Triage a bug or issue by exploring the codebase to find root cause, then create a GitHub issue with a TDD-based fix plan. Use when: user reports a bug, wants to file an issue, mentions "triage", or wants to investigate and plan a fix for a problem.

Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when: user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

Lint and format Python with Ruff. Use when a user asks to set up Python linting, replace flake8/black/isort, configure code quality rules, or speed up Python code formatting.

Captures clause risks, compliance gaps, precedent shifts, contract deviations, regulatory changes, and litigation exposure to enable continuous legal operations improvement. Use when: (1) An unfavorable clause is accepted or slips through review, (2) A compliance deadline is missed or approaching, (3) A new regulation impacts the organization, (4) A contract remains unsigned past SLA, (5) An IP infringement notice is received, (6) New case law changes interpretation in a relevant jurisdiction, (7) A data subject access request reveals process gaps.

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology evaluation tools, and ADR templates. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

Build and test Polymarket prediction market trading strategies for YES/NO token trading. Provides 6 tools: get_all_prediction_events (browse markets, $0.001), get_prediction_market_data (analyze price history, $0.001), create_prediction_market_strategy (generate code, $1-$4.50), run_prediction_market_backtest (test performance, $0.001). Trade on real-world events (politics, economics, sports, crypto). Currently simulation only (live deployment coming soon).

AI code review for PR or local changes

Review and analyze product metrics with trend analysis and actionable insights. Use when running a weekly, monthly, or quarterly metrics review, investigating a sudden spike or drop, comparing performance against targets, or turning raw numbers into a scorecard with recommended actions.

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

Write the test first, watch it fail, write minimal code to pass

Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.

Creates comprehensive post-incident documents with timeline, root cause analysis, contributing factors, action items, and ownership. Follows SRE best practices for blameless postmortems. Use for "postmortem", "incident review", "RCA", or "post-incident".

Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales

Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heatmap for sharing (e.g., via Telegram). Use when the user says things like “start deep work”, “stop deep work”, “am I in a session?”, “show my deep work graph”, or asks to review deep work history.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Review legal documents (NDA, contracts, agreements) for sensitive clauses, risks, and red flags

Validate CRM/PM changes before PR

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Rapidly evaluate incoming NDAs, classify them as GREEN (sign-ready), YELLOW (minor issues needing review), or RED (material problems requiring negotiation), and route them appropriately. Use when sales or business development sends a new NDA, when triaging confidentiality agreements, when deciding if an NDA can be approved without counsel, or when assessing non-disclosure agreement risk.

Transform raw user research data into actionable product insights, personas, and prioritized opportunities. Activate for interview analysis, survey interpretation, usability test findings, support ticket pattern mining, behavioral data synthesis, thematic coding, affinity diagramming, persona building, or opportunity scoring.

Decompose financial variances into underlying drivers and produce narrative explanations with waterfall bridge analysis. Use for budget vs actual analysis, period-over-period comparison, revenue variance decomposition, expense variance analysis, variance commentary, waterfall charts, forecast accuracy measurement, or P&L flux review.

Apply statistical techniques to data — descriptive statistics, distributions, hypothesis testing, A/B test evaluation, outlier detection, trend analysis, correlation, forecasting, p-values, confidence intervals, significance testing, and avoiding common statistical pitfalls like Simpson's paradox and survivorship bias.

Construct and review journal entries with correct debit/credit structure, supporting calculations, and approval workflows. Use for month-end accruals, prepaid amortization, depreciation entries, payroll booking, revenue recognition journal entries, manual adjustments, recurring entries, reversing entries, or intercompany journal entries.

Alpha Forge quality gates for PR review - RNG determinism, URL validation, parameter validation, manifest sync.

Run a structured quality review before shipping code at any checkpoint such as PRs, releases, or milestones. Use whenever the user says.

Detect and refactor code duplication with PMD CPD. TRIGGERS - code clones, DRY violations, duplicate code.

Complete post-session workflow - finalize orphaned recordings, convert, and AI summarize. TRIGGERS - post session, analyze recording, session review

Validate and fix GFM links in PR descriptions. TRIGGERS - PR links, gh pr create, GFM validation, broken PR links.

Manage global ignore patterns for lint-relative-paths. TRIGGERS - statusline ignore, add ignore pattern, lint ignore, path lint exclude.

Print a compact health report for FloatingClock. Covers binary info, code-sign status, running process, and test-suite status. Use when a user.

Reviews sales calls, extract coaching insights, and score against MEDDPICC/SPIN/Challenger. Use when a rep lost a deal and you want to understand why, call went sideways and need to debrief, not sure if rep is qualifying properly, need to pull action items from a recorded call, rep talking too much and not listening, or need to give structured feedback on a call. Do NOT use for prepping discovery questions (use /sales-discovery), general objection handling strategy (use /sales-objection), or deal-level risk analysis (use /sales-deal-inspect).

Birdeye platform help — reviews, listings, social media, messaging, surveys, referrals, payments, and BirdAI for multi-location businesses. Use when review requests not generating responses, Google Business Profile listings out of sync, webchat not converting visitors, survey response rates low, unsure how to set up BirdAI automation, or comparing Birdeye vs Podium vs Yext vs Reputation.com. Do NOT use for ecommerce product review apps like Judge.me or Yotpo (use /sales-customer-reviews) or B2B software reviews on G2 (use /sales-g2).

KUDO platform help — enterprise real-time AI speech translation and human interpretation in 200+ languages, embeddable widget for any meeting platform, 12,000+ interpreter marketplace, SOC 2 Type 2 + ISO 27001. Use when setting up KUDO for multilingual meetings or conferences, choosing between AI speech translation and human interpreters on KUDO, KUDO embeddable widget not working on a third-party event platform, comparing KUDO vs Interprefy vs Wordly vs JotMe for live interpretation, understanding KUDO Pro vs ProPlus vs ProPlatinum vs Enterprise pricing, or embedding KUDO translation into a hybrid event workflow. Do NOT use for choosing between all AI note-takers (use /sales-note-taker) or reviewing a call for coaching (use /sales-call-review).

Sybill platform help — AI sales assistant with Magic Summaries, CRM Autofill, Deal Workspace, Ask Sybill, and follow-up automation. Use when setting up Sybill CRM autofill for Salesforce or HubSpot, Magic Summaries not generating or taking too long, Sybill bot joining meetings you don't want it on, configuring Ask Sybill for deal questions, choosing between Sybill and Gong or Fathom or Avoma, CRM fields not populating after calls, setting up Sybill webhooks or Zapier automations, or understanding Sybill pricing tiers and what's gated to Business or Enterprise. Do NOT use for picking between note-takers generally (use /sales-note-taker) or reviewing a single call for coaching (use /sales-call-review).

Memoro platform help — German GDPR-first AI meeting assistant with local device recording, customizable Blueprints, and searchable Memories. Use when setting up Memoro for a team, choosing between Memoro plans (Free/Plus/Pro/Ultra), Memoro transcription quality is poor or wrong language detected, Memoro Blueprints not producing the right output format, Memoro recordings not syncing across devices, comparing Memoro vs Jamie or Granola for bot-free EU-hosted recording, or evaluating GDPR-compliant meeting note-takers hosted in Germany. Do NOT use for reviewing a specific call for coaching (use /sales-call-review) or comparing note-takers broadly (use /sales-note-taker).

Dicte platform help — EU privacy-first AI meeting assistant with post-quantum encryption, on-device DicteBOX, and open-source/EU AI models only. Use when evaluating Dicte for GDPR-compliant meeting recording, setting up Dicte for multilingual transcription in French/German/Spanish/Italian/English, configuring customizable AI analysis SKILLs (SWOT, project reports, mind maps), needing on-premises meeting recording for regulated industries, or troubleshooting transcription accuracy on mobile recordings. Do NOT use for choosing between note-takers generally (use /sales-note-taker) or reviewing a single call for coaching (use /sales-call-review).

Scribbl platform help — bot-free AI meeting notes Chrome extension for Google Meet with instant summaries, action items, and AI Copilot chat. Use when setting up Scribbl for automatic meeting recording and transcription on Google Meet, troubleshooting Scribbl Chrome extension not recording or transcription missing, configuring team sharing and meeting library organization with collections, deciding between Scribbl free and Pro plans or evaluating whether Team plan CRM integrations are worth it, comparing Scribbl to other bot-free note-takers like Tactiq or Granola, or wondering why Scribbl only works on Google Meet and when Zoom and Teams support is coming. Do NOT use for comparing AI note-takers across all platforms (use /sales-note-taker) or reviewing a sales call for coaching (use /sales-call-review).

Meeting.ai platform help — AI meeting notes with visual mind maps, 30+ language transcription with strong Southeast Asian accent support, speaker identification, Ask AI post-meeting Q&A, and multi-format export. Use when setting up Meeting.ai for Zoom, Google Meet, or Teams meetings, Meeting.ai mind map notes not displaying correctly or looking messy, choosing between Meeting.ai and Fathom or Fireflies or Otter for visual meeting notes, Meeting.ai transcription accuracy issues with accents or multiple languages, Meeting.ai export options or sharing meeting notes with teammates, or understanding Meeting.ai pricing and free trial limits. Do NOT use for comparing all AI note-takers (use /sales-note-taker) or reviewing a call for coaching (use /sales-call-review).

SaaSHunt platform help — AI-powered SaaS discovery directory with free dofollow backlinks (DR49). Covers submission process (download Excel template, fill out product details, upload for review), listing categories (HR, CRM, Accounting, ERP, Marketing, PM, Risk Management, Retail/POS), AI-powered software matching, comparison tools, demo booking for vendors, and Pro plans for enhanced visibility (~$49/mo internationally). Use when your SaaS product needs more directory visibility, you want a free dofollow backlink from a DR49 domain, or your SaaSHunt listing isn't standing out against competitors. Do NOT use for multi-directory launch strategy (use /sales-launch-directory). Do NOT use for Product Hunt launches (use /sales-producthunt).

Inspects deal health, map stakeholders, identify risks, and recommend next actions. Use when a deal feels stuck or at risk, you're not sure who the real decision-maker is, champion seems weak or disengaged, MEDDPICC gaps are unclear, a deal review is coming up and you need to prep, or you can't tell if a deal will actually close. Do NOT use for portfolio-level pipeline management (use /sales-pipeline), revenue forecasting (use /sales-forecast), or reviewing a specific sales call (use /sales-call-review).

This skill should be used when a decision is ready to become an ADR and the user wants co-thinking rather than template filler. PROACTIVELY activate on "draft the ADR", "write up the decision", "co-think this ADR", "challenge my reasoning", "ADR for X", "MADR for X", "Y-statement for X", "we decided to use X", "co-draft", "ADR drafting", or "scripted push-back." Provides: seven-phase ADR drafting, one-question turns, failure-mode pressure test, and self-critique against the ADR-is-NOT checklist.

PowerShell 7.5/7.6 features and enhancements. PROACTIVELY activate for: (1) PowerShell 7.5 stable features, (2) PowerShell 7.6 preview features, (3) ConvertTo-CliXml/ConvertFrom-CliXml, (4) Test-Path -OlderThan/-NewerThan, (5) += operator optimization (8x-16x faster), (6) PSResourceGet 1.1.1/1.2.0, (7) Get-Clipboard -Delimiter, (8) Get-Command -ExcludeModule, (9) DSC v3 resources, (10) .NET 9/.NET 10 integration. Provides: Latest cmdlet usage, performance benchmarks, migration patterns.

This skill should be used when the user asks to evaluate, validate, compare, explain, or debug model performance. PROACTIVELY activate for: (1) metrics selection for classification, regression, ranking, NLP, CV, recommender, forecasting, and generative AI, (2) train/validation/test splits, cross-validation, grouped or time-series validation, (3) confusion matrices, ROC/PR curves, calibration, thresholds, error analysis, (4) ablation studies, statistical significance, confidence intervals, bootstrap tests, (5) bias, fairness, explainability, robustness, leakage detection. Provides: rigorous evaluation methodology and production-readiness checks.

Kaggle runtime environment, paths, accelerators, and reproducibility. PROACTIVELY activate for: (1) `/kaggle/input` path errors, (2) `/kaggle/working` output placement, (3) local vs Kaggle notebook behavior, (4) GPU/TPU/accelerator selection, (5) internet enablement, (6) package/version pinning, (7) memory cleanup and timeout issues, (8) DEBUG flags for fast runs, (9) Kaggle Secrets usage guidance, (10) quota-consuming runtime settings. Provides: path conventions, runtime checklist, accelerator IDs, reproducibility patterns, and resource safeguards.

Kaggle `kernel-metadata.json` setup and repair. PROACTIVELY activate for: (1) creating kernel-metadata.json, (2) fixing metadata validation errors, (3) setting `id`, `title`, `code_file`, language, or kernel type, (4) configuring private/public, internet, GPU, or accelerator behavior, (5) attaching dataset_sources, competition_sources, kernel_sources, or model_sources, (6) preparing metadata before `kaggle kernels push`, (7) converting script/notebook metadata. Provides: schema checklist, valid fields, source arrays, defaults, and push-readiness review.

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology evaluation tools, and ADR templates. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.

Write competitive research proposals for NSF, NIH, DOE, and DARPA. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

Senior Risk Management specialist for medical device companies implementing ISO 14971 risk management throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use for risk management planning, risk assessments, risk control verification, and risk management file maintenance.

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

Automatically suggest tests for new functions and components. Use when new code is written, functions added, or user mentions testing. Creates test scaffolding with Jest, Vitest, Pytest patterns. Triggers on new functions, components, test requests, testing mentions.

Reviews documentation for factual accuracy

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding

Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

Address PR review comments and resolve threads. Use when CHANGES_REQUESTED is set, working through unresolved review threads, or replying to reviewer feedback.

Universal linter that auto-detects ruff/eslint/clippy/gofmt for the project language. Use when linting code, auto-fixing, formatting, or running pre-commit checks.

Debug K8s pods/nodes with kubectl debug — ephemeral containers, pod copying, debug profiles, interactive sessions. Use when the user mentions kubectl debug or debugging pods.

Detect test smells, overmocking, flaky tests, and coverage issues. Use when reviewing tests, improving test quality, or analyzing test effectiveness and reliability.

Derive test regression plans from git history by finding commits lacking tests. Use when finding untested bug fixes, coverage gaps, or generating a test backlog.

Debug Helm failures — template errors, dry-run, YAML parse errors, value type errors, resource conflicts. Use when the user mentions Helm errors or template rendering issues.

Recover from failed Helm deployments — rollback, fix stuck states (pending-install/upgrade), atomic deployments. Use when the user mentions rollback, failed Helm upgrade, or stuck releases.

Test frameworks: Vitest, Jest, pytest, cargo-nextest. Use when setting up test infrastructure, migrating to a modern framework, or validating coverage config.

EditorConfig and VS Code workspace settings for team consistency. Use when setting up format-on-save, recommended extensions, or debug configurations.

Mutation testing with Stryker (TS/JS) and mutmut (Python). Use when finding weak tests that pass on mutated code, or improving test quality through mutation analysis.

Build a persistent knowledge graph of your codebase so Claude reads only what matters — up to 49x fewer tokens on coding tasks.

Makefile with standard targets (help, test, build, clean, lint). Use when setting up a Makefile, auditing missing targets, or adding language-specific targets.

Backup-first skill for inspecting, archiving, and maintaining local Codex state to keep it fast, clean, and recoverable.

Resolve merge conflicts file-by-file. Use when a merge/rebase has conflicts, a PR can't merge, "fix conflicts" is requested, or branches have diverged.

Process GitHub issues end-to-end with TDD and parallel work. Use when asked to work on an issue, fix issue #N, pick issues to tackle, or batch-process several.

Sync docs with actual skills, commands, and agents. Use when docs are out of sync, updating the skill catalog, or regenerating command reference to fix mismatches.

Evaluate a skill by running test cases and grading results. Use when testing whether a skill produces correct guidance, validating improvements, or benchmarking before release.

Git branch naming conventions — type prefixes (feat/fix/chore), issue linking, kebab-case. Use when creating branches or setting up repo conventions.

Multi-phase refactoring with checkpoint files that survive context limits. Use when refactoring spans 10+ files, needs phased rollout, or risks running out of context mid-session.

Analyze test quality: smells, empty assertions, flaky patterns, coverage gaps. Use when tests are unreliable, coverage is misleading, or after major refactors.

Automated TDD test-fix-refactor cycle until tests pass. Use when looping on failing tests, running a TDD cycle, or driving RED/GREEN/REFACTOR until green.

Run one test file fail-fast for rapid TDD — Playwright, Vitest, Jest, pytest, cargo, go test. Use when iterating on a failing spec, headed/debug mode, or serial WebGL tests.

Pre-work validation before implementation. Use when starting an issue or fix to verify remote state, check for existing PRs, and detect branch conflicts before coding.

Detect dead code, unused exports, unreachable branches, and orphaned files. Use when reducing maintenance burden, cleaning up after refactors, or auditing codebase health.

Refactor toward pure functions, immutability, composition. Use when extracting pure functions, removing side effects, replacing loops with map/filter/reduce, or separating I/O.

Repo maintenance — gc, branch pruning, stash cleanup, fsck. Use when asked to clean up the repo, run git gc, delete merged branches, prune stashes, or shrink .git.

Run complete test suite in pyramid order — unit, integration, E2E. Use when running all tests before a PR, generating coverage reports, or doing pre-commit verification.

Auto-select test tiers based on change scope — unit for small, full suite for large. Use when running tests, discussing testing strategy, or after code modifications.

Offline YAML frontmatter maintenance for Obsidian notes. Use when stripping legacy `id:`, cleaning Templater markers, or fixing bare emoji tags.

Bun debugger via --inspect. Use when the user wants to debug a TS/JS file interactively, break at first line, wait for attach, or debug tests with --inspect-brk.

Run fast unit tests only, skip slow/integration/E2E. Use when checking units after a change, running affected tests since last commit, watch mode TDD, or sub-30s feedback.

Show cached test status without re-running. Use when checking test health, standup status, coverage summary, history, or identifying flaky tests from recent runs.

Universal test runner auto-detecting pytest, vitest, jest, cargo, go test. Use when running tests, targeting a file/pattern, running with coverage, or watch-mode dev loops.