ai-projects
Skill17 starsChanged 2 months agoMITView on GitHub
Sync a Git repository of AI projects to a local directory.
In this repository18 other files it gives its agents.
- 3dprinterSkill
- ciberjohn-no-slopSkill
- excalidrawSkill
- gymcoachSkill
- jevSkill
- joplin-brainSkill
- medium-storySkill
- openrouter-image-genSkill
- openscad-cadSkill
- paperclip-creatorSkill
- proxmox-estateSkill
- short-videosSkill
- skill-writerSkill
- social-posterSkill
- t3mp3st-autonomous-securitySkill
- technical-trainerSkill
- transcribeSkill
- uk-business-consultantSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
If the directory already exists, it performs a git pull to update.
- Very specific: line 50
If {{AI_PROJECTS_LOCAL_PATH}} exists but is not a Git repository, the skill halts with an error message.
- Distinctive: line 52
If the remote is unreachable, git pull will fail with the underlying Git error — review network connectivity and repository URL.
- Distinctive: line 54
If the local tree has uncommitted changes, git pull --ff-only will reject the update.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
ai-projects
Syncs a configured Git repository containing AI projects to a local directory.
If the directory already exists, it performs a git pull to update. If not, it
clones the repository fresh. Always reports the current status of the local
working tree.
Configuration Variables
| Variable | Purpose | Example |
{{AI_PROJECTS_REPO_URL}} | The full Git remote URL to clone from | https://github.com/example/ai-projects.git |
{{AI_PROJECTS_LOCAL_PATH}} | Absolute path to the local copy | ~/ai-projects |
Set these in your Hermes profile configuration under the ai-projects skill
block, or export them as environment variables before invoking the skill.
Steps
- Check existence — If
{{AI_PROJECTS_LOCAL_PATH}}does not exist, clone{{AI_PROJECTS_REPO_URL}}into it. If it already exists and is a Git repository, proceed to step 2. - Update — Run
git pull --ff-onlyinside{{AI_PROJECTS_LOCAL_PATH}}to fetch and merge upstream changes without creating merge commits. - Report — Print the current branch, latest commit hash, commit message, and whether the working tree is clean.
Prerequisites
- Hermes Agent — The skill relies on Hermes's variable interpolation and terminal execution.
- Git — Must be installed and available on
PATH. - Network access — The remote repository must be reachable from the execution environment.
Error Handling
- If
{{AI_PROJECTS_LOCAL_PATH}}exists but is not a Git repository, the skill halts with an error message. - If the remote is unreachable,
git pullwill fail with the underlying Git error — review network connectivity and repository URL. - If the local tree has uncommitted changes,
git pull --ff-onlywill reject the update. Stash or commit local changes before running the skill again.
Usage
# The skill is invoked via Hermes:
# "sync my ai projects"
# or directly from the shell:
hermes skill run ai-projectsDoes 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.

