Results for “pr-review”

Audit, write, or revise Architecture Decision Records (ADRs), including the decision of whether one is warranted. Use when an architecturally significant decision needs recording, when reviewing an existing ADR collection, or when adding ADRs to a project that has none. Detects existing template (Nygard or MADR) and defaults to Nygard for new repos. Gates comparison ADRs through a decompose-and-verify interview before drafting.

Drafts a Petition for Writ of Certiorari to the U.S. Supreme Court under Rules 10, 13, 14, and 33. Enforces Rule 10 criteria (circuit splits, precedent conflicts, important federal questions), jurisdictional verification under 28 U.S.C. §§ 1254/1257, timeliness, document structure, and booklet formatting. Use when seeking discretionary Supreme Court review, filing a cert petition, or drafting a writ of certiorari.

Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.

Use for writing, reviewing, debugging, testing, or diagnosing Python Bayesian models built directly with PyMC, including Model, coords/dims, Data, random variables, potentials, posterior sampling, prior/posterior predictive checks, and InferenceData output. Trigger on model geometry, shape errors, divergences, sampler choice, mutable prediction data, and probabilistic validation. Do not use for Bambi formula models, NumPyro/JAX programs, ArviZ-only analysis of existing draws, deterministic optimization, or general statistics without PyMC code.

Use to assemble a fair, evidence-backed coaching pack for a support agent's one-to-one from QA evaluations and conversation history. Trigger for "prepare a coaching session for X", "what areas does X need to improve", "areas of markdown for this agent", "what coaching opportunities stand out", "build a coaching agenda from these tickets", or preparing a weekly or monthly agent review.

Evaluates Claude Agent Skills on 10 quality axes with letter grades (A+ through F) and specific improvement recommendations. Use when auditing a skill, comparing skills, prioritizing improvements, or performing quality control on a skill library. Activate on "grade skill", "evaluate skill", "skill quality", "skill audit", "skill review", "rate skill". NOT for creating skills (use skill-architect), grading code quality, or evaluating non-skill documents.

Differentiates aldosterone-producing adenoma from idiopathic adrenal hyperplasia based on 18-hydroxycorticosterone levels, with APA patients generally having levels >100 ng/dL at 8:00 a.m. and IAH patients usually having levels <100 ng/dL. Use when reviewing 18-OHB test results to help subtype PA; triggers include 18-OHB >100 ng/dL (suggesting APA) or <100 ng/dL (suggesting IAH).

Use for writing, reviewing, debugging, testing, or diagnosing Bayesian regression and hierarchical models built with Bambi formulas, Model, Family/Likelihood/Link, Prior, fit, prior predictive, and predict. Trigger on common versus group-specific terms, categorical coding, family/link choice, automatic prior scaling, missing rows, PyMC backend settings, and InferenceData predictions. Do not use for hand-built PyMC graphs, NumPyro programs, ArviZ-only analysis of existing draws, frequentist statsmodels formulas, or generic pandas work.

Simplify application code for clarity without changing behavior — refactor after tests pass, reduce nesting and duplication, match project conventions. Load when refactoring for readability, cleaning up after a feature ships, or when code review flags complexity. Also triggers on "simplify this code", "code simplification", "make this easier to read", "reduce complexity", "refactor for clarity". Not for compress/split/prune-skill (skill-library files). Pairs with technical-debt-audit.

Use this skill when the user asks specifically about preparing for the New Entrant Safety Audit (NESA) under 49 CFR 385 Subpart D — different from a Compliance Review. Covers what auditors look at, the 18-month window, automatic failure conditions, the 60-day fix window, what to NOT do, and how to convert from "new entrant" to permanent authority. Cite 49 CFR 385.301-321.

Use when designing a new system, choosing between architectural patterns, planning how components will connect, evaluating scalability and reliability trade-offs, or reviewing an existing system for structural problems. For system design, service boundaries, database design, API structure, monolith vs microservices decisions, and architecture decision records (ADRs). Activate when user says "how should I structure this", "design the system", "is this architecture right", or "plan the backend".

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use `improve-animations` or `review-animations` instead. Source: github.com/emilkowalski/skills.

Review an open GitHub issue for a selected repository against the current codebase, then either close it as already implemented with an evidence comment, label it needs clarification with an explanatory comment, or create a fleshed-out Jira story in the requested board/project when the remaining work is clear. Use when triaging GitHub issues into Jira backlog work or closing stale implemented GitHub issues.

Security vulnerability scanner and OWASP compliance auditor for codebases. Dependency scanning (npm audit, pip-audit), secret detection (high-entropy strings, API keys), SAST for injection/XSS vulnerabilities, and security posture reports. Activate on 'security audit', 'vulnerability scan', 'OWASP', 'secret detection', 'dependency check', 'CVE', 'security review', 'penetration testing prep'. NOT for runtime WAF configuration (use infrastructure tools), network security/firewalls, or compliance certifications like SOC2/HIPAA (legal/organizational).

Designs REST and GraphQL APIs following production best practices for resource naming, error handling, versioning, authentication, and documentation. Use this skill when designing new API endpoints, reviewing API contracts, implementing GraphQL schemas, establishing API conventions for a project, or writing API documentation. Apply when creating any route in Next.js API routes or route handlers, any Supabase Edge Function, or any backend endpoint — even if it starts small, these patterns prevent painful rewrites later.

Produces durable, structured documentation in codebases with sparse docs — readable by humans and agents alike. Two invocation modes — `survey` proposes a doc plan; `draft` writes one specific doc end-to-end with a factcheck-then-persona review gate. Triggered by phrases like "doxcavate this repo", "doxcavate the X", "doxcavate `runbook-deploy`", "what should be documented?", "document this code", "write a how-it-works for X", or any request to inventory or write project documentation.

Use for writing, reviewing, debugging, or testing Python code that inspects, edits, extracts, validates, preserves, or generates Excel .xlsx or .xlsm workbooks. Trigger on workbook contracts, formulas and cached values, Excel Tables, defined names, OOXML parts, types and precision, macros, charts, hidden sheets, external links, and semantic workbook verification. Do not use for CSV-only work, dataframe computation with no workbook boundary, Excel UI automation, recalculation, connection refresh, or macro execution.

Drafts and revises academic papers through a 12-agent pipeline with hardened LaTeX output (apa7 document class, justified text, table column-width formula, centered bilingual abstracts, standardized font stack, PDF compiled from LaTeX), supporting IMRaD, literature review, theoretical, case study, policy brief, and conference paper structures, APA 7.0 (default), Chicago, MLA, IEEE, and Vancouver citation formats, bilingual zh-TW plus EN abstracts, and multi-format output (LaTeX, DOCX, PDF, Markdown). Use when the request mentions write paper, academic paper, paper outline, write abstract, revise paper, check citations, convert to LaTeX, guide my paper, parse reviews, revision roadmap, or 寫論文, 學術論文, 論文大綱, 寫摘要, 修改論文, 檢查引用, 引導我寫論文, 帶我規劃論文, 逐章規劃, 論文架構, 審查意見, 修訂路線圖. Its citation-check mode formats and inserts citations while drafting; for a standalone anti-hallucination check that cited references actually exist prefer alterlab-citation-verifier instead. Part of the AlterLab Academic Skills suite.

Determines if primary aldosteronism is confirmed based on upright plasma aldosterone ≤6 ng/dL (170 nmol/L) on day 4 at 10 AM of fludrocortisone suppression test, provided plasma renin activity ≥1 ng/mL/h and plasma cortisol concentration lower than the 7 AM value to exclude ACTH confounding. Use when reviewing FST results to diagnose PA; triggers include "FST", "upright aldosterone ≤6 ng/dL", "PRA ≥1 ng/mL/h", and "cortisol drop".

Supabase-first database schema design for Nick's app stack. Generate production-ready Postgres schemas, Supabase SQL migrations, RLS policies, TypeScript types, seed data, role-aware access patterns, and schema checklists from plain English requirements. Use when starting any new project database, designing or reviewing schemas, adding tables, planning migrations, or turning product requirements into Supabase-ready data models. Bias toward product-led schema design, MVP discipline, core-workflow-first modeling, and avoiding premature table/role sprawl.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer

Designs the contract for an API change inside one codebase — a component's props, a function surface, URL or query parameters, an event payload, or a module boundary — through a discovery pass, an options document with one recommendation, a question round, and an adversarial validation round, with every element of the contract justified from one stated goal. Use when you want to design, shape, decide, or nail down an interface, contract, signature, or API change for a capability you can already describe, sized for roughly one pull request. Produces a design document and changes no code. Does not specify what a feature should do — use plan-a-feature. Does not plan delivery or sequencing — use plan-implementation. Does not assess the architecture of existing code — use architectural-analysis. Does not write the code — use tdd. Does not restructure existing code — use refactor. Runs its rounds without pausing for review; to review each round as it lands, use pairing.

Best practices and patterns for C# async/await programming including Task and ValueTask usage, CancellationToken propagation, IAsyncDisposable and await using, ConfigureAwait, async streams (IAsyncEnumerable), parallel task execution, and common pitfalls like deadlocks and async void. Use this skill whenever writing, reviewing, or refactoring asynchronous C# code — including when the user mentions async methods, Task-returning APIs, cancellation, deadlocks, blocking on async code, or resource disposal in async contexts, even if they do not explicitly say "async best practices."

Expert copy editor for Quarto (.qmd) files. Checks grammar, spelling, punctuation, and academic writing quality. Produces a structured markdown report organized by document section — never modifies the source file. Use when asked to proofread, check grammar, fix typos, or review prose in a .qmd document. For APSA style rules (numbers, citations, capitalization, abbreviations, neutral language), use the apsa-style skill instead. Supports an optional output-file argument and an optional @sec-label argument to restrict checking to one section.

Single entrypoint for taw-kit. User types `/taw <anything in VN or EN>` — this skill classifies the intent (BUILD / FIX / SHIP / MAINTAIN / ADVISOR) and loads the matching branch file to execute. Replaces the old one-command-per-task model (/taw-new, /taw-add, /taw-fix, /taw-deploy, /taw-security) with a single unified command. Supports dev workflows out of the box: test, upgrade, clean, perf, rollback, refactor, types, seed, review, stack-swap, status, and ADVISOR group (analyze, suggest, coverage, adversarial, scope-check) for opinionated review of existing code. User-visible strings match the user's input language (Vietnamese by default for VN users). Two modes: SAFE (default — clarify + approval, max 1 round-trip) and YOLO (skip gates, smart defaults — for demos/power users). YOLO triggers: prose contains `yolo`, `nhanh nha`, `lam luon`, `khoi hoi`, `auto`, or args start with `yolo`. Trigger phrases (EN + VN) — broad match so user can keep typing plain prose without re-invoking /taw every turn. Grouped by

For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and perform a retrospective on a chosen run -- what went well, what failed, process suggestions, quality of effect design, breakpoint patterns -- mirroring the /babysitter:retrospect workflow but applied to an external repo. Invoke when asked to "retrospect on repo X's run", "analyze how someone else used babysitter", or "review an external babysitter run".

Intelligent inbox triage that connects to Gmail or Outlook, scores emails by importance (0-100) using sender recognition, urgency keywords, thread depth, time sensitivity, and business relevance, categorizes into Urgent/Important/Routine/Archive, and generates reply suggestions for top priority items. Use when the user wants to check email, review inbox, triage messages, see what's urgent, or get reply suggestions. Triggers on check email, inbox triage, what's important, email summary, unread emails, priority inbox.

Use for writing, reviewing, debugging, testing, or optimizing Python code that inspects, edits, extracts, validates, preserves, or generates Microsoft PowerPoint Open XML presentations, primarily .pptx, using python-pptx, PresentationML/OOXML, Pillow, or supporting Python libraries. Trigger on slides, masters, layouts, placeholders, shapes, text, pictures, tables, charts, notes, themes, hyperlinks, embedded objects, macros, preservation, geometry, rendering verification, and presentation package inspection. Do not use for .ppt binary files, PowerPoint UI automation, VBA execution, slideshow execution, or presentation advice with no Python or file boundary.

| Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the standard chain with a PR exit. Trigger with /hyperflow:issue, "work on issue #N", "fix this issue <url>", "implement this issue", "triage issue #N and raise a PR".

Interactive project learning coach via interview-style Q&A. Reads codebase and docs, dynamically generates interview questions per knowledge domain and sub-topic, conducts up to 4 follow-up rounds, scores answers, provides learning guidance with code/doc references, and persists progress. 10 domains × 3-5 sub-topics = 45 knowledge points for comprehensive interview coverage. Use when user says '学习项目', '了解项目', '检验项目', '项目学习', '面试准备', 'learn project', 'study project', 'review project', 'interview prep', 'knowledge check', or wants to understand/master the project through guided Q&A.

Create structured plans for multi-step tasks -- software features, research workflows, events, study plans, or any goal that benefits from breakdown. Also deepens existing plans with interactive sub-agent review. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a brainstorm doc is ready for planning. Use 'deepen the plan' or 'deepening pass' for the deepening flow. For exploratory requests, prefer ce-brainstorm first.

Unified multi-platform paid media audit with parallel execution. Spawns scored audits for Google Ads, Meta Ads, and Microsoft Ads simultaneously, merges results into a budget-weighted aggregate health score (A-F), adds cross-platform analysis (budget allocation, tracking consistency, creative alignment, attribution overlap), and produces a prioritized action plan. Optionally generates a client-ready deck via pro-deck-builder. Use when the user asks for a full paid media audit, cross-platform review, or multi-channel ad assessment.

Use this skill whenever LMX is used, produced, reviewed, migrated, or modified. This includes composing campaigns, loops, lifecycle emails, or email-message bodies for the Loops editor or Content API. LMX (Loops Markup Language) is the format used for Loops email content. Trigger on phrases like "create a campaign", "generate an email", "write a welcome email", "draft a lifecycle email", "build an email template", "create an onboarding email", "copy this into LMX", "migrate this email", "convert this email to LMX", "design a new Loops email", "use imagegen for a Loops email", "use gpt-image for an LMX reference", "visual reference for a Loops email", "LMX", "Loops email", or any request to produce, copy, migrate, convert, review, or modify email body content intended for Loops. For net-new emails or major visual redesigns, follow this skill's Net-New Email Design Flow before generating or sourcing new visual assets. Source copy, existing HTML, MJML, Markdown, screenshots, and migration instructions do not byp

Interactive project learning coach via interview-style Q&A. Reads codebase and docs, dynamically generates interview questions per knowledge domain and sub-topic, conducts up to 4 follow-up rounds, scores answers, provides learning guidance with code/doc references, and persists progress. 10 domains × 3-5 sub-topics = 45 knowledge points for comprehensive interview coverage. Use when user says '学习项目', '了解项目', '检验项目', '项目学习', '面试准备', 'learn project', 'study project', 'review project', 'interview prep', 'knowledge check', or wants to understand/master the project through guided Q&A.