "attention budget governance for rules".

0
installs
▌
Test Driven Development · allanbian1017
Drives development by enforcing a strict Red-Green-Refactor pipeline for features and a Prove-It pattern for bug fixes, completely language and framework agnostic.

0
installs
▌
Skill Context Refactor · allanbian1017 bundle
Refactor and optimize Agent Skills using modern Context Engineering principles. Removes 50%+ bloated micro-rules (Unhobbling), converts ad-hoc examples into explicit JSON/YAML schemas and Enums (Design Interfaces), and restructures SKILL.md into a Lean Spine (<200 lines) with on-demand references (Progressive Disclosure). Use this skill whenever asked to "refactor skill", "unhobble skill", "optimize skill context", "clean up skill instructions", "apply context engineering to skill", or when an agent skill is bloated, overly rigid, or hard to maintain.

0
installs
▌
Planning And Task Breakdown · allanbian1017
Decomposes specifications into structured, ordered, and verifiable tasks using vertical slicing and dependency mapping.

0
installs
▌
Review Newsletter Subscriptions · allanbian1017 bundle
Audit and evaluate newsletter subscriptions based on past 30 days of ingestion reports and suggestion review history. Analyzes newsletter frequency, suggestion conversion rates (accepted vs. rejected), and rubric blocklist vetoes to propose evidence-backed recommendations: Keep, Unsubscribe, or Adjust/Filter. Use whenever the user asks to 'review my newsletter subscriptions', 'audit newsletters', 'which newsletters should I unsubscribe', 'analyze newsletter subscriptions', 'evaluate newsletter value', '檢查電子報訂閱', '該取消訂閱哪些電子報', '分析電子報', or asks for advice on newsletter subscriptions.

0
installs

37 published skills