Abhillashjadhav

Abhillashjadhav/AI-PM-essential-skills

Command Claude Code

Reviews any PR or proposed change to a skill file in this repo. Run before merging anything.

Abhillashjadhav/AI-PM-essential-skills

Command Claude Code

You are the PR review agent for Abhillash's repos. You are ONE agent playing TWO roles in sequence — reviewer first, then fixer — within a single context. There are no subagents. Do not invoke the Task tool.

Abhillashjadhav/AI-PM-essential-skills

Skill Claude Code

Forces a written PRD before any code generation. Use this skill when the user says "build", "create app", "make me a", "vibe code", "let's build", "I want an app that", "spin up a", "prototype a", "ship a", or any phrasing that signals they want code generated from a high-level idea. Also use when the user references…

Abhillashjadhav/AI-PM-essential-skills

Plugin Claude Code

Bundles 1 skill · 144 tokens together

Qualifies whether an AI workflow needs a graph, then designs a bounded graph of specialist loops or agents with typed node, edge, state, handoff, join, verification, budget, permission, recovery, and human-approval contracts. Produces a Mermaid view, machine-readable contract, and vendor-neutral orchestration skeleton.

Abhillashjadhav/AI-PM-essential-skills

Plugin Claude Code

Bundles 1 skill · 72 tokens together

Pre-build decision skill for AI product teams: converts an AI feature idea into falsifiable assumptions, explicit kill thresholds, an evidence plan, and a decision date before development starts.

Abhillashjadhav/AI-PM-essential-skills

Skill Claude Code

Use this skill when a user wants to compress verbose model output, shorten a draft, reduce token usage, or improve the signal-to-noise ratio of any text. Triggers on phrases like "make this shorter", "compress this", "too verbose", "reduce tokens", "cut this down", "rewrite more concisely", or when a user pastes a…

Abhillashjadhav/AI-PM-essential-skills

Skill Claude Code

Use this skill when a user wants to audit a CLAUDE.md, system prompt, agent context file, or any assembled context before running it in production. Triggers on phrases like "audit my context", "check my CLAUDE.md", "review my system prompt", "why is my agent behaving badly", "context issues", or when a user pastes a…

Abhillashjadhav/AI-PM-essential-skills

Plugin Claude Code

Bundles 1 skill · 226 tokens together

Designs recurring workflows with explicit discovery, deduplication, verification, work limits, durable-state rules and notifications. Produces scheduled prompt templates; runtime locking, budget enforcement and deployment remain host responsibilities.

Abhillashjadhav/AI-PM-essential-skills

Plugin Claude Code

Bundles 1 skill · 220 tokens together

Reviews MCP configs against selected source-cited migration rules for protocol 2026-07-28. Reports observed incompatibilities, scoped clearances and unconfirmed capabilities; does not certify full protocol conformance.

Abhillashjadhav/AI-PM-essential-skills

Plugin Claude Code

Bundles 1 skill · 112 tokens together

Voice-preserving editor for product writing. Removes recognisable AI-writing patterns, protects concrete facts and product judgment, and returns a clean draft plus named edits without turning the writer into generic polished prose.

Abhillashjadhav/AI-PM-essential-skills

Plugin Claude Code

Bundles 5 skills, 3 agents · 899 tokens together

Five skills with manual acceptance examples that make a PM's daily Claude workflow cheaper, faster, and self-checking — now proactive by default: model-complexity-router (silently scores every task handoff, not just direct questions), builder-validator (frozen-spec self-QA, checklist frozen silently, never invents…

Abhillashjadhav/AI-PM-essential-skills

Plugin Claude Code

Bundles 1 skill · 190 tokens together

AI Evals for PMs turns a product contract into outcome, trajectory, system, and optional memory evidence with isolated trials, calibrated judgments, inspection, and CI-safe PASS/FAIL/BLOCKED release gates.

Abhillashjadhav/AI-PM-essential-skills

Skill Claude Code

Use this skill when estimating inference cost before running a prompt in production or sharing a workflow with stakeholders. Triggers on phrases like "how much will this cost", "compare model costs", "which model should I use", "estimate tokens", "pre-flight check", or when a user pastes a prompt and asks about…

Abhillashjadhav/AI-PM-essential-skills

Command GitHub Copilot

Command "001-optional-claude-review" from Abhillashjadhav/AI-PM-essential-skills, covering date, branch, public task record, privacy note and status.

Abhillashjadhav/AI-PM-essential-skills

Command GitHub Copilot

Make the public repository surface accurate and evidence-backed without modifying existing AI-PM skills or removing ContextPort.

Abhillashjadhav/AI-PM-essential-skills

Command GitHub Copilot

Make pm-verifier the single public AI PM evaluation product. Migrate the useful capabilities from Abhillashjadhav/pm-evals and Abhillashjadhav/Evals-pass-1; do not create another eval product.

Abhillashjadhav/AI-PM-essential-skills

Command GitHub Copilot

Make pm-verifier the one installable, versioned evaluation product in this repository. A clean checkout must support this complete loop without a second evaluation product.

Abhillashjadhav/AI-PM-essential-skills

Plugin Claude Code

Bundles 1 skill · 174 tokens together

Asks the questions needed to build a model grader, and nothing else. Twenty-six questions: ten on shape, eight on integrity, eight on verdict — the shape a grader mechanically needs, the eight integrity questions whose absence lets a model fake success, and the verdict and judgment rules. Exits on a buildability test.