Autoresearch Optimizer
An iterative agent loop that optimizes any prompt, config, or artifact by making one change at a time, scoring it against a metric, and keeping only the winners.
New: UPI payments are live. Buyers in India can now pay for skills with UPI in INR -> Browse skills
THE AGENSI STORE
3995 skills found
An iterative agent loop that optimizes any prompt, config, or artifact by making one change at a time, scoring it against a metric, and keeping only the winners.
Audit a draft against your own voice spec and flag every line that breaks your house style. Checks banned words and phrases, em-dashes (when your spec bans them), sentences over your word-count cap, off-spec terms that have a preferred replacement, missing contractions, and forbidden clichés. Config-driven by a voice-spec.json you control, with a sensible default spec if you don't supply one.
Your headless Ollama box crashes at 3am and you find out hours later. OllamaWatch pings your Telegram the instant a model dies, the GPU runs out of memory, or the API hangs — with a fix hint in every alert. One Python file, no SaaS, no dashboards.
Generates a single-file, JSON-backed Python task CLI that both humans and orchestrator agents can call, with recurrence and priorities.
Audit paid ads and landing pages as one conversion path for service businesses.
Views but no sales? Get the one ready-to-paste fix for the biggest blocker stopping your first order.
Most 'TDD' skips the failing test. This mentor enforces Red before Green, even on legacy code.
Merge files, URLs, and research into a single coherent document with deduplication and source attribution.
Identify conversion blockers and ad-budget leaks with a severity-ranked landing page audit.
Map supply chains, identify overlooked upstream chokepoints, score candidate quality, audit evidence, and generate research reports.
Produces a scored go/no-go pre-launch audit for a WordPress site across code quality, security, accessibility, and SEO. Use when the user says "is this WordPress site ready to launch", "run a pre-launch QA check", "go/no-go audit for my site", "re-audit after fixes", or "launch readiness scorecard". Do not use when only one domain needs auditing — use that domain-specific WP audit skill instead.
Produces a full-stack SaaS architecture spec — database schema, authentication, REST API design, multi-tenant patterns, billing, deployment plan — for the stack specified. Use when the user says architect my SaaS, design a database schema for this app, set up authentication and billing, or scaffold a SaaS from spec to production. Do not use when the user wants a single automation pipeline instead.
Automated Belgian tax prepayment (VA) memos with scenario modeling and penalty calculations for accountants.
Automation routing (moviepy/ffmpeg), batch processing, audio, effects automation, quality gates.
Build a complete printable savings challenge bundle spec for ANY goal — trackers, challenge sheets, layouts, SEO, 13 tags, and image prompts.
Find the LLM integration code that breaks when a model blocks a response or falls back to a different model. Flags calls with no try/except or refusal branch, responses used or parsed with no guard for a blocked or empty answer, and hardcoded model ids with no fallback handling. Built for the Fable 5 era, where a high-risk call is blocked and silently falls back to Opus 4.8.
Find the model-version coupling that breaks when you swap LLMs. Flags hardcoded model names and versions, deprecated or renamed parameters (the max_tokens to max_completion_tokens class of change), hardcoded token and context-window limits, response-format parsing tied to one model's output, tool-schema format coupling between providers, and hardcoded per-token cost constants. The patterns load from an editable model-rules table you update as new models ship.
Before an agent acts on a plan, verify that the things it named actually exist. Checks each referenced file path, function or method, import or package, environment variable, and CLI command against your repo, and flags the ones that do not resolve. Catches the hallucinated function and the phantom package before the edit, not after the build breaks. Resolves Python and JavaScript/TypeScript.
Catch the Open Graph and Twitter Card problems that make a shared link preview blank or broken. Flags missing og:title, og:image, og:description, og:url, or twitter:card, a relative og:image URL (crawlers need an absolute one), an SVG og:image (no platform renders it), and image dimensions that miss the 1200x630 standard. Reads your HTML or pasted head markup; it does not fetch the page or refresh a platform's cache.
A systematic Local SEO auditor that generates weighted scorecards and prioritized action plans for local businesses.
A production-ready Manifest V3 extension to strip tracking parameters and hidden Unicode from copied text.
Scaffolds a demo-website factory that turns a prospect URL into a branded demo site through a 6-step FastAPI pipeline.