AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
pratikshadake avatar

pratikshadake

29 listings · 0 installs

Open-source publisher. Listings imported from github.com/pratikshadake — credited to the original author with their license.

↗ github.com/pratikshadake
29 results
Self-run
SKILL

Value Vs Effort

Prioritizes features using structured scoring across user impact, revenue potential, strategic alignment, confidence, and engineering effort. Use when deciding which feature to build next or comparing competing priorities.

0
9
Free
Self-run
SKILL

Prompt Regression Tester

Tests AI prompts for quality regression by storing baseline outputs and detecting drift after prompt changes. Use when modifying prompts in production AI systems and you need to verify that changes do not degrade output quality.

0
10
Free
Self-run
SKILL

Hallucination Detector

Detects hallucination risks in AI-generated content by identifying missing sources, overconfidence, and fabricated facts. Use when reviewing AI outputs, validating claims, or assessing the reliability of generated text before using it in production.

0
7
Free
Self-run
SKILL

Incident Commander

Guides incident response for production outages and system failures. Use when a production incident occurs and you need to assess severity, stabilize the system, communicate updates to stakeholders, and track the incident timeline in real time.

0
10
Free
Self-run
SKILL

Tradeoff Articulator

Clearly explains gains, losses, and reasoning behind a product decision. Use when communicating tradeoffs to stakeholders or documenting why a particular path was chosen over alternatives.

0
7
Free
Self-run
SKILL

Growth Experiment Designer

Designs structured growth experiments to improve key product metrics. Use when you want to increase signups, retention, conversion, or any measurable metric and need a hypothesis-driven experiment with clear success criteria and decision rules.

0
8
Free
Self-run
SKILL

Feature Adoption Analyzer

Analyzes why a shipped feature is or isn't being used, covering adoption metrics, barriers, user feedback signals, and recommended actions. Use after launching a feature to diagnose adoption issues.

0
9
Free
Self-run
SKILL

Stakeholder Alignment Checker

Reveals hidden disagreements between stakeholders before execution begins. Use when kicking off cross-functional projects, planning launches, or sensing misalignment between teams on goals or priorities.

0
10
Free
Self-run
SKILL

Blameless Postmortem Writer

Writes structured blameless postmortems for production incidents. Use when an incident has occurred and you need to document what happened, the impact, root cause, timeline, and action items without blaming individuals.

0
5
Free
Self-run
SKILL

Jtbd Extractor

Translates feature ideas into Jobs-to-Be-Done format with functional and emotional jobs, success criteria, and switching triggers. Use when reframing feature requests to understand the underlying user motivation.

0
8
Free
Self-run
SKILL

Token Cost Optimiser

Reduces AI API costs by optimizing prompts, caching results, and selecting smaller model fallbacks. Use when AI inference costs are too high, when optimizing LLM usage in production, or when you need a cost reduction plan for token-heavy workflows.

0
7
Free
Self-run
SKILL

Roadmap Reality Checker

Detects unrealistic planning and hidden delivery risks like overcommitment, missing dependencies, resource mismatches, and undefined metrics. Use when reviewing quarterly roadmaps or sprint plans.

0
9
Free
Self-run
SKILL

Eval Dataset Generator

Generates evaluation datasets for AI systems by defining success criteria and creating normal and edge case test inputs. Use when building or testing AI models, prompts, or pipelines and you need structured test sets to measure quality.

0
11
Free
Self-run
SKILL

Kill The Feature Analyser

Analyzes whether a product feature should be killed, kept, or replaced by evaluating usage data, revenue impact, and maintenance cost. Use when considering sunsetting a feature, cleaning up a product, or making hard prioritization decisions about existing functionality.

0
6
Free
Self-run
SKILL

Problem Clarity

Evaluates whether a proposed idea addresses a genuine user problem worth solving. Use when assessing new feature ideas, startup concepts, or vague user complaints to determine if the pain justifies building a solution.

0
10
Free
Self-run
SKILL

User Segment Prioritizer

Identifies which user segment to focus on first using pain severity, willingness to pay, reachability, and strategic alignment. Use when choosing your initial target audience or re-evaluating segment focus.

0
9
Free
Self-run
SKILL

Build Vs Buy

Provides a rigorous, repeatable framework to decide whether a team should build a solution internally or purchase an external product. Use when evaluating a new capability, considering a SaaS tool or vendor, or when someone asks "should we just build this?" Covers time to value, TCO, strategic differentiation, control and risk, and opportunity cost.

0
7
Free
Self-run
SKILL

Retention Drop Diagnoser

Identifies root causes behind declining user retention with likely causes, supporting evidence, and fix experiments. Use when you observe a retention drop and need to systematically diagnose why users are leaving.

0
10
Free
Self-run
SKILL

Launch Readiness

Audits whether a feature or product is truly ready for launch with a structured checklist and readiness status (Ready/At Risk/Not Ready). Use before any product launch to catch critical gaps.

0
12
Free
Self-run
SKILL

Ship In 7 Days Planner

Creates an aggressive day-by-day execution plan to launch a product or feature within one week. Use when you need to ship fast, freeze scope, cut polish, and break work into daily milestones to hit a 7-day launch deadline.

0
9
Free
Self-run
SKILL

Prd Critic

Evaluates PRD quality for clarity, testability, and build-readiness across problem clarity, scope, acceptance criteria, edge cases, and metrics. Use before sharing a PRD with engineering to catch gaps early.

0
8
Free
Self-run
SKILL

Outcome Definition

Shifts thinking from feature delivery to measurable user or business outcomes. Use before building a feature, during roadmap planning, or while defining success metrics to ensure work ties to real results.

0
10
Free
Self-run
SKILL

Rollback Decision Framework

Evaluates whether to roll back a deployment immediately or wait for a fix by assessing user impact, data risk, and estimated fix time. Use during production incidents when a recent deployment may be causing issues and you need a fast, structured rollback decision.

0
9
Free
Self-run
SKILL

Experiment Design

Designs fast, reliable validation experiments with hypothesis, method, success metric, and decision rules (Ship/Iterate/Kill). Use when you need to validate an assumption or test a product hypothesis before committing resources.

0
9
Free
Self-run
SKILL

Should We Build This

Evaluates whether a feature or product idea is worth building by scoring user pain severity, revenue impact, effort, and strategic alignment. Use when deciding whether to add a feature to the roadmap or when someone asks "should we build this?" and you need a structured go/no-go decision.

0
10
Free
Self-run
SKILL

Refactor Vs Growth

Decides whether to refactor existing code now or ship new features first by comparing the risk of current code, time to refactor, and roadmap impact. Use when technical debt is slowing development and you need to choose between cleaning up code or continuing to ship.

0
9
Free
Self-run
SKILL

Post Launch Learning

Turns launches into structured learning by comparing expected vs actual outcomes and extracting key learnings. Use after any product launch to capture what worked, what didn't, and inform future decisions.

0
9
Free
Self-run
SKILL

Assumption Mapper

Exposes hidden risks by identifying and ranking assumptions across desirability, feasibility, and viability categories. Use when evaluating new products or features to surface the highest-risk assumption to test first.

0
8
Free
Self-run
SKILL

Mvp Scoper

Defines the smallest possible product that delivers real user value and can be built quickly. Use when scoping a new startup idea, a large feature request, or during pre-build planning to identify the minimum testable feature set buildable in 14 days or less.

0
12
Free
You've reached the end · 29 loaded