update-dependencies
Skill7 starsChanged 11 days agoMITView on GitHub
Update this repo's toolchain and app dependencies, only when asked.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- Kindness-Kismet/Storage-redirection-X-Publictheir own version, first seen Nov 9, 2026
- sesori-ai/sesori_apps_monorepotheir own version, first seen Nov 8, 2026
- Krzysztof318/MailFathomtheir own version, first seen Nov 7, 2026
- heypinchy/pinchytheir own version, first seen Nov 6, 2026
- nateberkopec/dotfilestheir own version, first seen Nov 2, 2026
- AlvaroVFon/skillstheir own version, first seen Nov 1, 2026
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- microsoft/fluentui-blazor★ 4.9ksame name
- danbooru/danbooru★ 2.9ksame name
- testcontainers/testcontainers-node★ 2.6ksame name
- IndrajeetPatil/ggstatsplot★ 2.2ksame name
- GoogleCloudPlatform/magic-modules★ 975same name
- Kindness-Kismet/Storage-redirection-X-Public★ 527same name
- microsoft/dcp★ 195same name
- heypinchy/pinchy★ 192same name
- nateberkopec/dotfiles★ 157same name
- sesori-ai/sesori_apps_monorepo★ 140same name
10 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 repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-browserSkill
- applySkill
- browserSkill
- closeSkill
- connectSkill
- continueSkill
- dailySkill
- dream-memorySkill
- exploreSkill
- hand-overSkill
- improve-codeSkill
- lessonSkill
- memorySkill
- paste-this-into-your-aiSkill
- planSkill
- saveSkill
- scheduleSkill
- servicesSkill
- shipSkill
- shopSkill
- verifySkill
- wong-setupSkill
- wong-syncSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
0
Distinctive
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 16
needs you:: ask first, per required tools. - Very specific: line 17
major:: read the linked notes and migrate.
“Common” is measured: kept by at least 6 in 10 of the 20 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
/update-dependencies
This skill is meta-repo only: it is absent from the payload inventory, so no target gets it, and editing only it is no payload release. Run it on demand, never on a schedule.
Run the script
Run node .claude/skills/update-dependencies/scripts/update.mjs and watch its log; in Claude Code, start it in the background. It surveys every tool, app/, scripts/tests/, and site/, updates what is behind, majors too, and moves every OpenSpec pin together; update-dependencies.test.mjs fails, naming the file, when one pin differs. Act on its lines:
FAIL: fix what it names, then rerun; finished stages report current.needs you:: ask first, per required tools.major:: read the linked notes and migrate. One you can't: restore its old range and rerun with--hold <package>; name it in the report.openspec:: the contract test ran. Check the release notes against the shared contract and adapt the owning WongStack skill; never accept a missing field silently. No generated layer exists: never runopenspec updateor regenerateopenspec-*skills.status: current: say so and stop without/save.
Payload files changed → follow the release rule; otherwise say why no release is due.
Hand off
Pass a nonempty diff to /save; the change loop owns git and the gate. Fix what CI catches, and never claim green CI proves every major safe. Report what moved, each major's migration or hold, the contract result, and the checks CI ran.
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.

