summary
Skill1 starsChanged 31 days agoBSD-3-ClauseView on GitHub
Show the curator what this session actually did, from the session transcript rather than from memory. Use when the user invokes /summary, asks "what did you do", "what did we change", "which models did you touch", "what did you save and where", or wants a record of the session for themselves or a reviewer. Runs the hub's summary tool and presents its output as is.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- saksham10arora-dotcom/everything-claude-codextheir own version, first seen Nov 1, 2026
- robo311/devflowtheir own version, first seen Oct 20, 2026
- Dev-PGVAA/skillstheir own version, first seen Oct 16, 2026
- finos/git-proxytheir own version, first seen Oct 9, 2026
- isas1/skillstheir own version, first seen Sep 21, 2026
- postproxy/postproxy-claude-plugintheir own version, first seen Sep 8, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- finos/git-proxy★ 263same name
- isas1/skills★ 210same name
- saksham10arora-dotcom/everything-claude-codex★ 74same name
- yarikleto/claude-teacher-plugin★ 9same name
- robo311/devflow★ 1same name
- timsvoice/skills★ 1same name
- Dev-PGVAA/skills★ 0same name
- kys42/claude-skills★ 0same name
- postproxy/postproxy-claude-plugin★ 0same name
- TechHU-GS/cc-discipline★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- amigoSkill
- annotate-functionSkill
- gene-reviewSkill
- gocam-best-practiceSkill
- gocam-reviewSkill
- noctuaSkill
- pubmed-eutilsSkill
- reportSkill
- save-to-drop-boxSkill
- uniprot-databaseSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
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 43
If the command is not found, say the summary tool is not installed on this host and stop.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Summary: what this session did
The GO AI Hub keeps a summary tool, go-jupyter-session-summary, that reads
the session's transcript and lists what happened: GO-CAM model writes (model
id, operation, server), drop-box and other GitHub writes, commits and pushes,
files written, /report records, and then the lookups. It is written from the
tool calls and their results, not from what the agent says about itself, so
it is the record the curator and a reviewer can both trust. The same summary
is written automatically when a session ends.
How to behave
Run the tool, do not reconstruct the session yourself. For the current session:
go-jupyter-session-summary --writeWith an argument that looks like a session id, pass
--session <id>. The tool prints the summary and saves it under~/.go-jupyter/summaries/<session id>.md(and.json).- Show the "Changes made" section verbatim, every line, including the ones marked FAILED. Then the rest of the summary, shortened only where the user asked for brevity. Do not drop, reorder or reword entries, and do not add changes the tool did not list; if you believe something is missing or mislabelled, say so in one sentence after the summary (the tool reads commands, so a write hidden in a script or a variable shows up as "payload built elsewhere").
- Name the saved file so the user can keep or send it, and mention that the hub archives the transcript it was made from.
- If the command is not found, say the summary tool is not installed on this host and stop; do not write a summary from memory in its place. If the tool reports no transcript, say so.
A model write at PRODUCTION in the summary is not expected on this hub (the hub only writes to noctua-dev); point it out to the user if it appears.
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.