graph-link
Skill12 starsChanged 3 months agoMITView on GitHub
Use when you want Wheeler to batch-propose grouped Execution provenance for session orphan nodes (companion to /wh:close)
In this repository47 other files it gives its agents.
- .claude/commands/wh/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- wheeler/CLAUDE.mdCLAUDE.md
- wheeler-briefSkill
- wheeler-service-creatorSkill
- addSkill
- askSkill
- asta-assistantSkill
- asta-litSkill
- asta-reportSkill
- asta-scholarSkill
- astaSkill
- asta-theorizeSkill
- backupSkill
- bumpSkill
- chatSkill
- closeSkill
- compileSkill
- dev-feedbackSkill
- discussSkill
- dreamSkill
- executeSkill
- graph-reviewSkill
- handoffSkill
- ingestSkill
- initSkill
- lessonSkill
- llmsr-discoverSkill
- llmsr-transferSkill
- noteSkill
- pairSkill
- pauseSkill
- planSkill
- queueSkill
- reconveneSkill
- reportSkill
- restoreSkill
- resumeSkill
- serviceSkill
- skill-creatorSkill
- startSkill
- statusSkill
- triageSkill
- updateSkill
- wheeler-voiceSkill
- writeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 45
Call get_act on the wheeler_core MCP server with name="graph-link", then follow the returned instructions exactly.
- Very specific: line 55
If get_act is unavailable, the Wheeler MCP servers are not connected.
≈ “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
<!-- GENERATED FILE. Do not edit.
Source: wheeler/_data/commands/graph-link.md
Regenerate: python -m wheeler.build_plugin
The act body is served over MCP by wheeler_core.get_act(), so it is
deliberately absent here: there is exactly one copy of it. -->Call get_act on the wheeler_core MCP server with name="graph-link",
then follow the returned instructions exactly. They are the authoritative
definition of this act. Do not improvise the workflow or substitute your own
plan for it.
Pass host="codex" when running under Codex so the orchestration guidance
matches the tools this host actually has.
Mode: write. Orchestration: none.
If get_act is unavailable, the Wheeler MCP servers are not connected. Say so
rather than guessing at the workflow: acting without the act text is how
provenance gets silently skipped.
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.