Loading...
Loading...
Found 2,052 Skills
Use to write the hook — the opening that earns attention — for any social content: a caption's first line, a video's first three seconds, a carousel cover slide, a thread opener, a YouTube title, or an email subject. Run when the user says "write a hook," "hook for this," "opening line," "first three seconds," "cover slide," "make this scroll-stopping," or when good content keeps getting ignored. Reads brand-profile and voice first so hooks sound like the brand, not viral-bait templates. Hooks must be TRUE to the content that follows — this skill extracts the hook from the post's strongest element and never overpromises. For full captions use caption-writer; for full video scripts use the video skills. This writes the opening itself.
Social media analytics and reporting — read native platform data honestly and turn it into next actions. Use when someone wants to "check my analytics," "see how my posts are doing," "build a social media report," "which content is working," "what metrics/KPIs should I track," or to turn performance data into next steps. Measures goal-mapped SIGNAL metrics (saves, shares, watch time/retention, engagement-rate-by-reach, follower-growth-rate, CTR, conversions) — not vanity (followers/impressions/likes) — and closes the loop. Uses the METER framework. Reads brand-profile + social-strategy (goals) first. WoopSocial has NO analytics surface, so this reads NATIVE platform dashboards (+ GA4/UTM) and interprets numbers the human provides; it NEVER fabricates a metric. Feeds content-recycling, experimentation, competitor-analysis, and every growth skill. Distinct from goals-and-kpis (sets targets) and experimentation (runs tests).
Safely start new or continue in-progress Git integration and history operations through verified completion. Use when asked to run or resume a rebase, merge, cherry-pick, or revert; when Git is already in the middle of one of those operations; or for interruption recovery, conflict resolution, ours/theirs interpretation, and deciding when user guidance is required. Continue a detected active operation before considering new work, never choose the integration method, and never guess an unclear next action or resolution.
Shopee（虾皮）套装优惠 Bundle Deal（与 linkfox-shopee-store-auth 同系列），经 /shopee/developerProxy 转发 Shopee Open API Bundle Deal 模块全部 10 个接口：add_bundle_deal、get_bundle_deal_list、add_bundle_deal_item、update_bundle_deal、end_bundle_deal 等。当用户提到 Shopee 套装优惠、Bundle Deal、组合促销、add_bundle_deal、bundle_deal_id、满件优惠 时触发。即使未明确提及"套装"，只要涉及已授权 Shopee 店铺的 Bundle Deal 活动管理，也应触发。
Take one or many customer-interview files you already have and extract the AJTBD structure from them — segments by Core Jobs, personas, Consideration Set, existing Solutions and Problems, value hypotheses — using Ivan Zamesin's AJTBD / Next Move Theory methodology (distinct from generic Christensen JTBD). Input — a folder or list of files: deep-interview transcripts, interview notes, sales-call or demo transcripts, support/chat logs, survey open-ends. The interviews may be AJTBD or not, well- or poorly-conducted, one file or dozens. The skill first asks which business task you're solving (and helps you choose if you can't name one), then reads each interview in its own subagent (a fan-out so it never overflows context, no matter how many large transcripts), extracts the Core Jobs with an honest per-interview confidence (a clean extraction vs. a weak hypothesis), gives per- interview feedback (what was pulled, what's missing, whether this interview can even serve your business task), clusters the extractions into segments by similar Core Jobs + similar success criteria + similar priority order, and computes each segment's confidence from the supporting interviews' confidence. Output — one report: a data-quality summary, segments by Core Jobs with personas and confidence, structured existing Solutions and Problems, a Consideration Set per segment, value-creation hypotheses, and a gap list of what to interview next. Use when the user says "analyze my interviews", "extract jobs from these transcripts", "I have customer interviews — find the segments", "what jobs are in these calls", "synthesize my interviews", or has interview/transcript files and wants the methodology pulled out of them. The post-fieldwork counterpart to /nmt-interview-guide. Two modes — Quick (default, no internet) and Deep (subagents + web to enrich competitors and the Consideration Set). Plain language; defaults to English.
OpenTelemetry in Java — Javaagent zero-code instrumentation, Spring Boot Starter, manual autoconfigure SDK, declarative YAML configuration, BOM dependency management, sensitive-data capture and redaction (url.query, headers, request parameters, SQL sanitization). Use when adding, reviewing, or configuring OpenTelemetry in a Java service. Triggers on "setup otel in java", "java telemetry", "javaagent", "Spring Boot otel", "GlobalOpenTelemetry", "AutoConfiguredOpenTelemetrySdk", "TracerProvider java", "url.query redaction", "capture request headers", or any Java-related OTel question.
Federal award totals for a recipient name, with award counts and the agencies that paid. Called as POST /v1/gov/federal-spending, it takes recipient, limit and returns results, count. A procurement or diligence agent checking whether a counterparty depends on federal contracts needs the award record, and no model holds it. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.004, paid in USDC on Base over x402.
Diagnose and interpret AE/TE A/B experiments from configuration and report evidence through a defensible decision. Use when the user asks what an experiment means, whether it can roll out, why a result is not significant, why group sizes or exposure are wrong, why treatment results conflict, whether the report is trustworthy, or what to do next. Covers SRM, duration sufficiency, novelty effects, metric conflicts, missing or anomalous data, design reasonableness, data reliability, metric interpretation, trend and segment analysis, root-cause hypotheses, and rollout recommendations. All platform discovery and reads must use ae-cli.
Orchestrates infrastructure cost estimation with tier-based or custom TPS sizing. Offers pre-configured tiers (Starter/Growth/Business/Enterprise) or custom TPS input. Skill discovers components, asks shared/dedicated for EACH, selects environment(s), reads actual Helm chart configs, then dispatches agent for accurate calculations.
Run agentlint CLI after code changes to catch patterns for AI evaluation. Activate when finishing code modifications, before committing, or when the developer asks to lint, scan, or review code with agentlint. Covers agentlint check, agentlint list, agentlint review, agentlint init, inline suppression, and output interpretation.
Distills a person's or company's strengths, experiences, and obsessions down to their one or two VOTERS — the decisive, idiosyncratically extreme traits that win the contest because customers who value them accept every other trade-off. Runs each candidate through a hard gauntlet: extremity earned through obsession (not mere competence), rarity among peers, decisiveness (name the weaknesses it overpowers), and reverberation (it must force decisions in product, pricing, and market). Caps the answer at two, records survivors in VOTERS.md — plus the near-miss 'special strengths' to deploy — and delivers the honest zero-voter verdict when nothing is extreme yet. Takes a self-portrait file (M-numbered), strengths or keystones charts, or a live capture. Load when the user asks what makes them special, what to bet the strategy on, their unfair advantage or superpower, or to 'find our voters.' Do NOT load to build the full self-portrait (the previous step) or to design the whole strategy — this file feeds it.
Guided journey from a live website that underperforms to a prioritized, evidence-backed backlog of conversion, usability, message, and speed fixes - each shipped as a testable experiment. Orchestrates eight skills phase by phase - cro-methodology, ux-heuristics, refactoring-ui, web-typography, storybrand-messaging, high-perf-browser, made-to-stick, design-everyday-things - asking the user questions at every decision point and recording results in the project docs/ folder (WEBSITE.md, DESIGN.md, EXPERIMENTS.md, IMPROVE-WEBSITE-PLAN.md) so the journey resumes across sessions. Use when the user wants to fix a landing page that isn't converting, diagnose why visitors leave, audit for clarity and usability, or says 'the homepage feels off but a redesign didn't help'. Do not use with no site yet - use create-website; if it converts but needs more traffic or leads, grow-website; if the friction is in a product app, not the marketing site, improve-app. For one framework in isolation, invoke that skill directly.