New: Skill bounties are live. Post a request, fund the bounty, and creators compete for 7 days to build it -> See open bounties
THE AGENSI STORE
48 skills found
A QA lead for AI automations and agent systems — turns a delivery into acceptance criteria, UAT scripts, a non-determinism test plan, a failure-mode matrix, and a client-ready sign-off pack, or audits an existing automation for the gaps that cause silent production failures.
Audit any page, article, or doc for how likely AI answer engines — ChatGPT, Perplexity, Google AI Overviews, Claude — are to surface and cite it. Checks answer-first extractability, question-shaped structure, quotable units, factual specificity, sourcing, schema, and freshness, then returns a PASS/REVISE verdict with the prioritized fixes. This is Answer Engine Optimization, not classic SEO — it optimizes content to be quoted inside AI answers.
Write and review the docs AI agents actually read — AGENTS.md for your repo and llms.txt for your site. Drafts them from scratch or audits existing ones for completeness, clarity, and wasted context, with a PASS or REVISE verdict.
A fast READY or NEEDS WORK check for your README. Catches the make-or-break gaps — missing what-and-why, setup, or a working example — in about 30 seconds.
by Shandra
Creates phased migration plans for moving fragile Zapier, Make, Airtable, or spreadsheet automations into scalable enterprise-grade workflow architectures.
by SkillForge
Turn a messy description of your business into a sharp value proposition — a one-liner, a hero headline, and what makes you different. Free.
by Shandra
Recommends beauty and skincare products based on skin type, goals, budget, preferences, avoided ingredients, current routine, and availability, then builds routines and bundles.
Turn Claude into a court. One brain, a dozen free workers. King makes your agent the orchestrator, not the laborer — it plans the task, delegates the heavy lifting to a fleet of free-tier LLMs, cross-checks their work, and hands you a single verified answer better than any one model could give. You keep the judgment; the free models burn the tokens. Now with a guided first-run wizard that gets you set up in minutes.
Run this on your plan, spec, or prompt before any work starts. It surfaces the decisions you never made, names what an agent would silently assume for each, ranks them by the cost of a wrong guess, and hands back a short list of choices to make now — plus the gaps that are safe to leave open.
Strip AI linguistic tells and monotonous structures to make text and TTS scripts sound written by a real person.
by Timoranjes
Teaches AI coding agents to make minimal, surgical code edits instead of full-file rewrites or over-engineered solutions. Solves the #1 agent frustration: "it rewrote 500 lines when 50 would do." Work
by PromptWagon
Creates clear Gumroad product pages for creators, digital product sellers, template sellers, course creators, prompt sellers, and resource makers, including product titles, descriptions, cover brief, benefits, what’s included, FAQs, update notes, CTA copy, buyer instructions, launch copy, and product page audit recommendations.
by DesignBureau
Stop guessing at bugs. A 4-phase method that makes you find root cause before touching the code. Takes debugging from hours to minutes. Works in any language, with any AI agent.
Automates the research, art prompting, PDF assembly, and metadata generation for Amazon KDP coloring books.
by PromptWagon
Builds weighted comparison matrices for AI tools, model providers, automation platforms, productivity software, SaaS tools, agent platforms, workflow builders, and AI-enabled services, helping consultants, buyers, founders, agencies, procurement teams, and internal decision-makers compare options using clear criteria, scores, trade-offs, risks, assumptions, and recommendation notes.
by Kuan Ee Lau
Turn messy AI automation project evidence into a sign-off verdict, precise blocker chase, and—when ready—a client handoff page.
by OnwireFlow
Makes your coding agent work like a senior developer: exact money, configurable rules, real audit trails, honest testing. Any stack, any country.
by Kuan Ee Lau
Turn redacted n8n, Zapier, Make, webhook, API, or script incident observations into a first-hour evidence register and safe client/engineer handoff before repair or retry decisions.
Make a subagent complete the bounded assignment, preserve shared state, and refuse unsolicited expansion or external authority.
Make an agent give the essential fact, immediate next action, and principal risk before any optional detail.
Make an agent herd wandering work into explicit outcomes, owners, dependencies, boundaries, and the next executable move.
Make an agent notice missing sources, weak attribution, unsupported certainty, and information disorder while correcting calmly.
Make an agent selective, concise, observant, calm, and precise about boundaries without cat puns or fake animal roleplay.
Make an agent inspect neglected material for overlooked value, provenance, reusable components, and unresolved clues without inventing worth.