Productivity
pm-metrics-critic
Critiques a metrics dashboard, success-criteria section, or proposed North Star metric against the repo's metrics guide. Surfaces common failures: aggregate metrics hiding segment …
AI / ML
ce-optimize
Run metric-driven iterative optimization loops. Define a goal, add measurement scaffolding, execute parallel experiments across approaches, score results against gates or quality j…
Automation
os-improvement-loop
Coordinates concurrent multi-agent improvement cycles using shared event bus and memory. Each cycle executes, evaluates (KEEP/DISCARD), emits friction events, persists metrics and …
Business
pm-progress-auditor
Audit a status update, exec review, board email, all-hands talking point, or dashboard callout for credibility leaks before sending. Flags overstated claims, cherry-picked windows,…
Engineering
run
Sustained metric-improvement loop with atomic commits, auto-rollback, and experiment logging. Iterates with specialist agents, commits atomically, and auto-rolls back on regression…
Productivity
pm-north-star-selector
Selects a single North Star metric for a product. Weighs candidates across behavioral, value-delivered, and financial dimensions, emphasizing explainability, adoption + retention c…
Engineering
performance-budgets
Define, track, and enforce performance thresholds across time, size, and count dimensions using metrics, thresholds, percentiles, and consequences. Covers Core Web Vitals, RAIL, Li…
DevOps
forge-observability
Production observability with OpenTelemetry covering traces, metrics, and logs with correlation. Includes SDK initialization, span conventions, error handling, RED/USE metrics, sam…
Productivity
github-dashboard
GitHub repository analytics dashboard — stars, forks, contributors, issues, pull requests, recent activity, and top contributors. Use when the brief asks for a GitHub repo dashboar…
Research
hypothesis
Write testable product hypotheses with clear success metrics, baselines, targets, and timeframes. Produces a structured statement, supporting evidence, validation plan with method …
Data
metric-analyst
Use when the task involves defining, calculating, or implementing business metrics or KPIs. Covers KPI definition, SQL metric logic, Excel formulas, churn, retention, revenue, conv…
AI / ML
self-optimize
Analyzes system performance and failure patterns to autonomously improve skill prompts. Reads logs, identifies weak skills, rewrites prompts, commits changes, and rolls back if met…
Productivity
beta-program-management
Runs closed and open betas that generate actionable signal. Covers participant selection, structured feedback loops, and calibrated criteria distinguishing structured betas from un…
Productivity
ce-product-pulse
Produce a time-windowed report on user experience and product performance—usage, quality, errors, and signals to investigate. Triggered by phrases like 'run a pulse' or time ranges…
Business
ltv-cac
Unit economics calculations: LTV (Lifetime Value), LTGP (Lifetime Gross Profit), CAC (Customer Acquisition Cost), payback period, and ratios. Validates business model viability, ca…
Content
create-portfolio
Generates professional portfolio entries that highlight achievements with impact-focused content and measurable results. Use for adding projects or documenting accomplishments usin…
Research
g1
Real-time journal matching pipeline using OpenAlex and Crossref metrics. Supports multi-dimensional selection while avoiding impact-factor bias. Use for target journal choice, subm…
Productivity
goal-management
Tracks North Star goals with structured persistence, parsing vague objectives into measurable criteria, maintaining progress percentages and history, and integrating with wave exec…
Data
analytics
Queries local analytics across projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends with privacy-safe…
Productivity
north-star
Defines and maintains a project's long-term direction via North Star Statement, success metric, and will/won't boundaries. Used at project start, during scope review, or when prior…
Productivity
pm-status
Show project status dashboard with issue, feature request, and work package counts, active items, blocked items, and priority next actions. Use when asking about project status, pr…
Business
pivot-decision
Structure an evidence-based pivot, persevere, or stop decision using Eric Ries's Lean Startup pivot framework — evaluates current metrics against original hypotheses and scores piv…
Productivity
pr-ecosystem-audit
Performs a comprehensive diagnostic of the PR review ecosystem across 18 categories in 5 domains. Delivers composite health scoring, trend tracking, patch suggestions, and interact…
Productivity
ltx-leadership-weekly-report
Generates the LTX weekly leadership Slack update covering open source (Hugging Face LTX-2 family), API revenue, endpoints, leads, industries, and Studio Enterprise metrics. Runs vi…
Data
rehab-therapy
Audit rehabilitation and physical therapy platforms for recovery metrics, patient-reported outcomes, home exercise compliance, risk stratification, insurance authorization, and out…
Productivity
bmad-retrospective
Run an epic or sprint retrospective with tracker integration: gather metrics, analyze scope and quality, then save a structured retrospective to the tracker. Use for 'retrospective…
DevOps
principle-observability
Observability fundamentals covering logs versus metrics versus traces, structured logging, span context, cardinality control, OpenTelemetry integration, SLI/SLO/SLA definitions, an…
Automation
social-orchestrator
Unified social channel coordinator that manages Instagram, Telegram, and WhatsApp in a single workflow. Handles cross-channel publishing, unified metrics, content reuse, scheduling…
DevOps
buildkite-pipeline-profiler
Profiles Buildkite pipeline performance using REST and GraphQL APIs. Measures step durations, agent queue wait times, and artifact bottlenecks, then generates optimization reports …
Testing
agent-evaluation-framework
Framework for AI agent evaluation and benchmarking. Provides metrics, tests, comparisons, and quality assurance. Activates on terms like evaluate agent, agent eval, benchmark agent…
Productivity
evolve
Extract session patterns into reusable learnings. Supports analyze (pull from history), review (edit stored learnings), and list (show active items) modes. Manages .orchestrator/me…
AI / ML
vllm-speculative-decoding
vLLM speculative decoding reference covering eleven method options, --speculative-config schema, model-family pairing, Prometheus metrics, version gates, and composability with chu…
Engineering
code-metrics-analysis
Analyze code complexity, cyclomatic complexity, maintainability index, and code churn with metrics tools. Use for quality assessment, refactoring candidate identification, or techn…
Research
mobile-game-analyst
Analyzes successful mobile games (over $1M monthly) to extract working mechanics, review game design decisions, forecast metrics, and deliver market research with retention, LTV, a…
Productivity
progress-tracker
Track continuous improvement loop performance. Queries GitHub for metrics (issues created/closed, PRs merged, CI health), logs trends, and suggests process improvements. Invoke wit…
Business
roi-narrative
Produce a stakeholder-ready ROI narrative for AEM Edge Delivery Services. Compare pre- and post-launch metrics across performance, traffic, content velocity, and efficiency to quan…
DevOps
aggregating-performance-metrics
Aggregate and centralize performance metrics from applications, systems, databases, caches, queues, and external services. Facilitates metrics taxonomy design, tool selection, dash…
Data
analitica-de-produto
Tracks digital product metrics—DAU, MAU, NPS, retention, feature adoption, and activation funnels—while setting up events, analyzing data, and driving evidence-based decisions for …
DevOps
signoz
Work with SigNoz for application monitoring, distributed tracing, logs, metrics, alerts, and dashboards. Use for setup, OpenTelemetry instrumentation, or migration from other obser…
Data
wren-usage
CLI workflow for answering data questions end-to-end: gather schema, recall past queries, write SQL via the MDL layer, execute, and learn from results. Handles metrics, trends, and…
Business
biz-strategy
Perform integrated business viability review covering demand validation, business model canvas, revenue/pricing strategy, TAM/SAM/SOM analysis, GTM strategy, north-star metrics, an…
Engineering
detecting-performance-bottlenecks
Detects and resolves performance bottlenecks by analyzing CPU, memory, I/O, and database metrics. Use when diagnosing slow applications, optimizing resource usage, or preventing pe…
Research
omd-lab-02-design-harness
Runs identical tasks under successive harness versions to measure output quality, token cost, iteration count, and abandonment rate. Supports comparative analysis of harness config…
Business
product-market-fit-analysis
Expert framework for assessing and achieving product-market fit. Combines PMF measurement methodologies, Sean Ellis survey, retention analysis, segment-specific PMF, and post-PMF s…
Data
bio-clip-seq-clip-qc
Run quality control on CLIP-seq libraries covering complexity, FRiP, IDR reproducibility, metagene profiles, and contamination checks. Assesses library success and guides peak-call…
AI / ML
karpathy-autoresearch
Iterative optimization loop: modify one element, score the result, keep winners, discard losers, and repeat. Works on any scorable target including code, prompts, configs, content,…
Research
paper-repo-evaluator
Evaluates code repository quality linked to research papers, covering GitHub metrics, language, and integration effort. Auto-triggers during paper-pipeline workflows at the code as…
Data
reversa-docs-analyst
Reversa Docs analyst producing quantitative pages: metrics dashboard with Highcharts visualizations and interactive project event timeline. Handles metrics regeneration and dashboa…
Testing
validating-performance-budgets
Validate application performance against defined budgets to catch regressions early. Triggered by mentions of performance budgets, regressions, or metrics like load times and Light…
DevOps
lokalise-observability
Implement observability for Lokalise integrations including metrics, traces, and alerts. Use for monitoring Lokalise operations, building dashboards, and configuring integration he…
Business
forecast-accuracy-tracking
Tracks forecast accuracy over time, compares forecasts against actuals, detects systematic bias, and supports process improvements. Activates on accuracy, bias, MAPE, or track-reco…
Content
elsj-pruefkriterien-fuer-qualitaet
Provides quality criteria for plain and easy language: word length, sentence length, verb ratio, foreign-word ratio, active/passive balance. Recommends LIX and Hohenheim readabilit…
Data
app-analytics
Set up, interpret, or improve app analytics and tracking. Triggered by mentions of analytics, tracking, metrics, KPIs, install tracking, funnels, attribution, or app performance qu…
DevOps
dashboard-builder
Build monitoring dashboards that answer real operator questions for Grafana, SigNoz, and similar platforms. Use when turning metrics into functional dashboards rather than vanity d…
Web
olares-dashboard
Mirrors dashboard SPA routes with dual-shape JSON handling and monitoring utilities. Exposes stable Kind constants and ported formatting functions for metrics, units, and time-base…
Research
fortify
Runs systematic ablation studies by creating isolated git worktrees from diffs and diaries, executes metrics per component, ranks importance and generates venue-calibrated reviewer…
Productivity
framework-health
Evaluates Mycelium process effectiveness by measuring cycle velocity, discard trends, confidence calibration, gate effectiveness, and regression rate. Run quarterly or every 20 cyc…
Productivity
cost
Shows how many tokens engram has saved in this session, this week, and across all indexed projects. Use when the user asks about token usage, savings, costs, or wants a digest repo…
AI / ML
evaluating-machine-learning-models
Evaluates trained machine learning models using appropriate metrics and comparison logic. Use for benchmark review, threshold selection, calibration, validation, and model comparis…
AI / ML
optimizing-deep-learning-models
Optimizes deep learning models for accuracy, training time, or resource use. Analyzes architecture and metrics then applies techniques such as Adam, SGD, and learning rate scheduli…
Showing the top 60 of 788. See the full list →