workflow
Project workflow for PRDs, task tracking, changelog sync, and documentation updates. Use for any non-trivial task that spans multiple steps, touches several files, changes architecture, or needs project tracking updates. Also activates with @update to sync task.md, changelog.md, and files.md after completing work.
Best use case
workflow is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Project workflow for PRDs, task tracking, changelog sync, and documentation updates. Use for any non-trivial task that spans multiple steps, touches several files, changes architecture, or needs project tracking updates. Also activates with @update to sync task.md, changelog.md, and files.md after completing work.
Teams using workflow should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/workflow/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How workflow Compares
| Feature / Agent | workflow | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Project workflow for PRDs, task tracking, changelog sync, and documentation updates. Use for any non-trivial task that spans multiple steps, touches several files, changes architecture, or needs project tracking updates. Also activates with @update to sync task.md, changelog.md, and files.md after completing work.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Project Workflow Skill Use this skill for any non trivial task that spans multiple steps, touches several files, changes architecture, or needs project tracking updates. Activate with: `@update` (for docs sync only) ## Triage first Before changing code: 1. Identify what is missing, broken, or incomplete. 2. Theorize a few likely causes or approaches. 3. Narrow to the most likely plan. 4. Ask if anything important is still unclear. Skip the long process only for obvious one file fixes like typos or tiny copy changes. ## PRD rules Create a PRD before non trivial work. - Path: `prds/<feature-or-problem-slug>.md` - Extension: `.md` - Include: - problem - root cause for bugs - proposed solution - files to change - edge cases - verification steps - task completion log Add metadata at the top: - `Created: YYYY-MM-DD HH:mm UTC` - `Last Updated: YYYY-MM-DD HH:mm UTC` - `Status: Draft | In Progress | Done` ## Task tracking Update `task.md` as the work moves forward. - Put new work under `## to do` - Move finished work to `## completed` - Add timestamps in `YYYY-MM-DD HH:mm UTC` - Do not mark a task done until it has been verified - Keep task notes short but specific enough for the next session When useful, include: - the PRD path - the files touched - the verification command or outcome ## Docs sync after changes After each feature or fix, sync the project docs: - `task.md` - `changelog.md` - `files.md` For `changelog.md`: - use Keep a Changelog structure - get real dates from `git log --date=short -n 10` - add timestamps when helpful For `files.md`: - add new files - update descriptions that changed - keep descriptions brief and concrete ## Execution style - Use subagents for research or parallel analysis when the task is large enough to benefit. - Use one focused subagent per task. - Stop and re plan if the work stops making sense. - Keep the change set tight. - Ask whether a staff engineer would approve the result before calling it done. ## Learning loop If the user corrects a repeated pattern, record the lesson in `prds/lessons.md` so the mistake does not come back.
Related Skills
workos-convex-debug
Debug and troubleshoot WorkOS AuthKit authentication issues with Convex. Use when authentication fails, JWT validation errors occur, user identity returns null, email claims are missing, admin access checks fail, or sign in button does not work. Supports Netlify deployment.
workos-convex-auth
Set up and configure WorkOS AuthKit authentication with Convex backend. Use when integrating AuthKit, configuring JWT providers, setting up environment variables, or implementing sign in and sign out flows with React and Vite. Supports Netlify deployment.
convex-scale-optimization
Patterns for scaling read-heavy Convex apps to millions of users. Use when optimizing bandwidth, reducing query costs, fixing slow queries, creating digest tables, replacing reactive subscriptions with one-shot fetches, adding compound indexes, debouncing writes, rate-controlling backfills, or running npx convex insights. Trigger when users mention "scale", "bandwidth", "performance", "optimize", "slow queries", "expensive queries", "digest table", "denormalize", or "thundering herd" in the context of Convex.
convex-design-system
Convex UI component patterns from the live Storybook preview. Use when building React components, forms, modals, navigation, feedback states, or app layouts that should match the current Convex design system. Applies to both shared primitives and dashboard style product UI.
Update project docs
Sync project tracking files after completing work, then provide a ready to use git commit message.
typeset
Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.
teach-impeccable
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
robel-auth
Integrate and maintain Robelest Convex Auth in apps by always checking upstream before implementation. Use when adding auth setup, updating auth wiring, migrating between upstream patterns, or troubleshooting @robelest/convex-auth behavior across projects.
quieter
Tones down visually aggressive or overstimulating designs, reducing intensity while preserving quality. Use when the user mentions too bold, too loud, overwhelming, aggressive, garish, or wants a calmer, more refined aesthetic.
polish
Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
overdrive
Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
optimize
Diagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.