vercel-deploy-claimable
Skill2 starsChanged 7 months agoMITView on GitHub
Prepare or execute a claimable Vercel deployment for a local web project by packaging source, inferring framework, and optionally calling an imported deploy helper that returns preview and claim URLs. Use when the user explicitly wants a Vercel deployment or a deployment-ready package/assessment.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- xfstudio/skillstheir own version, first seen Oct 13, 2026
- ai4brands-design/claude-skillstheir own version, first seen Mar 22, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- xfstudio/skills★ 9same name
- ai4brands-design/claude-skills★ 2same name
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 repository47 other files it gives its agents.
- brainstormingSkill
- claude-code-termux-runbookSkill
- cli-patcherSkill
- code-review-workflowSkill
- commit-commandsSkill
- consulting-analysisSkill
- context7-cleanSkill
- data-analysisSkill
- deep-researchSkill
- edit-tool-compat-guardSkill
- env-managerSkill
- executing-plansSkill
- feature-devSkill
- firecrawlSkill
- frontend-designSkill
- gateway-device-pairingSkill
- githubSkill
- glibc-prebuilt-bundleSkill
- gogSkill
- image-generationSkill
- memory-setupSkill
- module-auditorSkill
- module-scaffoldSkill
- openclaw-config-guardianSkill
- openclaw-ollama-runtime-kbSkill
- plugin-cutover-guardianSkill
- plugin-runtime-guardianSkill
- python-env-managerSkill
- self-improving-agentSkill
- simplify-and-hardenSkill
- skill-benchSkill
- skill-creatorSkill
- skill-unificationSkill
- skill-vetterSkill
- socratic-groundingSkill
- subagent-orchestrationSkill
- systematic-debuggingSkill
- tailscale-oauth-bridgeSkill
- termux-packagerSkill
- termux-runnerSkill
- test-driven-developmentSkill
- verification-before-completionSkill
- video-generationSkill
- workspace-cleanupSkill
- writing-plansSkill
- yt-dlp-ingest-firstSkill
- zero-downtime-cutoverSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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
- Distinctive: line 63
If packaging would otherwise mutate the source tree, use a staging copy first or stop and report.
- Very specific: line 68
If a static HTML rename workaround is needed, stage a copy under .ops/staging/ instead of mutating source in place.
- Distinctive: line 70
Only with explicit approval, invoke the helper.
- Very specific: line 71
If the workflow exposes a critical install path (for example /install.sh), test that path explicitly after deploy instead of assuming …
- Distinctive: line 72
When the installer host is already canonical/fixed, prefer a static bootstrap over a dynamic serverless endpoint for the install path.
- Distinctive: line 84
treat as failed deploy; do not invent success.
- Distinctive: line 93
no fabricated deploy result
- Distinctive: line 94
no unsafe in-place source mutation for packaging convenience
≈ “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
Vercel Deploy Claimable
Indexed Reference Map
- @[SKILL.md#L1-L96] Frontmatter, scope, KB notes, trigger rules, SOP, error handling, output contract.
- @[references/INDEX.md#L1-L12] Reading order and file map.
- @[references/QUICK_REFERENCE.md#L1-L20] Trigger boundary, approval split, and stop conditions.
- @[references/CORE_API.md#L1-L33] Packaging/deploy contract, helper behavior, mutation risk, and output semantics.
- @[references/PATTERNS.md#L1-L18] Staging-first and deployment safety patterns.
- @[references/EXAMPLES.md#L1-L28] Representative deploy requests and handling.
- @[references/AI_WORKFLOW.md#L1-L13] Bounded orchestration flow.
- @[scripts/deploy.sh#L1-L249] Imported external deploy helper.
Scope
- In-scope:
- assess whether a local project is a suitable target for claimable Vercel deploy
- prepare a deployment package or staging copy for review
- execute the imported deploy helper only when external deployment is explicitly approved
- Out-of-scope:
- silent deployment without approval
- mutating the source project in place just to satisfy deploy packaging assumptions
- claiming a deployment succeeded without actual preview/claim URLs
KB Mode Notes
- Reading order:
references/INDEX.mdreferences/QUICK_REFERENCE.mdreferences/CORE_API.mdreferences/PATTERNS.mdreferences/EXAMPLES.mdreferences/AI_WORKFLOW.mdscripts/deploy.sh
- Coverage Matrix:
- trigger boundary + approval split ->
QUICK_REFERENCE.md - packaging/deploy contract + helper behavior ->
CORE_API.md - staging and source-protection patterns ->
PATTERNS.md - representative use cases ->
EXAMPLES.md - orchestration order ->
AI_WORKFLOW.md
- trigger boundary + approval split ->
- Portability note:
- Local governance forbids blind network deploys and in-place source mutation; re-check endpoint trust, packaging path, and rollback discipline before porting.
Trigger Rules
- Positive:
- The user explicitly wants to deploy a project/site to Vercel.
- The user wants a preview deployment, live preview URL, or claimable deployment link.
- The task needs a deployment-readiness assessment or package before deploy.
- Negative:
- The user only wants build/debug help without deployment.
- The source tree must remain untouched and no staging path is available.
- External deployment/network write is not approved.
- Escalation:
- Actual deployment is an external write and requires explicit approval.
- If packaging would otherwise mutate the source tree, use a staging copy first or stop and report.
SOP
- Confirm the target project path and whether the user wants assessment/package-only or real deploy.
- Inspect the project minimally for deploy suitability and likely framework signals.
- If a static HTML rename workaround is needed, stage a copy under
.ops/staging/instead of mutating source in place. - Prepare package/deploy notes and surface expected behavior.
- Only with explicit approval, invoke the helper.
- If the workflow exposes a critical install path (for example
/install.sh), test that path explicitly after deploy instead of assuming success from the preview URL alone. - When the installer host is already canonical/fixed, prefer a static bootstrap over a dynamic serverless endpoint for the install path.
- Return preview URL + claim URL only if deployment actually succeeded.
- Otherwise return assessment/package-only status truthfully.
Error Handling
- Missing project path or unsupported input:
- report the exact missing requirement.
- Packaging would mutate source:
- switch to staging copy or stop.
- Network/deploy failure:
- report the real stderr/response class and keep the project untouched.
- Missing preview/claim URL:
- treat as failed deploy; do not invent success.
Output Contract
- Deliverables:
- project path assessed
- staging/package path if created
- preview URL + claim URL only on real success
- Validation:
- no silent deployment
- no fabricated deploy result
- no unsafe in-place source mutation for packaging convenience
- Compliance Verdict:
PASSwhen assessment/deploy status is reported truthfully with real artifacts/URLs.
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.

