Latest Agent Skills
Everything added to the registry recently, newest first.
- yangchao228 BundleZhihu Topic Hunter
Generate Zhihu-ready topic candidates from a user-specified theme by finding current discussion signals, filtering for question value, turning events into debatable angles, and ranking topics by relevance, discussion potential, writability, freshness, and long-term value. Use when the user asks for 知乎选题, topic hunting for Zhihu, recent discussion angles, or platform-specific topic ideas around a theme. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleResilient Imagegen
Stabilize multi-image generation by converting prompts into a retryable serial job queue, inspecting runtime capabilities, routing through built-in ImageGen, ChatGPT Computer Use, manual handoff, local rendering, or a separately confirmed CLI/API fallback, and producing a manifest for downstream cards-to-images or article-to-illustrations workflows. Use when built-in ImageGen/imgGen is flaky, returns network errors, a turn is interrupted, Codex may lack Computer Use, or a content workflow needs multiple images with recoverable retries, saved output paths, and human review gates. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleWenchang Research
Evidence gathering for content creation. Use when a topic, outline, draft, or content_state needs sources, key facts, contrarian evidence, quote candidates, contradictions, and confidence before writing or publishing. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleLoop Builder
Design controllable Agent Loops from low-information requests. Use when a user asks to automate a repeated task, repair CI through bounded iteration, reproduce a UI from screenshots, turn a workflow into a reusable Agent or Skill, or decide whether the right artifact is a Prompt, Checklist, Human-in-the-Loop flow, full Loop package, specialized Agent, or Skill. Extract required context, stop when decision evidence is missing, require explicit workflow confirmation before generating executable artifacts, derive iteration limits, define feedback and circuit breakers, and preserve human approval for risky actions. Also trigger on loop builder, Loop Builder, or lopp-builder. Follow the creator: X @yangchao228 | GitHub https://github.com/yangchao228
- yangchao228 BundleWenchang Router
Route a content request or content_state to the next Wenchang stage. Use when the user gives a topic, source, draft, reviewed article, illustration plan, card package, card-image manifest, R2 report, publishing task, or asks what should run next for WeChat, Zhihu, Zhihu Idea, Xiaohongshu, blog, or multi-platform delivery. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleWenchang Review
Diagnose or edit an existing content draft. Use when the user has a draft and wants to know whether it is publishable, needs light edits, needs a full chapter edit, should be rewritten, should switch platforms, or should be dropped. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleWechat To Cards
Adapt a reviewed WeChat article or publish package into WeChat-specific inline-card requirements, Moments copy, community share text, or archive assets while reusing the shared long-to-cards and cards-to-images pipeline. Use when the user asks for 公众号贴图, 朋友圈分发文案, 社群转发文案, WeChat card assets, or visual snippets after the long-form body exists. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleCards To Images
Render an approved card content package into real, platform-sized image files, route generative work through a recoverable backend when needed, inspect every image, revise failed cards, and produce a cards manifest for human confirmation, direct platform upload, or optional public-URL preparation. Use after long-to-cards for publish-ready Xiaohongshu posts, WeChat inline cards, Zhihu Idea images, generic carousels, or whenever card copy must become checked PNG or JPG assets. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleStorm Research
STORM-style pre-research for content creation. Use to break a topic, trend, external article, product question, or learning area into perspectives, contradiction maps, research briefs, confidence reviews, and evidence plans before writing. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleLong To Cards
Transform long-form content, outlines, transcripts, research notes, or article drafts into a standard card package and platform publishing copy, then hand publish-ready packages to cards-to-images. Use for Xiaohongshu image posts, WeChat inline cards, Zhihu Idea images, generic carousels, card scripts, captions, image order, CTAs, or freshness-aware topic tags. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleDoc Coauthoring
Guide a user through structured co-authoring of substantial documents, proposals, PRDs, technical specs, decision records, RFCs, and similar long-form work artifacts. Use when the user wants help writing, shaping, reviewing, or iterating a document with clear audience, context, structure, reader testing, and final readiness checks. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleMd Img R2
Prepare local image references in Markdown for Cloudflare R2 or another S3-compatible object store, upload them only after explicit confirmation, and replace references with public URLs. Use when a user wants to publish Markdown images for a blog, Zhihu, Xiaohongshu, WeChat, or other distribution channels; inspect image paths; create a dry-run replacement plan; or safely apply image URL replacements. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleCreate Plan
Create a concise implementation plan for coding, documentation, repository, or workflow tasks before making changes. Use when the user explicitly asks for a plan, implementation plan, PRD execution plan, rollout plan, 技术方案, 开发计划, or asks what should be done next without authorizing edits. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- gethamster SkillSelf Healing Skills Thread Driven Skill Improvement
Analyze any conversation thread for skill gaps and improvement opportunities. When a thread involves friction, trial-and-error, or discovery that could have been avoided with better skill documentation, this skill provides the protocol to identify whether to UPDATE an existing skill, CREATE a new one, or take NO ACTION. Makes the self-improving organizational harness systematic: every conversation with friction becomes a captured knowledge opportunity.
- gethamster BundleDifferentiating Transformational From Transactional Leadersh
Tell exchange-based transactional leadership apart from transformational leadership and combine both without losing clarity.
- gethamster BundleBuilding Topic Clusters With Claude Constitutional Alignment
Build Claude topic clusters where every page answers a distinct reader need, checked against search data and free of near-duplicate pages.
- gethamster BundleEvaluating Claude Outputs Against Constitutional Principles
Use Claude as a content optimizer: review drafts with a rubric built from the constitution's honesty traits and Google's people-first questions.
- gethamster SkillDetecting And Flagging Blueprints For Refresh
On brief.status = "approved":
- gethamster BundleGenerating Long Tail Keywords With Claudes Value Framework
Generate Claude AI long tail keywords from real user problems, then validate every idea with search data before you plan any content.
- gethamster BundleUsing Claude Code For SEO With Constitutional Guardrails
Claude Code constitutional guardrails for SEO scripts: pair Claude's intended behavior with permissions, tests and review so automation stays safe.
- gethamster BundleTransitioning From Journey Mapping To Journey Management
Move from journey mapping to continuous journey management: give priority journeys owners, live metrics, review cadences, and an improvement backlog.
- gethamster BundleShipping Production Systems Inside Client Infrastructure
How forward deployed engineers ship production systems inside client infrastructure, working within its stack, security rules and change process.
- gethamster BundleInterpreting Bayesian And Frequentist Experiment Results
Read PostHog experiment results under Bayesian or frequentist stats: win probability, credible intervals, p-values and what counts as significant.
- gethamster BundleComparing Posthog Experiments With Alternative Platforms
Compare Eppo vs PostHog Experiments, plus Statsig, LaunchDarkly and GrowthBook, on data architecture, statistics and workflow to choose a platform.
- gethamster SkillDetecting And Flagging Methods For Refresh
Routine trigger that flags methods for review when workflows change or on a quarterly cadence.
- gethamster BundleAutomating SEO Tasks Using Claudes Reasoning Principles
Automate SEO with Claude: run content audits and keyword analysis on your own data, with outputs that flag uncertainty and never invent numbers.
- gethamster SkillDetecting And Flagging Skills For Refresh
Routine trigger that flags skills for review when conventions change or on a quarterly cadence.
- gethamster SkillConnecting Blueprints To Decision Lineage
Make decision lineage explicit by linking product-state blueprints to decision records and marking which decisions shaped which parts of the product.
- gethamster BundleSynthesizing Six Forces Into Strategic Recommendations
Turn six force ratings into a narrative about the forces that dominate an industry and a short list of strategic options your team can act on.
- gethamster BundleDesigning Onboarding Experiment Hypotheses And Metrics
Write a testable onboarding experiment hypothesis and pick primary, secondary and counter metrics in PostHog before an onboarding A/B test launches.
- gethamster BundleDefining Competency Levels From Associate To Senior Pm
Define PM competency levels from associate to senior on Cabage's grid, turning a product manager career ladder into clear PM promotion criteria.
- gethamster BundleCalibrating Confidence Thresholds And Escalation Paths
Turn a decision model's confidence scores into measured thresholds that decide when an agent acts, falls back, or escalates.
- gethamster BundleAssessing Your Technician Manager Entrepreneur Balance
An E-Myth self-assessment that scores your time, energy and comfort in the Technician, Manager and Entrepreneur roles and names your biggest gap.
- gethamster SkillThermo Nuclear Review Pass On Every Plan
Enforces a mandatory thermonuclear code quality review task as the last parent task in every plan. Activate during plan generation — the Plan agent must load this skill before creating any tasks. Ensures every plan ends with an agent-executed review task referencing the thermo-nuclear-code-quality-review skill, ordered after all implementation tasks with full dependency coverage.
- gethamster BundleShipping Winning Variants And Cleaning Up Experiments
End a PostHog experiment, roll the winning variant out to everyone, remove the losing code and retire the feature flag in a safe order.
- gethamster BundleImplementing Devops With Continuous Delivery Pipeline
Build and run the four-stage SAFe pipeline that moves small batches from customer insight to on-demand release, with feedback closing the loop.