Dev workflows
Claude Cortex
npx -y skills add NickCrew/Claude-Cortex --skill dev-workflowsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 23 stars23 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when running builds, executing tests, or improving developer experience workflows - provides structured guidance for build/test execution and DX improvement.
SKILL.md
1.7 KB, 261 tokens by cl100k_base, as published. Nobody here has run it
Dev Workflows
Overview
Unify build, test, and DX improvement workflows so they are repeatable and reliable. Focus on safe execution, clear diagnostics, and actionable follow-ups.
When to Use
- Running builds or resolving build failures
- Executing tests or analyzing test failures
- Improving onboarding, tooling, or developer workflows
Avoid when:
- The task is pure code implementation
- A full release process is required (use release-prep)
Quick Reference
| Task | Load reference |
|---|---|
| Build workflows | skills/dev-workflows/references/build.md |
| Test workflows | skills/dev-workflows/references/test.md |
| DX improvements | skills/dev-workflows/references/dx.md |
Workflow
- Select the workflow type: build, test, or DX.
- Load the matching reference file.
- Execute with monitoring and capture diagnostics.
- Apply fixes or improvements as needed.
- Verify outcomes and document next steps.
Output
- Execution summary (status, errors, next steps)
- Suggested follow-ups or improvements
Common Mistakes
- Skipping baseline environment checks
- Running tests without capturing failing output
- Changing DX workflows without documenting impact
What ships with it: 3 files
11.4 KB alongside SKILL.md
Gives 0 of the 12 instructions most test skills give in 261 tokens
Counted across 964 of the 1,571 authors here whose files we hold, read 2026-08-07
- Close the browser when donein 55 of 964, across 12 files
- Wait for network idle statein 51 of 964, across 6 files
- Launch Chromium in headless modein 49 of 964, across 6 files
- Use descriptive selectors for elementsin 49 of 964, across 6 files
- Run provided scripts with help flag firstin 49 of 964, across 6 files
- Add appropriate explicit waitsin 48 of 964, across 5 files
- Use bundled scripts as black boxesin 46 of 964, across 3 files
- Do not read script source codein 46 of 964, across 3 files
- Use sync playwright for scriptsin 46 of 964, across 3 files
- Inspect dom before executing actionsin 46 of 964, across 3 files
- Run the full test suitein 37 of 964
- Write the failing test firstin 29 of 964, across 23 files
Said here and by no other author read
- select build test or DX workflow
- execute with monitoring and diagnostics capture
- apply fixes or improvements as needed
- verify outcomes and document next steps
- run baseline environment checks
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.