@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 286.4K
Turn existing interface code into shared design rules for colors, type, and spacing, with documented decisions and an interactive preview. Audit visual consistency across ten areas and identify specific places to improve.
Write Django and Django REST Framework tests with pytest-django, starting with tests before implementation. Covers test data generation, simulated external services, model and API checks, and coverage reports showing which code the tests exercise.
Create monitoring dashboards for Grafana, SigNoz, and similar platforms. Choose metrics around operational questions, organize panels by purpose, and define clear titles, units, filters, and thresholds to help operators assess health and bottlenecks.
Plan database schema and data changes for production systems. Use staged column replacements, concurrent index creation, and batched data updates to limit disruption, with migration workflows for PostgreSQL, Prisma, Drizzle, Kysely, Django, and golang-migrate.
Define success criteria before AI coding, then assess new capabilities and check that existing behavior still works using code, rules, models, or human review. Track repeated-attempt success metrics and reports to compare prompt changes, agent changes, or model versions.
Add one optional Codex critique to a decision draft produced by council. With explicit consent to send the draft to OpenAI, examine weak conclusions, missing failure scenarios, and overlooked dissent before the user makes the final decision.
Handle customer billing issues with connected tools such as Stripe. Review subscriptions and invoices, classify the problem, address refunds or cancellations, and prepare a handoff with revenue impact, customer follow-up text, and product gaps.
Write, review, and refactor C# and .NET code using practical conventions for asynchronous work, configuration, and dependency injection—passing services into classes. Includes examples for data access and APIs to support maintainable applications.
Investigate unexpected costs in the ECC Tools GitHub App by tracing events, queued jobs, analysis workers, and billing logic. Identifies repeated pull request creation, usage-limit bypasses, unintended premium-model calls, and duplicate retries, then verifies targeted fixes.
Navigate ECC by checking its current files to find suitable skills, commands, and configuration options. Get focused guidance on installation, reset procedures, project setup, and troubleshooting duplicate installs, with concrete files and next steps to inspect.
Check learning-log timestamps, free disk space, and shortcut-related phrases before Claude Code ends a session. A Stop hook, which runs when the agent tries to finish, warns or blocks completion according to configured rules without using AI judgment.
Design task-specific workflows for repeated agent work, with pass/fail checks, progress records, and handoff notes. Identify when a temporary workflow should become a shared skill that teammates can run and evaluate again.
Design continuous agent workflows with quality checks, evaluations, and recovery controls. Helps choose a loop pattern for the task and define how to pause, audit, narrow scope, and retry when work stalls or fails.
Review Django authentication, permissions, input handling, and production settings. Use concrete configuration and code examples to address malicious queries, unwanted requests, injected scripts, unsafe uploads, and API access, alongside secret management and security logging.
Add background jobs to Django with Celery, moving work such as email delivery and PDF generation outside web requests. Covers scheduled runs, retries, linked or parallel tasks, monitoring, and tests, with Redis or RabbitMQ carrying task messages.
Helps prepare web applications for production with automated testing and deployment workflows, Docker packaging, health checks, and rollback plans. Provides examples and checklists for choosing release strategies and reviewing readiness before launch.
Build a scheduled agent that collects public website or API data, summarizes or scores it with Gemini Flash, and stores results. Includes guidance for duplicate removal and using user feedback to inform future scoring.
Compare ambiguous choices through four advisory perspectives covering long-term consequences, assumptions, practical execution, and failure risks. The skill presents each position, highlights the strongest disagreement, and combines the findings into a recommendation for the decision.
Write and review C# and .NET tests using xUnit examples. Covers unit tests, mocks that replace dependencies, API and database integration tests, reusable test data, and project organization to check behavior and outcomes.
Defines a browser workflow for placing signature, date, and text fields at verified numeric coordinates. Covers recipient ownership, placement screenshots, and draft saving, with explicit approval required before sending an electronic signature request.
Documents a legacy workflow for extracting reusable solutions from Claude Code sessions and saving them as learned skills. Useful for reviewing existing setups and extraction settings; this version is deprecated in favor of continuous-learning-v2.
Design an LLM API workflow that controls spending through task-based model selection, budget tracking, selective retries, and caching repeated prompts. Use the examples to route simpler tasks to cheaper models and track cumulative costs.
Coordinate parallel AI agent sessions with dmux, a tool that manages terminal panes. Split development, research, testing, or review into separate tasks, isolate overlapping file changes, and review results before merging them.
Define when an agent may respond in shared chats with customers or partners and what it may send. Separate authorized routine replies from approval-only drafts while keeping internal information out of external messages.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)