Code Review
Automated code review and analysis
Semantic Version Advisor
by alienfast
Advises on semantic version bumps and classifies version changes according to semver rules. Use when determining version numbers, analyzing dependency updates, or classifying version changes as MAJOR, MINOR, or PATCH.
Brand Name Comparison
by MaxGhenis
Use this skill when the user wants to compare multiple brand name fates side-by-side to divine which is destined for success.
us-5x-stock-research
by hwjxp
Use when the user wants to study, screen, or review U.S. stocks with potential to become 5x to 10x multi-baggers. Supports regime analysis, theme selection, leader identification, catalyst mapping, market-cap and float filters, technical entry review, and post-mortem comparison against historical U.S. 5x winners. Also use when the user wants a repeatable investing framework or stock-picking checklist focused on major winners rather than broad diversification.
start
by alienfast
Start working on a Linear issue — check blockers, assign, move to In Progress, create branch, plan implementation, execute with checkpoint updates. Use when the user says 'start issue', 'work on PL-XX', 'begin PL-XX', or invokes /start.
email-editorial
by tonyflo79
Systematic quality review and revision of the complete assembled email campaign. Use as the final quality gate after E3 has assembled the full sequence. Scores every email against the EMAIL-QUALITY-RUBRIC, identifies structural and voice issues, applies revisions (full Arena for critical/major issues, direct fix for minor/cosmetic), rescores to verify improvement, and packages the final revised campaign. Every email must score 7.5+ to pass. Trigger when users mention email review, editorial pass, quality check, email polish, campaign revision, or finalizing an email campaign. Requires E3 assembled-sequence.yaml output.
data-analyze-refined
by gzsteven666
"Use when a user provides tabular business data (Excel/CSV) and wants market-facing, non-academic insights with unclear analysis direction, requiring automatic metric/dimension selection and actionable outputs."
pr-create
by gentamura
Use this skill to create a pull request from current local changes. Invoke when the user asks to create a branch, commit, push, and open a PR.
executing-plans
by ederheisler
Use when you have a written implementation plan to execute in a separate session with review checkpoints
csv-data-summary
by JetSquirrel
Analyzes CSV files, generates comprehensive summary statistics, identifies data patterns, and creates visualizations using Python and pandas. Automatically adapts analysis based on data type (sales, customer, financial, survey, operational).
pr-review
by Tmeister
Review a GitHub pull request, run targeted checks, and provide a decision-ready summary.
pr-summary-cn
by VitaDynamics
Generate concise Chinese PR summary from git changes
tapforce-pnpm
by tapforce
Best practices for using pnpm ^10.0.0 in Node.js projects. Use when working with Node.js-based projects.
next
by ddaanet
Find pending work in secondary locations. Triggers on "what's next?", "any pending work?", or when no pending work exists in already-loaded context. Checks shelf, todo.md, ROADMAP.md.
verifying-changelog-in-framework
by Seika139
"外部公開を想定したフレームワークにある CHANGELOG.md の内容が適切かどうかを確認するスキルです。CHANGELOG.md を更新する際、またはレビューする際に利用します。"
unsafe-checker
by lywa1998
"Use when reviewing unsafe code or writing FFI. Keywords: unsafe, raw pointer, FFI, extern, transmute, *mut, *const, union, #[repr(C)], libc, std::ffi, MaybeUninit, NonNull, PhantomData, Send, Sync, SAFETY comment, soundness, undefined behavior, UB, how to call C functions, safe wrapper for unsafe code, when is unsafe necessary, memory layout, bindgen, cbindgen, CString, CStr, invariant, 安全抽象, 裸指针, 外部函数接口, 内存布局, 不安全代码, FFI 绑定, 未定义行为"
Ravenclaw Operations Skill
by ibrahimq21
Documentation: See README.md in Ravenclaw repo
fp-check
by aleister1102
"Systematically verifies suspected security bugs to eliminate false positives. Produces TRUE POSITIVE or FALSE POSITIVE verdicts with documented evidence for each bug."
issue-triage
by aleister1102
Use when triaging GitHub security issues — fetch issues by number or range, classify as false positive or true positive, assess bypass potential, and then label and close each issue with a brief comment. Triggers on "validate issue N", "triage issues 189-199", "check if issue is exploitable", "close false positive issues".
typescript-master
by Tomlord1122
TypeScript language expert specializing in type system, generics, conditional types, and advanced patterns. Use when writing complex types, debugging type errors, or designing type-safe APIs.
plan-review
by rozwer
Review a phase plan interactively, explaining each task and asking for confirmation.
gh-pr-review
by squirrel289
Interact with GitHub pull requests for review, comment management, and merge operations
gh-pr-create
by AutoFor
作業完了時に GitHub PR を作成し、ブランチ名から Issue を検出して紐付けを行う。ユーザーが「作業が完了した」「PRを作成したい」と言ったときに使用します。
commit-work
by VisualxIntelligence
"Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits."
fortify-scsast
by crance
ScanCentral SAST guide for MCP tools. Package source code, run SAST scans on ScanCentral sensors, monitor scan progress, and retrieve results from SSC.