automate-before-manual
Skill0 starsChanged 2 months agoMITView on GitHub
Try PAT, SSH, APIs, Azure CLI, and documented scripts before asking the user for manual browser or terminal steps. Use when about to request login, token, deploy, DNS, or "please run this yourself".
- Reads credentials
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/automate-before-manual.mdcCursor rule
- .cursor/rules/finish-task-dev-server.mdcCursor rule
- brainstormingSkill
- caveman-commitSkill
- find-skillsSkill
- semantic-versionSkill
- systematic-debuggingSkill
- verification-before-completionSkill
- writing-plansSkill
- ask-before-architectureSkill
- caveman-commitSkill
- diagrams-mermaidSkill
- dont-be-lazySkill
- dont-forgetSkill
- find-jobSkill
- finish-with-dev-serverSkill
- google-calendar-mcpSkill
- init-fmzSkill
- instagram-chrome-postSkill
- project-initSkill
- recapSkill
- semantic-versionSkill
- skills-sh-maintainerSkill
- ui-change-e2eSkill
- validate-before-shareSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before asking the user to click, install, create a token, configure DNS, or run something in their terminal:
- Very specific: line 40
If the repo layout differs, check AGENTS.md or secrets.local.md in the project for the vault location — still prefer relative paths in docs.
- Distinctive: line 49
Ask permission for steps you can already run with existing keys
- Very specific: line 50
Commit or paste secrets into the repo or skills.sh
- Very specific: line 54
Read and follow dont-be-lazy: search MCP/API, store creds in ../secrets/, then drive the Cursor browser — do not be lazier than the user.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Automate before manual
Before asking the user to click, install, create a token, configure DNS, or run something in their terminal:
1. Try automation first
- GitHub:
ghCLI or PAT from the secrets vault (see below) - Deploy: scripts in
docs/deploy-vps.md,scripts/deploy-*, GitHub Actions API - SSH: deploy keys documented in the project or secrets vault
- Azure:
az loginor service principal path documented in the repo
2. Secrets vault (relative paths only)
Never hardcode absolute paths (C:\..., /home/...) in skills, commits, or chat copy.
From the project repo root, the shared vault is:
../secrets/Common files (read only if they exist):
| Need | Relative path |
| GitHub PAT | ../secrets/github/pat.txt (line starting with ghp_) |
| VPS SSH | ../secrets/vps/ssh/ |
| Per-app env | ../secrets/projects/<app>.env |
| VPS inventory | ../secrets/vps/inventory.md |
If the repo layout differs, check AGENTS.md or secrets.local.md in the project for the vault location — still prefer relative paths in docs.
3. Before asking for a credential
State which role/scope unlocks full automation (e.g. GitHub repo scope, Azure Contributor). Only escalate when impossible: OAuth consent, 2FA, billing, domain registrar.
4. Do not
- Send a manual checklist without trying API/SSH/PAT/Azure first
- Ask permission for steps you can already run with existing keys
- Commit or paste secrets into the repo or skills.sh
5. User pushes back ("lazy", "you do it")
Read and follow dont-be-lazy: search MCP/API, store creds in ../secrets/, then drive the Cursor browser — do not be lazier than the user.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

