audit-agent-documentation
Audit and improve agent documentation across a codebase while preserving project contracts.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-21 00:15
258,941 results
Audit and improve agent documentation across a codebase while preserving project contracts.
Generate or edit images via the Doubao Seedream (Jimeng / Dreamina) image model on ByteDance's Volcano Engine Ark.
Use when generating videos with Model Studio DashScope SDK using Wan video generation models (wan2.6-t2v, wan2.6-i2v-flash, wan2.6-i2v and regional variants).…
Perform basic arithmetic using a direct operator implementation
Build TypeScript clients for SpacetimeDB. Use when connecting to SpacetimeDB from web apps, Node.js, Deno, Bun, or other JavaScript runtimes.
Stage 2 of the feature flow—write code in the order given by {slug}-design.md, then report completion to the user for review in a unified format. The prerequisite is that {slug}-design.md has been approved (a standard design includes test design, or a fastforward design includes acceptance criteria), and that in the same directory there is…
When fixing a bug, enter this sub-process—take "discovered a problem" from a verbal description to a closed loop of verified fix, leaving three files in between: problem report, root cause analysis, and fix record. This process adds a layer of buffering between "seeing the problem" and "changing the code," avoiding several common ways of going off the rails: the problem description in your head disappears once the fix is done, you act without analyzing the root cause and only change the surface, the scope of the fix sprawls and can't be traced, and after the fix there's no verification so you don't know whether you fixed it right. This skill only does routing, ...
Stage 2 of the issue flow—read the issue report + read the code to find the real root cause and assess fix risk, then give the user 2-3 fix options to let them decide. This stage is **not about starting to change code**—after analysis, show the user the conclusion first, and only enter stage 3 after the user confirms the approach. Prerequisite: easysdd-issue-report is complete. Trigger scenarios: user says "analyze this…
Phase 1 of the issue workflow—turn the problem in the user's head into a reproducible, traceable {slug}-report.md through conversation. Here the AI only asks "what did you see, how do you reproduce it, what should happen instead" and does not guess the root cause for the user (that is phase 2's job). At the same time, this phase is the only formal decision point for deciding whether to take the fast track or the standard path: based on the user's description, first read the relevant code, and if it can be pinpointed at a glance and the change is small, directly tell them to use…
End-to-end workflow for setting up Blender, rigging a character, and creating a simple animation with a clear output (rendered animation).
Split a large task across parallel sub-agents with clean role boundaries and a merge step. Use when the user asks to "parallelize", "use multiple agents", "fan…
Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio). Manage code workflows, review PRs, search code,…
Plan the business analysis approach, stakeholder engagement, governance, and information management for a project
Use when extending an existing core-library Datex Studio component (most commonly a grid) via the baseConfiguration overlay mechanism, or flattening a tailored…
Guidance for .NET MAUI XAML data bindings, compiled bindings, value converters, binding modes, multi-binding, relative bindings, and MVVM best practices. USE…
Conduct Failure Mode and Effects Analysis (FMEA) for systematic identification and risk assessment of potential failures in designs, processes, or systems.…
Fonts for text in Decentraland SDK7 scenes — the three built-in faces and custom TTF fonts shipped with the scene (`fontSrc`) on TextShape, UiText, Label,…
Sales Ops expert. Use for sales processes, CRM, forecasting, and sales analytics.
Starting from a fixed point (commit, branch, tag, or merge-base), review the changes along two axes—convention (does the code follow the repository's documented coding conventions?) and specification (does the code match the requirements of the original issue/PRD?). The two review lines run in parallel sub-agents and report results side by side. When the user wants to review a branch, PR, in-progress changes, or asks to "from…
Scan the codebase for deepening opportunities, present them in a visual HTML report, then interrogate the options you selected.
Investigate questions against high-confidence primary sources and land the findings in a Markdown file. Use when the user wants to research a topic, collect documentation or API facts, or delegate reading legwork to a background agent.
Plan a large body of work—more than a single agent session can hold—as a shared map of decision tickets on your issue tracker, resolving them one by one until the road to the destination becomes clear.
This skill should be used when creating Git commits to ensure they follow the Conventional Commits specification. It provides guidance on commit message…
Create, test, and deploy synthetic monitoring checks from source code using the supaguard CLI. Triggers on monitoring setup, Playwright script generation,…