← all publishers

AmitSinghOM

@amitsinghom source repo

Report this profile Claim this profile

• 4 skills
• 0 followers
• 17 hours ago last updated

1. ▌
   Code Quality Gate · amitsinghom bundle

   Use when preparing a pull request and you want a quality read on the diff, wiring a pre-commit hook or CI step that must fail only on NEW issues, triaging analyzer JSON/SARIF findings, or the user mentions code quality, complexity, changed-line gating, baselines, or SARIF. Runs the privacy-first offline analyzer cqa-analyzer (Python, Go, TypeScript/JS, Java, Kotlin, C#, C/C++, and an experimental Rust pilot) and turns findings into a deterministic pass/fail gate scoped to the lines you changed.
   0 installs
2. ▌
   Learning Accelerator · amitsinghom bundle

   Use when the user asks to learn, understand, study, master, or prepare for any topic or skill. Turns the request into a structured learning loop — 80/20 plan, difficulty ladder, justified resources, one-page cheat sheet, escalating one-at-a-time quiz, Feynman teach-back — instead of a one-shot explanation. Enforces retrieval practice and spaced retest of logged weak areas.
   0 installs
3. ▌
   Architecture Baseline · amitsinghom bundle

   Use when starting work on an existing codebase, before implementing a feature that adds modules or dependencies, when the user asks 'where should this go', 'does this fit the architecture', or 'has the structure drifted', or when onboarding an agent onto a repo. Captures the codebase's observed architecture from cqa-analyzer output — layers, which design/DSA patterns live in which layers, score — into ARCHITECTURE.md + a machine snapshot, then guides new development to follow that structure and checks each change for drift (patterns leaking into new layers, score regressions).
   0 installs
4. ▌
   Source Grounded Claims · amitsinghom bundle

   Use when producing any substantive answer, claim, assumption, recommendation, or review — research findings, architecture calls, code review, status statements. Attaches an explicit calibrated confidence percentage to each substantive claim (80% is the 'likely true' threshold for acting on it), verifies facts against primary sources before asserting them, and cites only sources actually consulted. Never fabricates a citation.
   0 installs