keshav55

Collaborative drafting. Works with user to fill the outline sentence by sentence. Asks questions, offers options, matches the feel, shows improvement.

Interactive planning for writing. Gets user input, confirms intent, identifies research needs, does the research, outputs a filled outline ready for the writer.

Detects AI writing patterns and fixes them. Use when reviewing any written output, including docs, READMEs, messages, PRDs. Based on Wikipedia's AI Cleanup patterns.

Atris workflow enforcement for repos using atris/ (MAP, TODO, journal, features, plan-do-review, anti-slop). Use when the user asks to follow the Atris system or mentions atris, MAP.md, TODO.md, journal/logs, features, plan/do/review, or anti-slop policies.

PRD-driven autonomous execution - give it a task, it loops until done

Backend architecture policy. Use when building APIs, services, data access, or any backend work. Prevents over-engineering.

Detects AI writing patterns and fixes them. Use when reviewing any written output, including docs, READMEs, messages, PRDs. Based on Wikipedia's AI Cleanup patterns.

Frontend aesthetics policy. Use when building UI, components, landing pages, dashboards, or any frontend work. Prevents generic ai-generated look.

Self-improvement loop for agent-crm. Analyzes CRM data to find what's working, proposes one experiment, and tracks results via the facts table. Use when the user says evolve, improve, self-improve, optimize, what's working, experiment, or strategy.

Salesforce CRM sync via REST API. Pull contacts, opportunities, accounts, and activities into local agent-crm. Push local changes back. Use when user asks about Salesforce data, syncing CRM, importing deals, or pushing updates to Salesforce.

Security scanner for agentic engineering. Run before shipping to catch leaked secrets, injection vectors, and misconfig. Use when done coding, before commit, or before deploy.