Loading...
Loading...
Found 2,015 Skills
Comprehensive UI/UX quality audit covering visual hierarchy, accessibility, AI slop detection, typography, colour, layout, interaction states, responsive behaviour, performance, and microcopy. Produces severity-rated findings with actionable...
Refresh stale learning docs and pattern docs under docs/solutions/ by reviewing them against the current codebase, then updating, consolidating, replacing, or deleting the drifted ones. Trigger this skill when the user asks to refresh, audit, sweep, clean up, or consolidate stale docs in docs/solutions/ (phrases like "refresh my learnings", "audit docs/solutions/", "clean up stale learnings", "consolidate overlapping docs", "compound refresh", "/ce-compound-refresh"), or when ce-compound has just captured a new learning and flagged a specific older doc in docs/solutions/ as now inaccurate or superseded — invoke with the narrow scope hint ce-compound provides. Also trigger when the user points at a specific learning or pattern doc under docs/solutions/ and calls it stale, outdated, overlapping, or drifted. Do not trigger for general refactor, migration, debugging, or code-review work unless the user has explicitly directed attention to docs/solutions/ itself.
Runs comprehensive WCAG-oriented web accessibility audits using Chrome DevTools MCP (Lighthouse desktop and mobile, custom evaluate_script heuristics, keyboard focus and modals, a11y snapshot vs DOM parity, 320px reflow, touch targets, structured markdown reports). Use when auditing websites for accessibility, WCAG, a11y, inclusive design, Lighthouse or axe findings, screen reader parity, focus visibility, or Chrome DevTools MCP audit workflows.
PR-backed and current-main optimization manual for `moonshotai/Kimi-K2*` and `moonshotai/Kimi-K2.5*` in SGLang. Use when Codex needs to recover, extend, or audit Kimi optimizations, including K2 router/MoE fast paths, K2 thinking Marlin paths, K2.5 wrapper/multimodal/runtime plumbing, W4AFP8/W4A16 quant tracks, parser contracts, LoRA coverage, and backend-specific validation.
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations (cite present but the cited paper does not establish the claim). Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
Optimize App Store and Google Play listings with keyword strategy, metadata, and localization. Use when asked to improve app store visibility, ASO, or app discoverability. Don't use for web SEO, paid UA/ad campaigns, or pre-submission compliance/review audits.
Scans code for security vulnerabilities — injection flaws, authentication gaps, XSS vectors, mass assignment, CSRF, insecure deserialization, sensitive data exposure, broken access control, and misconfigurations. Generates severity-scored findings with copy-pasteable fix prompts. Trigger phrases: "security scan", "security audit", "vulnerability check", "find security issues".
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or audit such a base, or initialize a new one. Trigger on phrases like "add this to my wiki", "ingest this paper", "compile this into the knowledge base", "what does my wiki say about X", "lint the wiki", "build a knowledge base from these documents", "research notes", "second brain", "personal knowledge base", or any reference to LLM Wiki / OmegaWiki. Trigger even when the user does not say "wiki" — if they are accumulating sources over time and want them organized, this applies. The skill scales — sharded indexes, atomic pages, YAML frontmatter, and a bundled search script keep the wiki from becoming a context bottleneck at hundreds or thousands of pages.
Code review and audit system with specialized sub-skills covering SOLID principles, security, performance, architecture, error handling, testing, code smells, design patterns, and framework best practices. Generates severity-scored findings with copy-pasteable fix prompts. Strictly read-only — never modifies user code. Use when user says "review", "audit", "code review", "check my code", "security scan", "code smells", "SOLID check".
Manage app translations with goman.live. Use when: adding translations, adding i18n keys, localizing components, checking translation keys exist, searching translations, updating language content, managing i18n strings, extract hardcoded strings, localize folder, audit missing translations.
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks for a "design review", "design critique", "5 维度评审", "design audit", or "what's wrong with my design".
Write programmatic Node.js or TypeScript scripts that drive the DatoCMS Content Management API using @datocms/cma-client, @datocms/cma-client-node, or @datocms/cma-client-browser — the code-first companion for content-heavy and automation work. Prefer this skill whenever the task needs real code for records, uploads, or project automation — including short mid-conversation asks like "publish them", "fix those slugs", "delete all drafts", or "bulk import this CSV", and longer checked-in scripts. Covers four areas: (1) content operations — create/update/delete/publish records, bulk import/export and CSV pipelines, pagination over large record sets, asset uploads from URL or local files with metadata, structured text and block payload edits; (2) environment and project governance — fork/promote environments, webhooks and build triggers, project settings and maintenance mode, scheduled publish/unpublish workflows, audit logs, usage analytics, subscription limits; (3) access control and typed flows — roles and API tokens, upload tracks and tags, generated CMA schema types for type-safe record operations; (4) schema and UI configuration when the user explicitly bypasses the migrations workflow or wants schema mutations embedded in a larger script — models, fields, blocks, saved filters, dashboard and schema menus, plugin install and configuration. For ordinary schema changes inside a project with a migrations workflow or a secondary environment, prefer `datocms-cli` migrations as the safe default; reach for this skill only when the user opts out or the mutation is part of a broader automation. Works for both one-off execution via `cma:call` / `cma:script` and checked-in `buildClient()` scripts for reusable or unattended code.