Loading...
Loading...
Found 9,492 Skills
Opt-in evidence-first causal diagnosis for bugs, browser or app/device failures, flaky behavior, and performance regressions. Activate only when the user explicitly invokes `$diagnose` or explicitly asks to use the named diagnose skill. Do not activate merely because the user mentions a bug, asks why something failed, requests debugging or a fix, or describes unexpected behavior. Once explicitly invoked, locate likely causes, instrument relevant boundaries with extensive structured logging, reproduce the issue, analyze the collected logs, rank causes with confidence scores, and pursue 100% operational confidence while probes can increase confidence.
Write the test first, watch it fail, then write the least code that passes. Covers where the test belongs, what makes it honest, what a passing test proves and what it does not, recovering when code was written before the test, and starting a bug fix from a red run. A test nobody watched fail proves nothing. Use when implementing a feature or a bugfix, when a test was written after the code, when a test passes the first time you run it, or when the user says "write tests for this", "add coverage", or "TDD this". Not for judging tests inside a change under review, and not for choosing a test framework.
Atomic Skill for Brand Gene Style Extraction. Based on product images and user-provided brand gene parameters (main color, font, platform, region, language), extract a unified brand visual language (Brand DNA) and output structured brandGeneJson for consumption by downstream atomic skills. Keywords: brand gene extraction, brand gene extract, brand DNA, brand visual definition, brand tone extraction, brand style extraction, visual identity extraction. Called by the image layout layer (linkfox-aigc-imagegen-cloth / product image layout path) in Step 3; triggered when the user says "extract brand gene", "define brand style", "brand gene", or "brand visual".
Apparel Image Generation (for models/clothing). Supports single images or image sets: white background images (invisible model), model images, lifestyle marketing images, selling point images, A+ images, size chart images. Direct generation for single image of a single type; automatic orchestration and planning for multiple images of multiple types. Triggered when users upload model images or apparel images (topwear, bottomwear, dresses, outerwear, shoes & hats, etc.) and request actions like "create an image set", "make a model image", "make a lifestyle marketing image", "make a selling point image", "make an A+ image", "make a size chart image", "make a white background apparel image". Pure image editing operations go through linkfox-aigc-imagegen.
Trim a spec, ADR set, or design doc down to what a builder needs, without losing a fact. TRIGGER when: user says a spec is 'too long' or 'bloated'; user asks what to remove from it, or wants it cut to 'just what we need to build'.
Completes one or more tasks. Creates one tested and reviewed pull request for each task. Use to implement, build, fix, or deliver tasks, tickets, pull requests, or a milestone.
Track case deadlines — add, cross-case rollup report, update, complete, close. Warns at configurable thresholds (default 14/7/3/1 days); overdue items stay flagged until resolved. The operational record for a clinic workload. Use when a student or supervisor needs to add a deadline, ask what's due this week, get a deadline report, or update a case deadline.
Writes a clear design for a proposed feature or system change. Use when important product or technical choices must be settled before coding. Covers behavior, interfaces, failures, risks, acceptance criteria, and tests. Use architecture when the repository needs current ARCHITECTURE.md.
Explore codebase before committing to a change. Phase executor skill for specs.explore command.
Use Proxyman MCP to inspect and debug captured HTTP/HTTPS/WebSocket traffic and operate Proxyman through all MCP actions. Use this skill when an agent needs to analyze traffic, diagnose missing capture, manage rules, use Compose, inspect WebSockets, install certificates, control proxy settings, use setup guidance, export flows, generate code, run Proxyman automations, or troubleshoot Proxyman MCP.
Work in an existing vignette catalog: set it up, run or inspect its marimo notebooks, and answer data questions by reusing their @app.function helpers in a live kernel. Use whenever a repository has catalog.toml and the user asks to get started, run notebooks, explore the data, make an analysis or figure, or compose a new notebook. Do not use for generic notebooks or for creating a new catalog.
Run a complete repository-native, spec-anchored development loop inspired by DeepSeek Harness. Use for feature development, bug fixes, simplification, architecture, process, or testing work that changes behavior, contracts, structure, test strategy, durable formats, or decision rationale; when asked to write, review, continue, implement, reject, supersede, archive, or verify a spec/Agent Note/RFC/ADR; or when code, tests, current-state docs, and decision rationale must converge in one change. Also use for read-only spec-to-code drift checks. Do not create a spec for a purely mechanical local edit that changes none of those things.