quick-context
Skill4 starsChanged 3 months agoMITView on GitHub
Quickly load the selected project's CLAUDE.md instructions when a session starts outside that project. Use only when explicitly invoked as /quick-context with an optional project name or path; avoid code scans, tests, and edits.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- 1Skill
- 2Skill
- 3Skill
- 4Skill
- 5Skill
- ae-extendscriptSkill
- asapSkill
- backbeforeSkill
- componentsSkill
- githubSkill
- huhSkill
- instantSkill
- motion-animateSkill
- motion-assetsSkill
- motion-designSkill
- motion-pipelineSkill
- motion-planSkill
- shader-uiSkill
- thumbnailSkill
- ui-intergritySkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Use $ARGUMENTS: a project name, project path, repository path, or CLAUDE.md path.
- Distinctive: line 15
Use the active project selected in Note Overlay, when available.
- Distinctive: line 16
Use the current Git repository root.
- Very specific: line 24
Read the complete CLAUDE.md and/or .claude/CLAUDE.md.
- Very specific: line 25
Read CLAUDE.local.md when present.
- Very specific: line 26
Follow and read any @... imports referenced by those files.
- Distinctive: line 27
Read independent context files in parallel when possible.
- Distinctive: line 28
Treat the resolved root as the active project root for future work.
- Distinctive: line 40
If nothing is found, return only:
≈ “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
/quick-context
Load the correct project's instructions into the session immediately.
Find the project
Resolve the project in this order:
- Use
$ARGUMENTS: a project name, project path, repository path, orCLAUDE.mdpath. - Use the active project selected in Note Overlay, when available.
- Use the current Git repository root.
For a project name, check Note Overlay's project registry or known project folders. Never scan the entire computer. If multiple projects match, ask for one short selection instead of guessing.
Load the context
From the resolved project root:
- Read the complete
CLAUDE.mdand/or.claude/CLAUDE.md. - Read
CLAUDE.local.mdwhen present. - Follow and read any
@...imports referenced by those files. - Read independent context files in parallel when possible.
- Treat the resolved root as the active project root for future work.
Internalize the project's purpose, architecture, commands, conventions, constraints, priorities, and warnings. Do not scan the codebase, run tests, edit files, or summarize everything. Never claim that context is loaded until the files were actually read.
Return only:
⚡ Context loaded: [project]
Root: [absolute path]
Read: [context files]If nothing is found, return only:
⛔ Context not found: [project/path]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.

