Claude Skills by charlieviettq

Pre-landing PR review. Analyzes diff against the base branch for SQL

Restore working context saved earlier by /context-save. Loads the most

Save working context. Captures git state, decisions made, and remaining

Manage project learnings. Review, search, prune, and export what gstack

'Set up gbrain for this coding agent: install the CLI, initialize a local

'Keep gbrain current with this repo''s code and refresh agent search

Post-ship documentation update. Reads all project docs, cross-references

'Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies

Read-only queue dashboard for workspace-aware ship. Shows which VERSION

'Configure deployment settings for /land-and-deploy. Detects your deploy

'Ship workflow: detect + merge base branch, run tests, review diff, bump

'Design consultation: understands your product, researches the landscape,

'Design finalization: generates production-quality Pretext-native HTML/CSS.

'Designer''s eye QA: finds visual inconsistency, spacing issues, hierarchy

'Design shotgun: generate multiple AI design variants, open a comparison

'Auto-review pipeline — reads the full CEO, design, eng, and DX review

'Live developer experience audit. Uses the browse tool to actually TEST

'CEO/founder-mode plan review. Rethink the problem, find the 10-star

Designer's eye plan review — interactive, like CEO and Eng review. Rates

'Interactive developer experience plan review. Explores developer personas,

'Eng manager-mode plan review. Lock in the execution plan — architecture,

'Self-tuning question sensitivity + developer psychographic for gstack

Use when asked to review a plan, challenge a proposal, run a CEO review,

Use when asked to debug, fix a bug, investigate an error, or do root

Use when asked to brainstorm, evaluate whether an idea is worth building,

Weekly engineering retrospective. Analyzes commit history, work patterns,

'Pair a remote AI agent with your browser. One command generates a setup

Scrape the Hacker News front page (titles, points, comment counts).

Pull data from a web page. First call on a new intent prototypes the

Codify the most recent successful /scrape flow into a permanent browser-skill

Safety guardrails for destructive commands. Warns before rm -rf, DROP

'Chief Security Officer mode. Infrastructure-first security audit: secrets

Restrict file edits to a specific directory for the session. Blocks Edit

'Full safety mode: destructive command warnings + directory-scoped edits.

Clear the freeze boundary set by /freeze, allowing edits to all directories

'Upgrade gstack to the latest version. Detects global vs vendored install,

'YC Office Hours — two modes. Startup mode: six forcing questions that

'Launch GStack Browser — AI-controlled Chromium with the sidebar extension

'Weekly engineering retrospective. Analyzes commit history, work patterns,

Import cookies from your real Chromium browser into the headless browse

Analyze Meta (Facebook/Instagram) ad performance—campaign structure, breakdowns, marginal vs average CPA, and scaling decisions. Analytical workflow only, not financial or legal advice. Triggers: "Meta ads", "Facebook ads", "CPA", "ROAS", "ad account", "Breakdown Effect".

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to...

Self-learning system that captures corrections, discovers workflow patterns, and syncs learnings to skills and rules. Use when ending a session, after corrections, or when the user wants to formalize learnings (v1.1.3).

Convert the current phase doc into an ordered execution plan and propose work packages (spec-first + tiered tests), including RTL/Hebrew checks.

Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.

Prepare iOS App Store and Google Play submissions—metadata, assets, compliance checks, and release checklist. Use before store upload or review submission. Triggers: "App Store", "Play Store", "store submission", "app review", "release checklist".

Set up iOS TestFlight delivery via GitHub Actions—build, sign, upload—with secret hygiene and no auto-push. Triggers: "TestFlight", "iOS CI", "Fastlane GitHub Actions", "beta release", "App Store Connect upload".

Measure, identify bottlenecks, fix, verify, and guard performance regressions. Use for web vitals, slow APIs, heavy notebooks/pipelines, or video/render workloads. Triggers: "performance", "optimize", "slow", "latency", "bundle size", "profiling".