Ship better AI in 30 seconds. Browse 2,000+ expert-built and security scanned skills -> Browse skills
THE AGENSI STORE
80 skills found
by Timoranjes
Teaches AI coding agents the discipline of context engineering — designing what information the agent sees, when, and in what format — to dramatically reduce token waste, prevent session amnesia, and
Adversarially audit your agent hooks before you trust them. Catches command injection, secret leakage, over-broad matchers, destructive actions, and blocking-logic mistakes in pre/post-tool-use, prompt, and stop hooks — with a PASS or REVISE verdict and severity-ranked fixes.
Model what your LLM app or agent will cost, find where the money goes, and get a plan to cut it. Per-request and monthly projections, ranked cost drivers, an optimization plan with estimated savings, and unit economics against your pricing — with the arithmetic shown.
Diagnose and fix context-window problems in your agent setup. Inventories everything that loads — memory files, skills, MCP tool definitions, hooks — estimates where the budget goes, maps your symptoms to causes, and prescribes concrete trims, restructures, and session habits, rewriting the files where that's the fix.
Design the right team of specialized AI subagents for your project and get the definition files written properly — precise delegation triggers, focused system prompts, least-privilege tools, and the right model tier for each job. Includes a template, orchestration patterns, and a complete sample team.
Turn a diff into a structured pull request description — what changed and why, guidance on where to review and what's risky, honest testing notes, and migration/rollback notes. Scaled to the size of the change, so review is faster and the merge is safer.
by Timoranjes
Teaches AI coding agents to systematically verify their own work before declaring "done." Implements a structured five-check verification gauntlet (build/test/lint/git-diff/runtime) that the agent run
Review an AI-generated code diff for the failure modes coding agents actually have — claimed-done-but-not-done, gamed or weakened tests, stubs passed off as complete, silent scope creep, hallucinated APIs, and security regressions. Returns an APPROVE or REQUEST CHANGES verdict with a completion check and severity-ranked fixes.
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.
by Timoranjes
Teaches AI coding agents (Claude Code, Cursor, Codex CLI) to perform structured financial research using free APIs and systematic methodology. Covers SEC filing analysis, financial metrics extraction,
by Timoranjes
Teaches AI agents (Claude Code, Cursor, Codex CLI) to set up, dispatch, and coordinate multi-agent workflows using the `claude agents` command. Covers agent role definition, handoff protocols, paralle
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 Coil
A two-minute, top-down read of US market leadership. Pulls Coil's free daily board — S&P 500, Nasdaq-100, and macro regime verdicts with top names. Research, not advice.
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 build and run automated regression tests for SKILL.md files. When you update a skill that your team depends on, you need to know it still works — not just that it "looks ri
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 Timoranjes
Teaches AI coding agents to design safe Prisma schemas that prevent data loss, race conditions, N+1 queries, and the dangerous Prisma migration reset. Covers 12 critical anti-patterns (missing indexes
by Shogun Labs
Systematic framework for engineering AI agent context at the right level of abstraction
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 2005 qzr
An educational psychology-based tutor that teaches university slides step-by-step using learner aspect.
by Erdem Arıt
Turn a niche into 8–12 ranked content topics, each backed by real, dated sources. No guesses, no API keys.
by Timoranjes
Teaches AI coding agents to systematically reduce code complexity by identifying and refactoring high-cognitive-load patterns: deeply nested conditionals, god functions, excessive state mutations, tan
by Timoranjes
Teaches AI coding agents to enforce a strict spec-first workflow: write tests or formal specifications BEFORE implementing any code. Implements a pre-hook that blocks code edits until a test file or s
by Timoranjes
Teaches AI coding agents to generate optimized project rule files (.cursorrules, CLAUDE.md, AGENTS.md) that give agents precise context about a project's architecture, conventions, and workflow. Cover