evaluating-ai-harness-dimensions
Evaluates AI coding agent platforms across five structural dimensions that determine real-world performance independently of model quality, so teams select on architectural fit rather than benchmark scores.
New: Software for Agents, always up-to-date, delivered via MCP or web. Browse
THE AGENSI STORE
121 skills found
Evaluates AI coding agent platforms across five structural dimensions that determine real-world performance independently of model quality, so teams select on architectural fit rather than benchmark scores.
Bypass OS-native file upload dialogs in browser automation using JavaScript interception and DataTransfer injection.
by Perry
Expert guidance for selecting and executing Lean Six Sigma methodologies from DMAIC to DFSS and Hoshin Kanri.
by Aman Garg
AI drafts sound like AI wrote them. This skill learns how you actually write and makes every email, message, and doc sound like you typed it yourself.
by Kevin Cline
Instantly convert Markdown files into polished, self-contained HTML slideshows with dark mode and navigation.
by Kevin Cline
Automated niche research and SEO-optimized listing generation for Etsy sellers using live market data.
by SkillKits
Turn Claude into a senior sales copywriter. 6 frameworks (PAS, AIDA, 4U, BAB, Story Selling). Auto-detects format and tone.
by Aman Garg
Cuts the back-and-forth in half. 12 rules that stop your AI from rushing, guessing, and making you repeat yourself.
by Bidsmarket
Generate long-form, AEO-optimized blog posts with contrarian hooks and humanized PRISM voice.
A bear-market screening engine that ranks stock and crypto breakdowns using institutional distribution and Stage 4 rules.
by Sir Benjamin
A recursive, self-correcting reasoning framework that uses R_polish resonance scoring to solve complex problems.
by Julian
Audit your career and projects using Naval Ravikant’s framework for permissionless wealth and code-based leverage.
by Shandra
Audits AI agent failures and converts recurring mistakes into durable rules, anti-patterns, regression tests, memory candidates, and improved SKILL.md sections.
by Shandra
Audits Kubernetes manifests, Helm values, deployment logs, and service configs to detect configuration errors and produce safe, reviewable fix plans.
An adversarial self-review gate that hunts your agent's weakest claim, overclaims, and missing limitations before a human sees the output.
Turn a CRM export or live HubSpot/Salesforce/Pipedrive sync into an executive-ready pipeline report: a 12-month weighted forecast with three scenarios, win/loss themes pulled from deal notes, data-quality flags, and a board-ready PDF. Can run weekly and email itself to stakeholders.
by LB Creations
Secure, battle-tested patterns for user detection and credential prompting in Jamf and Kandji scripts
Autonomous loop that iteratively modifies, evaluates, and selects the best version of any text resource — skills, prompts, or campaigns — using a modify-measure-keep/discard cycle.
Scan your schemas, seed data, config, and logs for personal data before it leaks. Detects PII-indicating column and key names (email, ssn, phone, address) across SQL, CSV, and JSON, plus PII in the data itself: email addresses, SSN-like numbers, credit-card-like numbers, phone numbers, and PII written into log files. Each finding is flagged with its location and a GDPR-style review note. Heuristic by design: it surfaces what to review, not a compliance guarantee.
Map any repo into an interactive D3 dependency graph plus a Markdown onboarding guide: entry points, module relationships, circular dependencies, and dead-code candidates, with refactor suggestions. Parses TypeScript, Python, Java, Go, and Rust imports, exports, and calls. Self-contained HTML, no source changes.
Instant 20-item printable bundle blueprints with SEO, aesthetics, and design prompts for any holiday or occasion.
Audit your SPF, DKIM, and DMARC records for the misconfigurations that get mail rejected or sent to spam. Flags a missing DMARC record or p=none, missing rua reporting, a missing or duplicated SPF record, SPF over the 10-lookup limit, permissive +all/?all, a missing DKIM selector, and SPF/DKIM domain-alignment mismatches. Paste a DNS zone file or dig/nslookup output.
by Nex AI
Deploy a self-hosted, private RAG system with pgvector, Ollama, and a Telegram interface for your personal notes.
by Nex AI
Hybrid GLB/Procedural character system for Three.js with Draco compression, asset caching, and a selection UI.