Design and build automation workflows using building blocks — clarify outcomes, decompose by dependencies, reuse prior art, verify each block before chaining, and research when stuck. Covers generic divide-and-conquer (problem framing, observable surfaces, investigation vs shipping, CLI contracts) plus human-like pacing for social and communication platforms.
SkillScore45Maintained
Automatic
◆Doc Ops pack
Last verified 8/19/2026
What it changes
Passed 9 of 20 test cases with the skill, and 5 of 20 without it.
Without skill27%
With skill45%
Checks it passed that the model alone missed
Uses kebab-case for the workflow filename inside workflows/
Places the workflow file inside a subdirectory under workflows/
Uses a .md file extension for the workflow file inside workflows/
and 1 more in the full report
5 fixed5 passed either way11 still failing1 broke
Pass-rate lift
+18 pp
Tokens
-20%
Agent turns
0%
Response time
-12%
Model gemini-3.6-flashMeasured 8/19/2026v210 of 22 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
Create a performance benchmarking workflow document to track regression on main branch.
What was checked, without and with the skill
Checked
Without skill
With skill
Places the workflow file inside a subdirectory under workflows/
Missed
Passed
case-11 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md3 linessingle file
Canonical:workflows/create-workflow/create-workflow.md (in this repo). This file is a thin pointer for Cursor skill discovery — load the canonical workflow doc for the full methodology.
Read workflows/create-workflow/create-workflow.md and follow it.
Automated LinkedIn engagement workflow. The agent finds a relevant post on your chosen topic, drafts a comment with a genuine insight, gets your approval in chat, and posts it — all in one loop. You approve once before anything is posted. Use when asked to "engage on LinkedIn", "find a post to comment on", "post a LinkedIn comment", or "engage on [topic]". Requires LinkedIn session credentials in .env. Everything runs locally — credentials never leave your machine.