@affaan-m
Compute Trading Lead @ Jump Trading | prev. founded The Agentic Desk for Compute @Ito-Markets (acq.) | built ECC @ECC-Tools (272k+ stars)
325 skills1 repository 285K
Check skills before distributing them to Codex or Cursor. Identify unsupported metadata fields, Claude-specific variables in shell examples, and inconsistencies between source skills and their installation copies using the project's compatibility checker.
Organize feature development using files in the repository. Break larger goals into user stories, assign them to sprints, guide implementation and review, and track progress through confirmed merges without an external project management tool.
Inventory existing tests and identify gaps. Link requirements, business rules, risks, and bugs to stable test identifiers and executable evidence, maintaining a test registry that shows what is covered and what still needs verification.
Track module dependencies and verification commands in REGRESSION.md. After a change, check the affected module and downstream consumers, then report command exit codes as evidence that existing behavior still works or needs attention.
Maintain clear business definitions and relationships in an existing glossary or CONTEXT.md. Flag unresolved meanings and refer lasting design choices to the existing architecture decision record workflow, keeping terminology separate from decision rationale and task status.
Set up Everything Claude Code skills and hooks in DeepSeek Harness. Covers linking skill folders, generating hook settings, checking that hooks run, updating the setup, and investigating missing skills or inactive hooks.
Map the impact of a proposed change using real dependencies and project documentation. Identify affected code, data, interfaces, tests, and release steps, then compare the implemented changes with the plan to expose gaps and unverified risks.
Audit a focused part of an existing codebase, reconstruct its behavior and past decisions, and record gaps in reasoning, coding practices, features, and technology choices. Use the findings to plan, test, implement, and verify improvements.
Check the full connection between a local agent API and a remote sandbox through a temporary tunnel. Run a task that needs no connected tools, verify its response, and restore the web app’s original API connection.
Create an SVG usage card from local Claude Code, Codex, Gemini CLI, and OpenCode logs. It summarizes token counts, equivalent API cost, consecutive activity days, and each agent's share for inclusion in a README or documentation.
Restructure repeated LLM API requests so shared instructions and reference material can be cached, meaning reused across calls. Track cached input, write and storage costs, and response times to assess whether the changes actually save money.
Investigate photos, videos, public accounts, and records using OSINT, research based on public information. Connect sparse clues, test competing explanations, and report evidence, confidence, and unresolved questions about locations, events, identities, or infrastructure relationships.
Design and review Java database code using MyBatis and MyBatis-Spring. Covers mapping query results to objects, safe SQL parameters, transactions, pagination, batch writes, and investigating slow or unnecessarily repeated queries.
Review MCP configuration without running its servers. Identify npm, Python, and Docker references that may fetch different code later, classify their version settings, and recommend pinning versions or image contents that the team has reviewed.
Turn Git changes into a clear commit message using Conventional Commits, a format that labels the change type and optional scope. Review repository history to match its conventions, and flag unrelated changes that should be split.
Route broad requests about project documentation to a suitable specialist skill. When requested, run a read-only audit of document roles, local links, architecture decision indexes, and evidence references, reporting failures and items needing review.
Build Bengali search and AI features with guidance on consistent character encoding, word splitting, digit conversion, and safe text display. Includes patterns for cleaning training data, storing text, and handling Bengali alongside English.
Plan and verify security controls for AI agents that read untrusted content and use tools. Review permissions, file boundaries, network destinations, and credentials, then test that rejected actions leave no unintended changes.
Prepare web applications for production with Docker configurations, automated testing and deployment workflows, health checks, and rollback plans. Compare release strategies and review application, infrastructure, monitoring, security, and operational readiness before launch.
Structure server-side applications with practical patterns for Node.js, Express, and Next.js API routes. Covers API design, database queries, caching, authentication, error handling, and background jobs, with examples that separate business rules from data access.
Extract reusable solutions and project conventions from completed Claude Code sessions and save them as learned skills. This deprecated version documents the older session-end workflow and explains how it differs from its successor.
Turn Claude Code sessions into reusable working rules with evidence and confidence scores. Keep project-specific habits separate, share general patterns across projects, and group learned rules into skills, commands, or agents for repeated tasks.
Apply shared coding conventions to new modules, reviews, and refactoring. Guides descriptive naming, readable structure, updates that preserve existing data, and error handling, giving teams a consistent basis for checking code quality.
Plan database structure changes and existing data updates for production systems. Provides migration patterns for adding columns and indexes, switching applications in stages, and documenting recovery steps while accounting for downtime and database locks.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)