Code Review
Automated code review and analysis
reviewing-skills
by taisukeoe
Review skill files for best practices compliance (naming, description, structure, size). Use when checking SKILL.md quality or getting feedback before publishing. Static analysis only - does NOT execute the skill.
hardcoded-credentials
by tangjunyi23
Hardcoded credential and backdoor hunting in IoT firmware. Use when searching for default passwords, API keys, private keys, certificates, debug accounts, hidden backdoor accounts, or embedded secrets in firmware filesystems and binaries. Triggers on credential hunting, password discovery, secret scanning, or backdoor detection tasks.
data-migration-expert
by carmandale
Validates data migrations, backfills, and production data transformations against reality. Use when PRs involve ID mappings, column renames, enum conversions, or schema changes.
claude-agent-agent-sdk-dev-agent-sdk-verifier-py
by monkey1sai
Converted from Claude plugin agent "agent-sdk-verifier-py" (agent-sdk-dev).
project-coordinator
by violetio
Project coordination and task management
claude-command-commit-commands-commit-push-pr
by monkey1sai
Converted from Claude plugin command "commit-push-pr" (commit-commands).
code-review
by plutowang
Use when explicitly asked to review a git branch, Pull Request (PR), Merge Request (MR), or perform a pre-merge review. Do not use for inline code critiques.
leadership-sync
by jforksy
Cross-functional leadership alignment - synthesizes CMO, CFO, CPO, and CTO perspectives into unified strategic output
gtm-deal-intel
by jforksy
Analyze deal conversations (transcripts, notes, emails), score opportunities, extract competitive intel, and feed insights back upstream
rtos-analysis
by tangjunyi23
Real-Time Operating System vulnerability analysis for embedded devices running FreeRTOS, VxWorks, ThreadX, eCos, and other RTOS platforms
sk
by lambdamechanic
"How to use the repo-scoped sk CLI to manage Claude Skills in this codebase."
unity-debug-deep
by cuozg
Exhaustive multi-angle Unity bug analysis — read-only investigation across lifecycle, threading, state, data flow, and edge cases. Produces a structured report. Triggers — 'deep debug', 'analyze this bug', 'exhaustive analysis', 'debug report', 'root cause analysis'.
extensibility-advisor
by squirrelsoft-dev
Advises on choosing the right Claude Code extensibility approach (Skills, Commands, Subagents, Hooks, Plugins, MCP, Output Styles). Activates when user discusses extending Claude Code, creating automation, or is unsure which feature to use. Analyzes use cases and recommends appropriate solutions with trade-off explanations. Use when user mentions "should I use", "what's the best way", "skill or command", "which approach", or discusses extensibility options.
Shopify Workflow & Tools
by sarojpunde
Shopify CLI commands, development workflow, and essential tools for theme development
git-commit
by AnthemFlynn
Help users write professional git commit messages following Conventional Commits. Use when users ask about commits, need help writing commit messages, want to validate commit format, ask about git message conventions, or use slash commands like /commit, /validate, /changelog, /version.
simplify-code
by SebastiaanWouters
Simplify and refine code. Only trigger on /simplify-code.
adynato-github
by adynato
GitHub workflow conventions for Adynato projects. Covers creating PRs with gh CLI, writing thorough descriptions, and using stacked PRs for large deliverables. Use when creating pull requests, managing branches, or breaking down large features.
ai-readiness-audit
by cartoonitunes
Audit any website for AI agent readiness. Check llms.txt, MCP servers, structured data, semantic HTML, meta quality, and more. Use when optimizing a site for AI agents, checking AI discoverability, or preparing for AI search engines.
simplify
by ian-pascoe
Simplify and refine recently modified code for clarity and consistency. Use after writing code to improve readability without changing functionality.
ai-lingo
by sunnypatneedi
Meta-skill that maps cognitive mode-switch words to appropriate thinking behaviors and skills. AUTO-INVOKE when user uses these trigger patterns: - Depth: "rigorous", "first-principles", "mechanistic", "axiomatic", "falsifiable", "steelman", "non-trivial", "exhaustive", "load-bearing", "dispositive", "ultra think hard" - Reframe: "reimagine", "orthogonal", "contrarian", "subversive", "invert", "counterfactual", "zero-based", "provocative", "transmute", "reframe" - Precision: "probabilities", "bounded", "monotonic", "asymptotic", "invariant", "order of magnitude", "sensitivity analysis", "convex", "distribution", "marginal", "dimensionality" - Tradeoff: "sacrifice", "irreversible", "binding constraint", "pareto", "second-order", "opportunity cost", "regret minimization", "non-negotiable", "asymmetric" - Quality: "elegant", "idiomatic", "canonical", "production-grade", "battle-tested", "minimalist", "composable", "tasteful", "crisp" - Systems: "emergent", "cascading", "equilibrium", "phase transition", "feedback loop", "attractor", "entropy" - Epistemic: "Bayesian", "calibrated", "crux", "pre-mortem", "adversarial", "sparse", "steel-thread", "epistemic humility", "signal-to-noise"
mungers-lattice
by hexbee
Multidisciplinary analytical engine using Charlie Munger's latticework of mental models. Applies cross-disciplinary thinking (math, physics, biology, psychology, economics) to dissect life and business decisions. Use when user presents a decision problem, investment question, or complex analysis request requiring deep rational analysis.
eld-ground-pr-review
by CAPHTECH
Deprecated: /eld-ground review を使用してください。 このスキルは後方互換のためのエイリアスです。すべての呼び出しは /eld-ground review に転送されます。
disposable-autopsy
by CAPHTECH
Analyze a disposable prototype across 10 quality axes using static analysis, test results, and Codex MCP triangulation. Produces structured autopsy report with scored findings and recommendations. Part of H-DGM cycle. Use after disposable-spike completes.
honest-code-review
by kunickiaj
Gordon Ramsay-style brutally honest persona for direct, profane, theatrical criticism. Use when user asks for Gordon Ramsay mode, no-snowflake mode, unfiltered/harsh/direct feedback, code review, architecture review, or intense venting.