Loading...
Loading...
Found 584 Skills
Run a final release checklist before shipping. Verifies no TODOs, no debug code, docs updated, tests passing, dependencies justified, and security reviewed.
AI Image Generation Skill, using the latest ChatGPT image generation model gpt-image-2-all. This skill is applied when users need to generate images, visual infographics, create graphics, or edit/modify/adjust existing images. Based on the image generation service of the latest ChatGPT image generation model gpt-image-2-all from APIYI Platform (https://api.apiyi.com/), no external network access is required. The model is charged per image at $0.03 per piece, supporting text-to-image generation, single image editing, multi-image fusion, and natural language-based image modification, with high text restoration accuracy and friendly Chinese prompts. The size is controlled by prompt description (no explicit size parameter). Key differences from NanoBanana2: no size parameter, need to describe the size at the beginning of the prompt; unified $0.03 per image with no resolution tiering; the conversational endpoint /v1/chat/completions is the recommended one.
Analyze the writing style characteristics of articles, extract style dimensions and store them in the style material library. It can fuse multiple style materials to generate or update the main style profile (my_style.json). Use this skill when users say "analyze style", "extract writing style", "learn this tone", "analyze my writing style", "absorb this style", "update my style". Even if users just share an article and express interest in its style, consider using this skill.
Manage for output using Grove's "High Output Management": a manager's output is their organization's output, raised by high-leverage activities. Use when the user mentions "high output management", "managerial leverage", "one-on-ones", "1:1 agenda", "OKRs", "performance review", "task-relevant maturity", "delegation", "meeting overload", "new manager", "how do I run a 1:1", or "just got promoted to manager". Also trigger when structuring a manager's calendar and meeting cadence, designing team metrics, running planning, coaching delegation, or preparing performance reviews. Covers leverage, production principles, meetings as the medium of management, decisions, OKRs, and task-relevant maturity. For intrinsic motivation, see drive-motivation. For a company operating system, see traction-eos.
Apply Institutional Theory (DiMaggio and Powell, 1983) to analyze how coercive, mimetic, and normative isomorphic pressures shape organizational structures and practices. Use this skill when the user needs to explain why organizations in the same field look alike, evaluate whether a practice was adopted for legitimacy vs efficiency, analyze regulatory or social pressures on strategy, or when they ask 'why do all firms in this industry do the same thing', 'is this best practice or just conformity', or 'how do regulations shape our structure'.
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes: indigo→violet gradients, gradient-clip headline text, warm amber/stone "cozy" palettes, the default semantic palette (info-blue / tip-amber / success-green / error-red), one-hue status boxes, atmospheric/ambient gradients, serif-italic emphasis on one word, serif where sans belongs, decorative strikes and highlights, highlighted keywords in copy, AI copywriting voice ("not just X — it's Y"), emoji everywhere, glowing status dots, rounded colored-left-border callouts, pastel rounded-square icon tiles, glassmorphism and over-rounding, oversized drop shadows, corners that don't nest, badge & pill spam, AI-drawn SVG icons, icons in a tint of themselves, all-caps card grids, and the "tasteful terminal". Works on HTML/CSS, React/Vue/Svelte/Astro, Tailwind, and Markdown copy.
Guide for querying databases through DBHub MCP server. Use this skill whenever you need to explore database schemas, inspect tables, or run SQL queries via DBHub's MCP tools (search_objects, execute_sql). Activates on any database query task, schema exploration, data retrieval, or SQL execution through MCP — even if the user just says "check the database" or "find me some data." This skill ensures you follow the correct explore-first workflow instead of guessing table structures.
Format and restructure markdown documents so they publish cleanly to Confluence via `orbit confluence publish`. Use this skill whenever the user wants to prepare docs for Confluence, fix markdown formatting for wiki publishing, add frontmatter to docs, restructure a docs directory, or ensure markdown files follow Confluence-friendly conventions. Also trigger when the user says things like 'format these docs', 'prepare docs for Confluence', 'fix the frontmatter', 'restructure the docs folder', 'make these docs publishable', 'clean up the markdown', or any task involving making markdown Confluence-ready — even if they just say 'format this' or 'prep for wiki' without mentioning Confluence explicitly. If the user has a docs/ directory and mentions publishing or syncing, this skill applies.
Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked' — an A/B, a holdout, a score, a validation — and whenever a result feels too clean or self-confirming. Walks an 8-pattern leakage taxonomy and returns only the patterns that fire, each with an independence fix. Read-only.
Coverage Gaps audit worker (L3). Identifies missing tests for critical paths (Money 20+, Security 20+, Data Integrity 15+, Core Flows 15+). Returns list of untested critical business logic with priority justification.
Forces exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology. MUST trigger when: (1) any task has failed 2+ times or you're stuck in a loop tweaking the same approach; (2) you're about to say 'I cannot', suggest the user do something manually, or blame the environment without verifying; (3) you catch yourself being passive — not searching, not reading source, not verifying, just waiting for instructions; (4) user expresses frustration in ANY form: 'try harder', 'stop giving up', 'figure it out', 'why isn't this working', 'again???', '换个方法', '为什么还不行', '你再试试', '加油', '你怎么又失败了', or any similar sentiment even if phrased differently. Also trigger when facing complex multi-step debugging, environment issues, config problems, or deployment failures where giving up early is tempting. Applies to ALL task types: code, config, research, writing, deployment, infrastructure, API integration. Do NOT trigger on first-attempt failures or when a known fix is already executing successfully.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.