vendor-sync
Skill2 starsChanged 14 days agoApache-2.0View on GitHub
Move a vendored upstream (HyperFrames, LangSmith skills, Deep Agents skills) to a newer pin, re-vendor its skills unmodified, verify them, and update everything that depends on the pin.
- Installs packages
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 31
Read what changed on main of langchain-ai/langsmith-skills or langchain-ai/langchain-skills since the pinned commit, then bump that entry's …
- Very specific: line 35
If langsmith-trace changed, check its one-line summary in config/vendored-skills.toml still steers the deployed agent to list_traces and …
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Update vendored skills
Vendored skills are never edited; they are replaced from upstream at a commit and checked against
skills-lock.json in CI. Each upstream's pin lives in UPSTREAMS in
src/design_agent/skills_lock.py, with the skills it vendors into skills/ (runtime) and
.agents/skills/ (coding agents). uv run design-agent skills sync-vendor --check-only compares
every pin with its upstream's newest release (HyperFrames) or main commit (LangChain's packs).
HyperFrames
- Pick the release: the latest stable HyperFrames tag (never a prerelease) and its commit. Read its
changelog for CLI changes (flags, renamed or deprecated commands such as
validate→check). - Bump the
hyperframesentry'scommitandreleaseinUPSTREAMS, thehyperframesversion insandbox/render/package.json, thennpm install --package-lock-onlyinsandbox/render/anduv run python scripts/sync_sandbox_recipe.py(embeds the lock insetup.sh). uv run design-agent skills sync-vendor --upstream hyperframes; reviewgit diff skills/ skills-lock.json. Check the exclusion list still catches third-party media, unlicensed fonts and bundled libraries. Upstream skills carry their own.gitignores:git add -fany locked file they hide (test_git_tracks_every_locked_filenames them).- Rebuild and prove:
uv run design-agent sandbox build,sandbox test,uv run pytest -q -m render,uv run design-agent demo. MDA deployments needsandbox publishagain, since the recipe changed.
LangSmith and Deep Agents skills
- Read what changed on
mainoflangchain-ai/langsmith-skillsorlangchain-ai/langchain-skillssince the pinned commit, then bump that entry'scommitinUPSTREAMS. uv run design-agent skills sync-vendor --upstream langsmith-skills(orlangchain-skills); reviewgit diff skills/ .agents/skills/ skills-lock.json.- If
langsmith-tracechanged, check its one-line summary inconfig/vendored-skills.tomlstill steers the deployed agent tolist_tracesandread_trace: its sandbox has no network and no LangSmith key, so the CLI the skill teaches cannot run there.
Every upstream
- New or renamed runtime skills: add a one-line summary to
config/vendored-skills.toml, and the folder toextend-excludeinpyproject.toml(tests fail until both match the lock). New coding-agent skills need a route inAGENTS.md(test_coding_agent_skills.pychecks). - Prove:
uv run design-agent skills verify,uv run pytest -q. - Record the new pin and anything that changed in
NOTICE.md,docs/sources/andCHANGELOG.md.
In this repository53 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- brand-onboardingSkill
- deep-agents-coreSkill
- deep-agents-memorySkill
- deep-agents-orchestrationSkill
- design-agent-customizeSkill
- design-agent-deploySkill
- design-agent-evalsSkill
- design-agent-onboardingSkill
- design-agent-troubleshootSkill
- design-agent-updateSkill
- langsmith-datasetSkill
- langsmith-evaluatorSkill
- managed-deep-agentsSkill
- release-checkSkill
- brand-designSkill
- content-briefSkill
- data-vizSkill
- design-wikiSkill
- embedded-captionsSkill
- faceless-explainerSkill
- film-breakdownSkill
- general-videoSkill
- gif-editSkill
- hyperframes-animationSkill
- hyperframes-audioSkill
- hyperframes-cliSkill
- hyperframes-coreSkill
- hyperframes-creativeSkill
- hyperframes-keyframesSkill
- hyperframes-registrySkill
- hyperframesSkill
- image-generationSkill
- image-opsSkill
- langsmith-traceSkill
- launch-filmSkill
- media-productionSkill
- media-useSkill
- motion-directionSkill
- motion-graphicsSkill
- music-to-videoSkill
- paper-designSkill
- pr-to-videoSkill
- reference-studySkill
- remotion-to-hyperframesSkill
- slideshowSkill
- soundSkill
- stillsSkill
- storyboardSkill
- thumbnailsSkill
- visual-verifySkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

