mid session context recovery
by Timoranjes
Teaches AI coding agents to self-detect context rot (regression loops, instruction drift, hallucination drift, lost-in-the-middle) during long sessions and execute a structured checkpoint/recovery pro
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
509 skills found
by Timoranjes
Teaches AI coding agents to self-detect context rot (regression loops, instruction drift, hallucination drift, lost-in-the-middle) during long sessions and execute a structured checkpoint/recovery pro
by Timoranjes
Teaches AI coding agents to audit their own CLAUDE.md, cursor rules, and project config files for structural flaws that cause rule non-compliance. Diagnoses WHY agents ignore rules (ambiguity, contrad
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
Convert raw requirements into INVEST-compliant user stories and Gherkin acceptance criteria. Part of the Gnosis Technology Product Suite
by John Barros
Evaluate and plan the migration of vision inference pipelines to native OpenCV 5 DNN CPU execution.
by Shogun Labs
Systematic framework for engineering AI agent context at the right level of abstraction
by PromptWagon
Creates structured safety cases, risk arguments, controls evidence, assumptions, limitations, assurance claims, decision logs, review questions, and sign-off packs for AI-enabled products, systems, workflows, and features. Helps teams turn AI governance expectations into practical documentation rather than abstract policy language.
Migrate your Shopify app off the legacy REST Admin API — full-codebase scan, phased cutover plan, client-ready migration report.
Model quality is table stakes — the harness is where agents win or fail. This designs yours: it writes a structured, testable system prompt (role, tools, boundaries, method, output contract, failure handling) and maps every concern to the right layer — prompt, tool, guardrail, or evaluation — so the pieces reinforce each other instead of fighting.
by Matthew King
Punchy, honest, useful articles that read human, not AI, in a voice you will be proud to publish.
by Aiepco
Write deep, well-researched long-form content for Zhihu, Toutiao, blogs, Twitter Threads, and Facebook using the six-arc structure with Phase 0 knowledge reconnaissance.
Strips the AI fingerprint from prose by enforcing human-like rhythm, asymmetry, and concrete word choice.
by Timoranjes
Teaches AI coding agents to detect when they're stuck in a repeating action loop (same file edit, same tool call, same error pattern) and break out before burning tokens. Uses a three-layer detection
by acarchidi
DeFi safety layer for agents providing rug checks, transaction decoding, and contract audits on EVM and Solana.
Automates the research, art prompting, PDF assembly, and metadata generation for Amazon KDP coloring books.
by Shandra
Creates market-ready editable invitation template product specifications for birthdays, baby showers, bridal showers, graduations, weddings, holiday parties, and themed celebrations.
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.
by Romeo Apps
Secure local password broker for AI agents with human-in-the-loop GUI and encrypted storage.
by OnwireFlow
A senior Tauri 2 + Rust desktop engineer for your agent, AI inspect, verify, secure the IPC, test honestly, ship.
by Timoranjes
Teaches AI coding agents to perform structured, high-signal code reviews specifically for AI-generated code — catching the failure modes unique to LLM output (confident hallucinations, silent error sw
by PromptWagon
Creates LinkedIn thought leadership systems for consultants, founders, professionals, coaches, experts, and service providers, including profile positioning, authority angles, content pillars, recurring post series, post ideas, credibility themes, founder viewpoints, service/product CTAs, newsletter links, lead magnet connections, and consistency plans.
by PromptWagon
Turns multiple digital products into themed creator shop bundles with bundle concepts, product grouping, pricing tiers, bundle names, descriptions, launch messaging, offer positioning, what’s-included sections, preview guidance, README notes, licence reminders, upsell ideas, and publishing checklists.
by PromptWagon
Creates high-CTR thumbnail briefs for digital products, prompt packs, AI image bundles, templates, printables, courses, and creator products, including layout direction, title hierarchy, safe-zone placement, colour theme, visual concept, typography mood, preview-image guidance, and thumbnail audit recommendations.
by Ivan Fodjo
Deterministic tiered governance and human-in-the-loop guardrails for AI agent write-actions.