Latest Agent Skills
Everything added to the registry recently, newest first.
- skyf0xx BundleBackfire
Use on an activism goal before an action that could meet force, arrests or a smear, and right after a crackdown, an injury, a ban or a campaign of discrediting. Names the five ways authorities dampen public outrage — cover-up, devaluing the protesters, reframing the event, official channels and intimidation — prepares a counter for each, plans documentation, legal and medical support and nonviolent discipline, and records each expected move and its counter as a risk.
48 - skyf0xx SkillPricing
Use on a business goal when the user must set, raise or rethink a price, choose how to charge (per seat, per use, flat, subscription), or split an offer into tiers — ideally before building, while the answer can still shape what gets built. Runs Madhavan Ramanujam's willingness-to-pay method, then records the price and model as a decision, with a live test where the evidence is thin.
48 - skyf0xx BundleTactics
Use on an activism goal when choosing what to actually do — the next action, an escalation, or a replacement for a weekly march that is shrinking. Picks actions by which pillar they hit, from symbolic protest through non-cooperation to direct intervention, favours dilemma actions that leave the target no good response, weighs concentrated against dispersed actions under the policing expected, and records up to three as courses with the target's likely response and the campaign's answer.
48 - skyf0xx BundlePillars
Use on an activism goal to find where the target's power actually comes from — the groups whose daily cooperation it can't do without (staff, police, suppliers, funders, media, partners, voters) — and which of them the campaign can move. Maps the pillars of support and the spectrum of allies, picks the pillar to work on, and records each pillar as a stakeholder with its stance now and the stance to move it to.
48 - skyf0xx BundleMessage
Use on an activism goal to set the campaign's core message and frame — when the campaign is losing the public story, the press repeats the other side's words ("rioters", "unrealistic", "a minority"), the message only fires up people who already agree, or a new phase or crackdown needs a new frame. Works out who to persuade, builds the message from a shared value, a named cause, the demand and an action, picks the messengers, and records the frame as a decision with a test among persuadable people.
48 - skyf0xx BundleDemands
Use on an activism goal when the campaign has grievances but no winnable demand, a long list of demands, or a target that is an institution or "the government" rather than a person — and again when the other side offers talks, a consultation or a partial concession. Turns a problem into an issue one named decision-maker can grant, tests it as a campaign issue, sets what counts as a win, and records the lead demand as a decision.
48 - skyf0xx SkillIntake
Use for new-goal intake — the active goal is still a stub (its only success criterion is the placeholder "define success criteria") or the user wants to re-open the definition of what they are after. Runs a guided conversation that pins down the goal statement, pressure-tests what "done" means by working backwards, drafts success criteria marked control or influence, sets a deadline, and names the first people involved. Offers a quick take or a deep dive.
48 - skyf0xx SkillElicit
Use at a natural pause, or when the user asks for a deeper critique or names a method (socratic, first principles, pre-mortem, red team), to pressure-test the most recent piece of work — a draft, plan, decision or set of criteria — by running a chosen elicitation method against it. Offers a short menu of methods drawn from a catalog, runs the chosen ones, and hands back an improved version.
48 - skyf0xx SkillStakeholders
Use when the goal depends on people who are neither on your team nor your opponents — councils, regulators, media, landowners, sponsors, rival organisers, the undecided public. Maps who holds power over the outcome, what each actually wants underneath their stated position, and where the movable middle is. Distinct from threat, which models opposition to degrade.
48 - skyf0xx SkillExperiment
Use when the plan rests on an unproven assumption that could be tested cheaply before committing serious effort — will people turn up, will anyone donate, does this message land, will the partner actually deliver. Designs the smallest test that could falsify the assumption, with a pass/fail line set in advance. Writes to the goal's experiments key.
48 - skyf0xx SkillPremortem
Use before committing to a significant plan or an irreversible action. Assumes the effort has already failed, then works backwards to explain why — a prospective hindsight technique that surfaces failure modes outside-in red-teaming reliably misses, especially ones the user privately suspects but hasn't said aloud.
48 - skyf0xx SkillNegotiate
Use before a conversation where you need someone's agreement — a council, a landlord, a sponsor, a platform, a collaborator, a rival organiser. Preps interests on both sides, your walk-away alternative (BATNA), the zone where a deal exists, concessions ranked by cost, and the traps. Two-way, unlike comms, which prepares outward broadcast. Writes each conversation's prep to the goal's prep key, then its outcome once it has happened.
48 - skyf0xx BundleStrategy
Use when the user wants direction on a goal that already exists — starting a work session, asking "what should I focus on", or after a setback, new fact, deadline change, or escalation. Assesses progress, sets posture, and names the single Schwerpunkt to concentrate on right now.
48 - skyf0xx SkillForecast
Use when the plan rests on a belief about what will happen — turnout, a vote, a decision, a response, a timeline. Converts vague expectations into dated, falsifiable predictions with explicit probabilities, then scores them once the outcome is known so the user finds out whether their judgment is actually calibrated. Writes to the goal's forecasts key.
48 - skyf0xx SkillExposure
Use before a public action, a filing, a publication, or anything that puts the user personally on the record — protests, campaigns, public criticism, or organising that touches permits, liability, employment, or personal safety. Maps legal, financial, professional, and personal-safety exposure, and what reduces each. Not legal advice; a checklist for knowing what to check and who to ask.
48 - skyf0xx SkillCapacity
Use when the plan assumes more time, money, or personal energy than actually exists — or periodically on any sustained effort. Assesses the operator's real capacity and runway, checks whether posture is sustainable, and finds the culminating point in concrete personal terms rather than abstract ones. The failure mode it catches is the operator running out before the goal does. Writes to the goal's capacity key.
48 - skyf0xx BundleSystems
Use for a systems-level read before committing to a plan, when the goal or environment has shifted, or when progress feels diffuse. Runs Center of Gravity, PMESII/ASCOPE, Schwerpunkt identification, lines of effort, second/third order effects, and culminating point analysis, feeding results into strategy and plan.
48 - skyf0xx SkillOptions
Use when there is more than one real way to reach the goal and the user has not picked one — before committing to a plan, or when the current approach has stalled. Builds up to three distinct courses of action, each with why it could win, what could sink it and how others would react, then compares them so one can be chosen. Writes to the goal's courses key.
48 - skyf0xx SkillOnboard
Use at the start of any session touching a goal — a vague first message ("I want to...", "help me with...", "help me plan...", "what's going on with this"), or any time it's unclear whether the goal has been defined yet. Not a coding task even if the phrasing sounds like one ("help me plan" here means a life/business/campaign goal, not a software plan). Branches to intake for a new goal, or a welcome-back snapshot for a returning one, then hands off to strategy.
48 - skyf0xx SkillThreat
Use before committing to a plan or significant action, when something external changes, or to stress-test reasoning. Red-teams the plan for adversarial and non-adversarial failure modes, runs adversarial CoG analysis, assesses network exposure if people are involved, and flags interference indicators. Feeds findings to strategy and systems.
48 - skyf0xx SkillSitrep
Use when the user brings several updates at once — "quick catch-up", a list of things that happened, news touching the plan, people, time and money together. Sorts each update to the skill that writes it, shows the routing for a yes, then works through each one in the next turn. Writes only the log itself.
48 - skyf0xx SkillReview
Use after a discrete event, milestone, or push has completed — successful or not. Runs a structured after-action review — what was expected, what happened, why they differed, what transfers to next time — and converts the findings into concrete changes. Distinct from eval, which audits progress against the goal's success criteria rather than learning from a completed action. Appends to the goal's log and folds findings into the plan.nextActions array.
48 - skyf0xx SkillDecide
Use when analysis has produced options and one must be chosen — a fork in the plan, competing focuses, a tradeoff between speed and exposure, or a call the user keeps deferring. Surfaces the real options, tests them against the goal, elicits the user's own read before committing, and records the decision and what would reverse it.
48 - skyf0xx SkillRecon
Use when the plan hangs on something the user does not know yet — a date, a rule, a person's position, a price, whether a door is open. Turns each unknown into a question with a reason, a way to find out and a date to know by, and records the answer when it comes in. Writes to the goal's intel key.
48 - skyf0xx SkillComms
Use when the user needs to draft or sharpen outward communication in service of a goal — a post, pitch, update, or ask to the public or to people on the goal's people list. Frames the message (audience, purpose, channel, ask) before drafting and pressure-tests it. Appends to the goal's log if the communication is a critical-path step.
48 - skyf0xx SkillBrief
Use when the user wants to understand where things stand in plain language rather than in framework terms — returning after a gap, feeling lost, showing the situation to someone else, or asking "so what does all this actually mean". Translates the goal into ordinary prose, explains any jargon it contains, and names the one thing to do next. Also gives a terse quick snapshot for "where are we" or "are we on track". Read-only.
48 - skyf0xx BundlePlan
Use to break a goal or focus into sequenced, dependency-aware lines of operation — a new push, a replan after failure, or a stale plan. Builds each line's critical path and next actions, with escalations and forks linked in. Also the skill for any next action the user reports done, blocked or dropped in passing (its quick status mode).
48 - yangchao228 BundleXiaohongshu Topic Generator
Generate Xiaohongshu-ready topic ideas from a user theme, recent discussion signals, audience pain points, and platform fit. Use when the user asks for 小红书选题, Rednote topic ideas, content angles, post hooks, card-style outlines, or wants to turn a theme into publishable Xiaohongshu topic candidates. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleArticle To Illustrations
Plan, generate, insert, and hand off evidence-safe illustrations for reviewed long-form Markdown articles. Use when a WeChat, Zhihu, blog, or other long-form draft needs an illustration decision, image slots, generation prompts, local image insertion, alt text, an image manifest, or a safe handoff to md-img-r2 before 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 BundleResume Interview Generator
基于候选人简历自动生成面试题、笔试题、追问路径和评分标准的 AI Skill。当用户需要准备技术面试、生成笔试题目、评估候选人简历、或设计面试评估方案时使用。输入简历内容和岗位信息后,自动输出结构化的题目与评估内容,支持面试题模式、笔试题模式、综合评估模式等多种输出形式。 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 Wechat Writer
Draft WeChat-style long-form articles from a confirmed topic, outline, evidence pack, or content_state. Use when the user wants title candidates, hooks, an outline, a complete article body, an ending, structural visual anchors, and follow-up topics before content review and publish packaging. 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 Publish Check
Build and verify platform-specific publish packages for reviewed content. Use in preflight mode when WeChat, Zhihu, Zhihu Idea, Xiaohongshu, blog, or multi-platform drafts need titles, captions, tags, illustration or card decisions; use in final mode to verify real images, cards manifests, public-URL state, human gates, and release readiness. 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 Orchestrator
Orchestrate a reusable content workflow from topic or draft through research, review, platform adaptation, adaptive image generation, recoverable external handoff, long-form illustrations, publish-ready card rendering, image URL preparation, release checks, and knowledge asset capture. Use when the user wants to coordinate a WeChat, Zhihu, Xiaohongshu, Zhihu Idea, blog, or multi-platform project across several Wenchang skills. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleChatgpt Image Handoff
Route a multi-image content job through the best available generation backend, prepare a resumable prompt pack with readable-text fact boundaries, optionally operate an approved ordinary ChatGPT browser session with Computer Use, test an optional multi-image ZIP delivery when the active surface supports it, repair useful generated backgrounds with an allowlist-only mixed overlay, import outputs under stable names, and resume visual QA. Use when built-in ImageGen is unavailable or flaky, Codex may or may not have Computer Use, a user needs a manual ChatGPT fallback, repeated browser round trips should be reduced, exact names or numbers must not be invented, or external image outputs must re-enter a checked local asset pipeline without losing job state. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
- yangchao228 BundleRedbook Cards Skill
将任意文章 HTML 页面或纯文本,自动切片生成小红书风格图文卡片组(封面 + 内容图 + 金句图),输出单个可直接在浏览器预览的 HTML 文件。触发词:小红书、图文卡片、切片、种草图、笔记卡片。
- yangchao228 BundleProject Weekly Report
Generate evidence-based project weekly reports from a local code repository. Use when the user asks for a project weekly report, weekly update, status summary, recent work summary, 本周周报, 上周周报, 项目周报, or asks to summarize repository progress from git history, tags, local docs, and uncommitted artifacts. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228