harshitsinghbhandari
- 18 skills
- 0 followers
- 13 hours ago last updated
- ▌ LLM Forge · harshitsinghbhandari bundleRun existing work through 5 specialist craftspeople who each produce an improved version, then peer-review and synthesize the best into a single improved artifact. Use when the user says "forge this", "improve this", "make this better", "level this up", "refine this", or asks for multi-angle improvement on code, copy, strategy, plans, designs, or any artifact where the current version works but could be significantly better. Do NOT use for decisions (use llm-council), simple edits, or creation from scratch.
- ▌ Pr Review · harshitsinghbhandari bundleComprehensive PR review focusing on code quality, test coverage, security, backward compatibility, and what CI cannot check. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
- ▌ LLM Council · harshitsinghbhandari bundleConvene an LLM Council for high-stakes decisions requiring multiple perspectives. Use when the user says "council this", "run the council", "get council input", or asks for multi-perspective analysis on strategic decisions like pricing, positioning, pivots, hiring, or any question where being wrong is expensive. Do NOT use for simple factual questions, writing tasks, or summarization.
- ▌ Pr Learning · harshitsinghbhandariExtract actionable learnings from merged PRs by comparing initial submission vs final merged state. Analyzes review cycles to capture what changed and why. Use when the user says "learn from PR", "extract PR learnings", "what did we learn from this PR", or wants to build a knowledge base from merged PRs.
- ▌ Resume Critic · harshitsinghbhandari bundleConstructively critique resumes from multiple professional perspectives, but only against a specific job description or at least a concrete job title. Use when the user asks for resume review, ATS feedback, interview readiness, bullet improvement, or tailored resume critique for a target job. Do NOT use for full resume rewriting unless the user explicitly asks for rewrites.
- ▌ Spec And Ship · harshitsinghbhandari bundleUse when building, adding, or significantly changing any non-trivial feature, system, refactor, integration, or migration that will be built out through Agent Orchestrator (AO) workers. Also triggers on "interview me", "ask me questions first", "help me spec this out", "I want to build X", "let's plan Y before we code", or handing over a spec doc / PRD / design brief to start work. Skip for bug fixes, one-liners, and cosmetic tweaks.
- ▌ Resume Rewrite · harshitsinghbhandari bundleRewrite a resume using only the candidate's existing material, but only after a `resume-critic` review has been completed for a specific job description or job title. Use when the user wants the resume rewritten, tightened, or retargeted without inventing new experiences.
- ▌ Resume Upgrade · harshitsinghbhandari bundlePropose how to upgrade a resume by identifying missing projects, skills, evidence, and experience-building moves, but only after a `resume-critic` review has been completed for a specific job description or job title. Use when the user wants strategic suggestions beyond the current resume.
- ▌ Sharpen Intent · harshitsinghbhandari bundleUse ONLY when the user explicitly asks to sharpen, pressure-test, interrogate, or stress-test an idea, decision, or plan they are holding. Triggers on "sharpen this", "interrogate my idea", "pressure-test this decision", "grill me on X", "help me get this crisp before I act". Grills the human 2-3 questions at a time until their intent is stated cleanly enough that a stranger could act on it with zero ambiguity, then writes a sharpened-intent artifact. Manual-only: do NOT self-activate on "I want to build X" (that is spec-and-ship). Skip when intent is already clear, or the idea is small enough to just do.
- ▌ Edge Case Hunter · harshitsinghbhandari bundleExhaustive edge-case review that traces branching paths and boundary conditions in a diff or code sample and reports only unhandled cases. Use when the user asks to hunt edge cases, boundary conditions, missing guards, or wants an edge-case-focused review.
- ▌ Update Changelog · harshitsinghbhandari bundleExpert skill for maintaining a Keep a Changelog formatted CHANGELOG.md file. Use this skill whenever you add features, fix bugs, or release a new version. You MUST use this skill to record any changes that have a user-facing impact. It handles categorization (Added, Changed, Fixed, etc.), semantic versioning, and reverse-chronological ordering with surgical precision.
- ▌ Architecture Audit · harshitsinghbhandari bundleComprehensive architecture audit that combines ruthless analysis with solution-focused improvement planning. Reads architecture Markdown files, produces a brutal audit report with file/component scores, and generates a prioritized improvements roadmap.
- ▌ Code Quality Audit · harshitsinghbhandari bundleComprehensive code quality audit that combines ruthless analysis with a solution-focused refactoring roadmap. Reads source code files, produces a brutal audit report with per-file quality scores, and generates prioritized refactoring improvements.
- ▌ Itemized Functions · harshitsinghbhandari bundleGenerate exhaustive integration functions with comprehensive test suites for all 3rd-party APIs and external services. Automatically creates function wrappers, individual test files, integrated test runners, and a detailed report of API behavior, response signatures, latency, and failure modes.
- ▌ Boundary Bug Hunter · harshitsinghbhandari bundleAggressive user-flow and boundary-bug analysis on a diff or branch. Auto-detects entry points, traces flows through changed code, finds every seam (cross-module calls, serialization, file I/O, shared state, schema versioning, network/IPC), and refuses to mark the work complete until each unverified boundary has a real round-trip test or an explicit written out-of-scope record persisted in an audit file. Use whenever the user says "boundary check", "seam check", "round-trip check", "flow boundaries", "user-flow check", "before merge", "is this safe to ship", "pre-merge gate", "boundary bugs", "verify the joins", or asks to validate cross-module joins, producer/consumer contracts, or end-to-end coverage of a change. Also use as a final gate from pr-review on any diff that touches more than one file, module, or process. Be pushy. Most surviving production bugs live at seams, not inside units — if the diff crosses any boundary, this skill almost certainly applies.
- ▌ Test Coverage Audit · harshitsinghbhandari bundleComprehensive test suite audit that combines ruthless analysis with a solution-focused roadmap. Reads test suites (unit, integration, e2e) and source code, produces a brutal audit report of test quality and gaps, and generates prioritized testing improvements.
- ▌ Frontend Architecture · harshitsinghbhandari bundleUse when scaffolding a new web frontend or making any frontend architecture decision for a React web app (choosing a data-fetching layer, router, state management, styling system, sync/offline strategy, real-time transport like WebSocket/SSE, type generation, or deploy target). Triggers on greenfield "set up the app" work and mid-project structural choices alike (e.g. "how should we manage state", "what router", "add offline mode", "wire up the backend types").
- ▌ Code Refactor Executor · harshitsinghbhandari bundleExecutes a multi-stage refactoring plan based on existing `audit.md` and `improvements.md` files. Reads the recommendations, scans the target source code, and builds an implementation roadmap before applying atomic code transformations.