link-for-testing
Skill4 starsChanged 7 months agoMITView on GitHub
Symlink skills and agents from each domain plugin into .claude/ so they can be tested locally. Run this once after cloning or adding new plugins, skills, or agents.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- add-pluginSkill
- update-pluginSkill
- validate-marketplaceSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run these bash commands from the repo root:
- Distinctive: line 101
After linking, restart Claude Code for new skills to appear in the Skill tool.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Link for Testing
Each domain plugin lives at the repo root (e.g. decision-making/, communication/) and
contains skills/ and agents/ subfolders. This skill symlinks their contents into .claude/
so Claude Code picks them up for local testing.
Steps
Run these bash commands from the repo root:
1. Create target directories if missing:
mkdir -p .claude/skills .claude/agents2. Symlink each skill across all plugins:
For every plugin at the repo root, symlink each skill into .claude/skills/ with the plugin name prepended (e.g. communication-bluf-communication):
for plugin_dir in */; do
[ -d "${plugin_dir}skills" ] || continue
plugin=$(basename "$plugin_dir")
for skill_dir in "${plugin_dir}skills/"/*/; do
[ -d "$skill_dir" ] || continue
name=$(basename "$skill_dir")
target=".claude/skills/${plugin}-${name}"
if [ -L "$target" ]; then
echo "already linked: ${plugin}-${name}"
elif [ -e "$target" ]; then
echo "skipped (real dir exists): ${plugin}-${name}"
else
ln -s "../../${plugin_dir}skills/$name" "$target"
echo "linked skill: ${plugin}-${name}"
fi
done
done3. Symlink each agent across all plugins:
For every plugin at the repo root, symlink each agent in <plugin>/agents/ into .claude/agents/:
for plugin_dir in */; do
[ -d "${plugin_dir}agents" ] || continue
plugin=$(basename "$plugin_dir")
for item in "${plugin_dir}agents/"*; do
[ -e "$item" ] || continue
name=$(basename "$item")
target=".claude/agents/$name"
if [ -L "$target" ]; then
echo "already linked: $name"
elif [ -e "$target" ]; then
echo "skipped (real file exists): $name"
else
ln -s "../../${plugin_dir}agents/$name" "$target"
echo "linked agent: $name (from $plugin)"
fi
done
done4. Remove stale symlinks (source no longer exists): For skills:
for link in .claude/skills/*/; do
name=$(basename "$link")
target=".claude/skills/$name"
if [ -L "$target" ] && [ ! -e "$target" ]; then
rm "$target"
echo "removed stale skill symlink: $name"
fi
doneFor agents:
for link in .claude/agents/*; do
name=$(basename "$link")
if [ -L ".claude/agents/$name" ] && [ ! -e ".claude/agents/$name" ]; then
rm ".claude/agents/$name"
echo "removed stale agent symlink: $name"
fi
done5. Confirm what was linked:
echo "\n--- .claude/skills ---"
ls -la .claude/skills/
echo "\n--- .claude/agents ---"
ls -la .claude/agents/Notes
- Symlinks use relative paths so they work after the repo is moved.
- Items already linked or present as real files are skipped safely — re-running is idempotent.
- After linking, restart Claude Code for new skills to appear in the Skill tool.
- To unlink:
rm .claude/skills/<plugin>-<name>(removes the symlink, not the source).
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.

