Review & quality
19,284 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
brycewang-stanford/Awesome-Journal-Skills/SOSP-Skills/skills/sosp-review-process Skill
1,416★ repoUse when reasoning about how a SOSP submission is evaluated — double-blind HotCRP reviewing, staged review rounds, PC-chair-audited conflicts, the pre-PC-meeting author response, the single-track PC meeting where every decision is argued live, notification, and shepherded acceptance outcomes.
brycewang-stanford/Awesome-Journal-Skills/STOC-Skills/skills/stoc-review-process Skill
1,416★ repoUse when reasoning about how a STOC (ACM Symposium on Theory of Computing) submission is evaluated — the SIGACT program-committee model with external subreviewers, HotCRP mechanics, double-blind conflicts, the November-to-February decision arc, and what best-paper designation and rejection each actually mean.
brycewang-stanford/Awesome-Journal-Skills/Scientia-Sinica-Informationis-Skills/skills/ssi-review-process Skill
1,416★ repo当需要理解《中国科学:信息科学》(Scientia Sinica Informationis, SSI) 的审稿流程、校准评审预期、判断作者在各环节的可行动空间时调用。覆盖编辑部初审→编委送外审→外审专家评议→复审→主编/编委会终审的链路、三审三校制度(报道级,以官网为准)、审稿原则(公平公正公开客观)、退修(大修/小修)与录用/退稿决定、90 天未获意见可改投的条款、审稿周期与轮次,以及与英文姊妹刊 Science China Information Sciences 评审的异同。适用于投稿后到录用前的全过程校准。
brycewang-stanford/Awesome-Journal-Skills/SenSys-Skills/skills/sensys-review-process Skill
1,416★ repoUse when interpreting SenSys's two-deadline, self-contained review model — what a first-deadline outcome means, that a reject may return at the second deadline only with a substantive revision and Response to Reviewers, how systems reviewers weigh energy and deployment evidence, and how to classify a notification before drafting a response.
brycewang-stanford/Awesome-Journal-Skills/SoCC-Skills/skills/socc-review-process Skill
1,416★ repoUse when reasoning about how an ACM SoCC submission is evaluated, covering dual-anonymous review, the two-round-per-year model with the no-cross-round-resubmission rule, the author-response (rebuttal) period, the joint SIGMOD+SIGOPS reviewer pool that reads for both systems and data quality, and how SoCC's process differs from OSDI/NSDI/EuroSys.
brycewang-stanford/Awesome-Journal-Skills/Social-Forces-Skills/skills/sf-review-process Skill
1,416★ repoUse to understand how Social Forces (SF) evaluates a manuscript — double-anonymized review via ScholarOne, what expert reviewers weigh (rigor, general significance, theoretical grounding), the typical decision categories, and the journal's reported review timeline. Sets expectations and shapes the paper to survive review; it does not contact editors.
brycewang-stanford/Awesome-Journal-Skills/Social-Psychology-Quarterly-Skills/skills/spq-review-process Skill
1,416★ repoUse to understand how Social Psychology Quarterly (SPQ) evaluates a manuscript — masked (blinded) review, the blinding check that temporarily rejects under-blinded papers, what reviewers from different sociological-social-psychology traditions weigh, and the reject / revise-and-resubmit / accept decision pattern. Sets expectations and shapes the paper to survive review; it does not contact editors.
brycewang-stanford/Awesome-Journal-Skills/Sociological-Theory-Skills/skills/soctheory-review-process Skill
1,416★ repoUse when you need to understand Sociological Theory (ST)'s double-anonymous peer review and interpret a decision letter focused on conceptual novelty and logical soundness. Explains the process and decision types; it does NOT draft the response document (that is soctheory-rebuttal).
brycewang-stanford/Awesome-Journal-Skills/Strategic-Management-Journal-Skills/skills/smj-review-process Skill
1,416★ repoUse when interpreting the Strategic Management Journal (SMJ) review process and a decision letter, and planning the revision strategy. Explains the process and triages the decision; the actual response letter is drafted in smj-rebuttal.
brycewang-stanford/Awesome-Journal-Skills/TACAS-Skills/skills/tacas-review-process Skill
1,416★ repoUse when reasoning about how a TACAS (ETAPS) submission is evaluated, covering the per-category blind model (double-blind research vs single-blind tool/case-study), the single annual PC round with a rebuttal, the parallel mandatory artifact evaluation that feeds tool-paper acceptance, accept/reject decisions, and how TACAS's process differs from CAV's and from a journal's.
brycewang-stanford/Awesome-Journal-Skills/The-Accounting-Review-Skills/skills/tar-review-process Skill
1,416★ repoUse when understanding how The Accounting Review (TAR) review and decisions work, or when reading a TAR decision letter — the editor routing, double-blind two-reviewer model, decision types, and post-publication integrity rules. Explains and interprets the process; it does not draft the revision and response (tar-rebuttal).
brycewang-stanford/Awesome-Journal-Skills/The-Art-Bulletin-Skills/skills/artbull-review-process Skill
1,416★ repoUse to understand how The Art Bulletin evaluates a submission — double-blind peer review, what referees and the editor look for in art-historical work, and the likely decision outcomes. Helps anticipate review; it does not contact editors or simulate a specific referee.
brycewang-stanford/Awesome-Journal-Skills/The-Econometrics-Journal-Skills/skills/ectj-review-process Skill
1,416★ repoUse when interpreting or planning around The Econometrics Journal's one-week editorial screen, editor assignment, three-month decision target, resubmission window, conformance rejection, and replication checks.
brycewang-stanford/Awesome-Journal-Skills/The-Web-Conference-Skills/skills/webconf-artifact-evaluation Skill
1,416★ repoUse when packaging datasets, models, or code for the Web Conference (WWW) Artifacts Available badge or for reviewer scrutiny, covering archival-repository choice, the light-verification bar, web-data licensing and takedown realities, anonymized artifacts during review, and what the badge does and does not certify.
brycewang-stanford/Awesome-Journal-Skills/The-Web-Conference-Skills/skills/webconf-review-process Skill
1,416★ repoUse when reasoning about how the Web Conference (WWW) evaluates papers — track-scoped double-blind review, the rebuttal-to-notification pipeline, how the ten research tracks shape reviewer expectations, main versus companion proceedings outcomes, and what authors can and cannot influence at each stage.
brycewang-stanford/Awesome-Journal-Skills/UAI-Skills/skills/uai-review-process Skill
1,416★ repoUse when reasoning about UAI peer review on OpenReview, including bidding, double-blind evaluation against the correctness, novelty, backing, and clarity criteria, the author-response window, the reviewer-and-area-chair discussion that follows it, decision timing, spotlight versus poster outcomes, and PMLR publication of accepted papers.
brycewang-stanford/Awesome-Journal-Skills/UIST-Skills/skills/uist-review-process Skill
1,416★ repoUse when interpreting the UIST review pipeline — anonymous PC-plus-external review of papers and videos, the rebuttal's role, PC-meeting decisions, conditional acceptance mechanics, reading systems-reviewer psychology, and choosing the demo/poster fallback or resubmission path after a rejection.
brycewang-stanford/Awesome-Journal-Skills/USENIX-Security-Skills/skills/usenixsec-review-process Skill
1,416★ repoUse when reasoning about how a USENIX Security Symposium cycle actually decides — early-reject notifications, multi-round reviewing, the retirement of Major Revision in favor of shepherd-approval acceptances, resubmission restrictions between cycles, and what each notification email means for planning.
brycewang-stanford/Awesome-Journal-Skills/VIS-Skills/skills/vis-author-response Skill
1,416★ repoUse when drafting IEEE VIS author responses across the two-phase review, covering the first-round reviewer discussion, and — distinctively — the conditional-accept second-round revision with its summary-of-changes that maps every required change to a concrete edit and is re-read by the same primary, secondary, and external reviewers under the IEEE TVCG process.
brycewang-stanford/Awesome-Journal-Skills/VIS-Skills/skills/vis-review-process Skill
1,416★ repoUse when reasoning about how an IEEE VIS full-paper submission is evaluated, covering the two-phase review that mirrors IEEE TVCG, the primary/secondary/external (and 2026 student) reviewer roles, the six-area routing through Area Paper Chairs, the conditional-accept second round, and how VIS's journal-integrated process differs from a single accept/reject conference and from CHI/CVPR.
brycewang-stanford/Awesome-Journal-Skills/VLDB-Skills/skills/vldb-review-process Skill
1,416★ repoUse when reasoning about how PVLDB reviewing actually works, covering the rolling monthly pipeline, the roughly six-week review turnaround, the accept/revise/reject outcome space, the one-shot revision's odds, single-blind dynamics, the volume review board, and how a VLDB decision differs from batch-deadline venues.
brycewang-stanford/Awesome-Journal-Skills/WACV-Skills/skills/wacv-review-process Skill
1,416★ repoUse when reasoning about how WACV decides a paper, covering the two-round model, the Round 1 Accept / Revise-and-Resubmit / Reject recommendations, the optional Round 1 rebuttal, the no-rebuttal Round 2, area-chair consolidation, double-blind confidentiality, and where author leverage actually exists across the two rounds.
brycewang-stanford/Awesome-Journal-Skills/WSDM-Skills/skills/wsdm-review-process Skill
1,416★ repoUse when reasoning about how WSDM reviews and decides papers - the hybrid single/double-blind architecture with Associate-Chair metadata visibility, at-least-three PC reviews plus senior PC assessment, the absence of a rebuttal phase, the August-to-October window, and what ~17% selectivity at a single-track venue implies.
brycewang-stanford/Awesome-Journal-Skills/World-Politics-Skills/skills/wp-review-process Skill
1,416★ repoUse to understand how World Politics evaluates a manuscript — triple-blind review with author anonymity preserved through the editorial decision, at least two non-Princeton reviewers and often an editor, a roughly four-month decision target, scope screening, and the APSA human-subjects requirement. Sets expectations and shapes the paper to survive review; it does not contact editors.
brycewang-stanford/Awesome-Journal-Skills/Yale-Law-Journal-Skills/skills/ylj-footnotes-and-cite-check Skill
1,416★ repoUse when running the final footnote-apparatus audit of a The Yale Law Journal (YLJ) piece — verifying every cite exists, is pinpointed, is correct Bluebook form, and actually supports its sentence, in preparation for (or during) the student source-pull. It verifies; it does not construct new cites (ylj-sources-and-bluebook).
brycewang-stanford/Awesome-Journal-Skills/Yale-Law-Journal-Skills/skills/ylj-preemption-check Skill
1,416★ repoUse when verifying that a The Yale Law Journal (YLJ) claim is genuinely novel and not preempted by prior scholarship. It runs the systematic SSRN/Westlaw/HeinOnline search and writes the "what's new" paragraph; it does not draft the thesis (use ylj-thesis-and-contribution).
brycewang-stanford/Awesome-Journal-Skills/Yale-Law-Journal-Skills/skills/ylj-revision-and-editing Skill
1,416★ repoUse when working through The Yale Law Journal (YLJ) post-acceptance editing cycle and answering author queries, or when preparing a shorter YLJ Forum piece. It covers the intensive student edit + the online companion path; it does not run the final cite verification (ylj-footnotes-and-cite-check).
brycewang-stanford/Awesome-Journal-Skills/Yale-Law-Journal-Skills/skills/ylj-student-editor-review Skill
1,416★ repoUse when working with The Yale Law Journal (YLJ) student editors during evaluation and acceptance — the Articles & Essays Committee read, the Notes Development process for student authors, and the source-pull. It explains how the student-edited model works; it does not run the intensive line-edit cycle (ylj-revision-and-editing).
CloudAI-X/claude-workflow-v2/skills/managing-git Skill
1,405★ repoManages Git workflows including branching, commits, and pull requests. Use when working with Git, creating commits, opening PRs, managing branches, resolving conflicts, or when asked about version control best practices.
The same file is in 5 other repositories
first-fluke/oh-my-agent/.agents/skills/oma-docs Skill
1,369★ repoVerify documentation references against the current codebase, propose updates for diff-affected docs, detect i18n translation drift, and lint translated docs for CJK style issues. Use to check if docs still match reality (broken file paths, CLI commands, config keys, env vars, scripts), to surface docs that may need updating after code changes, or to find stale or style-broken translations.
first-fluke/oh-my-agent/.agents/skills/oma-explainer Skill
1,369★ repoTurn a code change (diff, PR, branch, commit range) into a rich, self-contained interactive HTML explainer with Background / Intuition / Code / Quiz sections. Use for explain, walkthrough, code-change explanation, diff/PR/branch explainer requests — 설명서, 해설, コード解説, 代码讲解. Produces a single offline-capable HTML file with diagrams, callouts, and an accessible quiz.
first-fluke/oh-my-agent/.agents/skills/oma-scm Skill
1,369★ repoSCM (software configuration management) and Git: branching, merges, conflicts, worktrees, baselines, audit readiness, plus Conventional Commits and safe staging.
first-fluke/oh-my-agent/benchmarks/runs/oma/.agents/skills/oma-scm Skill
1,369★ repoSCM (software configuration management) and Git — branching, merges, conflicts, worktrees, baselines, audit readiness, plus Conventional Commits and safe staging.
first-fluke/oh-my-agent/generated/agent-skills/oma-docs Skill
1,369★ repoVerify documentation references against the current codebase, propose updates for diff-affected docs, detect i18n translation drift, and lint translated docs for CJK style issues. Use to check if docs still match reality (broken file paths, CLI commands, config keys, env vars, scripts), to surface docs that may need updating after code changes, or to find stale or style-broken translations.
first-fluke/oh-my-agent/generated/agent-skills/oma-scm Skill
1,369★ repoSCM (software configuration management) and Git: branching, merges, conflicts, worktrees, baselines, audit readiness, plus Conventional Commits and safe staging.
gooseworks-ai/goose-skills/skills/ads/capabilities/verify-product-image Skill
1,323★ repoQC gate for a generated static ad image — verify the file opens, matches the requested dimensions, shows the correct product/subject (right shape, colour, label, logo), and has no garbled text or severe artifacts. Records pass/fail/needs-human in verification.md. Used as the final check in the static ad remix flow before shipping.
gooseworks-ai/goose-skills/skills/ads/composites/meta-ad-policy-checker Skill
1,323★ repoPre-flight policy check for Meta ads. Takes ad copy plus advertiser context, resolves and fetches the relevant Meta transparency-center policy pages at runtime, and returns a Pass / Fix Required / Block verdict with cited findings and rewrites.
gooseworks-ai/goose-skills/skills/ads/packs/ugc-video-formats/review-ugc-render Skill
1,323★ repoMandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates set_final_render — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops an approved phrase, or comes back silent. Runnable, gating counterpart to content-goose's review-transcript-integrity atom. Every ugc-video-formats recipe runs this after render and BEFORE set_final_render.
gooseworks-ai/goose-skills/skills/lead-generation/capabilities/icp-website-review Skill
1,323★ repoEvaluate a website, landing page, content, or any online asset through the eyes of pre-built synthetic ICP personas. Loads personas from buyer-persona-generator output, then runs them against target URLs. Supports three modes: structured scorecard, freeform focus group, and head-to-head competitive comparison. Reusable — run against the same site after changes, or against new content anytime.
gooseworks-ai/goose-skills/skills/lead-generation/capabilities/verify-email Skill
1,323★ repoVerify if an email address is valid and deliverable
gooseworks-ai/goose-skills/skills/monitoring/capabilities/review-scraper Skill
1,323★ repoScrape product reviews from G2, Capterra, and Trustpilot using Apify. Single script with platform dispatch. Use when you need to monitor competitor reviews, track product sentiment, or gather customer feedback from review sites.
gooseworks-ai/goose-skills/skills/monitoring/capabilities/review-site-scraper Skill
1,323★ repoScrape product reviews from G2, Capterra, and Trustpilot using Apify. Single script with platform dispatch. Use when you need to monitor competitor reviews, track product sentiment, or gather customer feedback from review sites.
gooseworks-ai/goose-skills/skills/research-tools/capabilities/identity-verification-didit Skill
1,323★ repoIdentity verification via phone/email OTP and AML screening using Didit API
gooseworks-ai/goose-skills/skills/research-tools/capabilities/phone-verification Skill
1,323★ repoVerify phone numbers using SMS one-time codes via the Didit API. Use when you need to confirm a user owns a phone number, implement SMS-based 2FA, or validate phone during signup/onboarding flows.
gooseworks-ai/goose-skills/skills/research/composites/review-intelligence-digest Skill
1,323★ repoScrape G2, Capterra, and Trustpilot reviews for your product and competitors, then extract recurring themes, objections, proof points, and exact customer language for use in messaging. Chains review-site-scraper with LLM analysis. Produces a weekly or monthly digest that feeds directly into copywriting, positioning, and sales enablement. Use when a marketing team needs to ground messaging in real customer language.
gooseworks-ai/goose-skills/skills/sales/composites/pipeline-review Skill
1,323★ repoPipeline analysis composite. Pulls deal/meeting data from any CRM or tracking system, analyzes the pipeline over a user-defined period (weekly, fortnightly, monthly, quarterly), and produces both an executive summary and a detailed diagnostic report. Covers volume, qualification rates, source effectiveness, stage velocity, stuck deals, and actionable recommendations. Tool-agnostic — works with any CRM (Salesforce, HubSpot, Pipedrive, Close, Supabase, CSV).
amElnagdy/guard-skills/skills/test-guard Skill
1,317★ repoReview generated or changed test code against universal testing rules before it ships. Best used reactively after an agent writes, edits, generates, or refactors tests, before presenting, committing, or merging them. Use for pytest (test_*.py, *_test.py), PHPUnit/Pest (*Test.php), Jest/Vitest (*.test.ts, *.spec.js), Go (*_test.go), files under tests/, __tests__/, or spec/, and review requests like 'write tests for X', 'add tests', 'test this', 'review these tests', or PR diffs containing tests. Can also guide test writing when explicitly invoked before the work. This skill is the quality gate that prevents AI-generated test bloat. DO NOT USE for production or implementation code review (use clean-code-guard), CI or test-runner configuration, running or debugging tests, or general architecture discussion.
The same file is in 7 other repositories
amElnagdy/guard-skills/skills/woo-guard Skill
1,317★ repoReview generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WooCommerce APIs: wc_get_order, wc_get_orders, wc_get_product, WC() cart or session, woocommerce_* hooks, Store API endpoints, payment gateways, order or product meta, HPOS, subscriptions, or bookings. Use on 'review this Woo plugin', 'is this HPOS compatible', or after tasks like 'write a WooCommerce extension', 'add a checkout field', 'hook into the order flow', or 'update stock'. Enforces HPOS-safe order access, CRUD over direct meta, feature-compatibility declarations, server-side checkout validation, money-handling discipline, and hooks over template overrides. DO NOT USE for WordPress code without WooCommerce APIs (use wp-guard), generic code review (use clean-code-guard), test review (use test-guard), or store configuration and admin-screen questions.
The same file is in 9 other repositories
amElnagdy/guard-skills/skills/wp-guard Skill
1,317★ repoReview generated or changed WordPress code — plugins, themes, and blocks — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WordPress APIs: add_action/add_filter, shortcodes, meta boxes, AJAX handlers, REST routes, WP_Query or $wpdb, widgets, or WP-CLI commands. Use on 'review this plugin', 'is this safe to ship', 'make this translatable', 'speed up this query', or after tasks like 'write a plugin' or 'add an endpoint/shortcode/meta box'. Enforces escaping and sanitization, nonces plus capability checks, prepared database queries, core-API-first development, translation-ready strings, and query/caching discipline. DO NOT USE for WooCommerce-specific order, product, or checkout logic (use woo-guard), non-WordPress PHP, generic code quality review (use clean-code-guard), test code review (use test-guard), server or hosting configuration, or conceptual WordPress questions.
The same file is in 9 other repositories
AI-Builder-Club/skills/skills/verifier-setup Skill
no license1,312★ repoSet a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (`dev-local`) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the `playwright-cli` skill for web by default). Outputs three artifacts: a committed `/verify` skill (per-task verification SOP — spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded), the `/dev-local` skill + script, and the installed driver skill. Use when someone says "set up verification", "make this repo verifiable", "scaffold a verify skill", "set up the verifier".
The same file is in 1 other repository
fcakyon/claude-codex-settings/plugins/codex-advisor/skills/codex-advisor Skill
1,200★ repoBattle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
The same file is in 1 other repository
fcakyon/claude-codex-settings/plugins/github-dev/skills/commit-staged Skill
1,200★ repoThis skill should be used when user asks to "commit these changes", "write commit message", "stage and commit", "create a commit", "commit staged files", or explicitly invokes "commit-staged".
The same file is in 1 other repository
fcakyon/claude-codex-settings/plugins/github-dev/skills/create-pr Skill
1,200★ repoThis skill should be used when user asks to "create a PR", "make a pull request", "open PR for this branch", "submit changes as PR", "push and create PR", or explicitly invokes "create-pr".
The same file is in 1 other repository
fcakyon/claude-codex-settings/plugins/github-dev/skills/review-pr Skill
1,200★ repoThis skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this PR", "check PR #N", provides a GitHub PR URL, or explicitly invokes "review-pr".
The same file is in 5 other repositories
fcakyon/claude-codex-settings/plugins/overleaf-skills/skills/review-overleaf Skill
1,200★ repoThis skill should be used when user asks to "fetch overleaf review comments", "address overleaf reviews", "apply overleaf comments", "review my overleaf paper", "sync overleaf feedback to local", "what comments are on my overleaf doc", or wants to act on Overleaf reviewer feedback in a local git-tracked LaTeX repo.
The same file is in 4 other repositories
microsoft/power-platform-skills/plugins/power-pages/skills/audit-permissions Skill
1,152★ repoAudits existing table permissions on a Power Pages site by analyzing them against site code and Dataverse metadata. Generates an HTML audit report with findings grouped by severity (critical, warning, info, pass) and suggests fixes for issues found. Use when the user wants to review, verify, or check table permissions for security issues.
The same file is in 1 other repository
microsoft/power-platform-skills/plugins/power-pages/skills/security-review Skill
1,152★ repoRuns a guided, end-to-end security review of a Power Pages site and consolidates every finding into one HTML report covering source code and dependencies, the live site, browser headers, firewall, authentication, and role-based permissions. Use when the user wants a full security review, a release-readiness check before publishing, a code-and-config check during development, live site monitoring, or asks open-ended questions like "review my site security", "is my site safe to ship", "do a security check", "monitor my site" — even if they do not name the individual checks.
The same file is in 1 other repository
microsoft/power-platform-skills/plugins/power-pages/skills/test-site Skill
1,152★ repoTests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
The same file is in 1 other repository
xuzhougeng/wisp-science/skills/bear-review Skill
1,148★ repo给一个观点,同时检索支持它的文献和反对它的文献,在一份综合报告里呈现正反两侧的证据格局——支持侧最强证据是什么、反对侧最危险的挑战是什么、哪些角度有支持但无反对、哪些角度有反对但无支持。底层走真实检索(scimaster-cli),绝不编造引用。 **以下情况请主动触发本技能**:用户想同时看到"支持和反对"、"这个观点稳不稳"、"帮我做一个全面的论点评估"、"正反两面都找一找"——即使没有说"bear-review",只要意图是**对一个观点做完整的证据格局分析**,就使用本技能。 不适用于:只找支持(用 bear-support)、只找反对(用 bear-counter)、选题查重(用 bear-scoop)、概念地图(用 bear-map)、溯源演化史(用 bear-trace)。
xuzhougeng/wisp-science/skills/figure-style Skill
1,148★ repoPublication-grade figure correctness and legibility rules. Load before drawing any plot and call `apply_figure_style()` — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look: data fidelity (claim-titles tested against every row, excluded data never enters summaries), label economy (floor and ceiling), colour threading, chart-choice-by-data-shape, layout, and a render-then-verify QA loop (bbox collision + per-panel perceptual check). Ships helpers: focal_palette, bar_with_points, strip_with_median, end_of_line_labels, panel_letter, set_frame, panel_crops. For multi-panel figures load `figure-composer`; for whole-paper figure arc load `paper-narrative`.