portfolio-publish
Skill0 starsChanged 49 days agoMITView on GitHub
Publish an approved portfolio package into the user's portfolio website codebase (card + case study page + optimized screenshots), adapting to the site's existing content model. Use whenever the user says /portfolio-publish, asks to add/publish a project to their portfolio site, or wants the case study integrated into the website repository. Publishes to the codebase only, never deploys to production.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- imMamdouhaboammar/portfolio-interviewtheir own version, first seen Sep 24, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- imMamdouhaboammar/portfolio-interview★ 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 repository3 other files it gives its agents.
- portfolio-pipelineSkill
- portfolio-reviewSkill
- portfolioSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Read ../portfolio-pipeline/references/publishing-policy.md and privacy-policy.md before acting.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
/portfolio-publish — Publisher
Integrate an approved .portfolio/ package into the portfolio website repository. "Publish" means PUBLISH TO PORTFOLIO CODEBASE; production deploy happens only if the user explicitly asks in this conversation.
Read ../portfolio-pipeline/references/publishing-policy.md and privacy-policy.md before acting. Validate with ../portfolio-pipeline/scripts/validate_project.py.
Gates (check in order, stop at the first failure)
.portfolio/exists in the current project.project.jsonvalid against the schema.REVIEW.mdexists and is a real review, not the placeholder.verification.approvedForPublishistrue.- Portfolio target known (config or discovery below).
On failure, tell the user exactly which gate failed and the command that fixes it (usually /portfolio or /portfolio-review).
Target configuration
Persistent config: ~/.claude/portfolio/config.json:
{
"portfolioRepository": null,
"portfolioLocalPath": null,
"projectDataDirectory": null,
"projectAssetsDirectory": null,
"projectRoutePattern": null,
"defaultLanguage": "it",
"brandName": null,
"publishMode": "repository"
}If values are null, try to detect the portfolio site automatically (a local repo whose content matches a personal/studio portfolio). If detection fails, ask the user only for the indispensable values (typically the local path), write them to the config, and reuse them in every future session. Never invent values.
Discovery before writing
Analyze the target repo first: stack, content model, data model for projects, routes, how cards and case study pages are built, asset/image pipeline, localization, components, build process. If a projects/case-studies model exists, map project.json onto it; do not build a parallel system. If none exists, propose the minimal addition consistent with the site's conventions and get the user's ok before scaffolding.
Publish
Follow the steps in publishing-policy.md: map data, copy and optimize screenshots, create/update card and case study page reusing existing components, idempotent by slug (existing slug = update in place, never duplicate), run formatter/linter, run the build (a failing build means not published), run relevant tests, verify the page locally when possible (browser tools or local server).
Immediately before writing anything into the target: final privacy sweep (PII, credentials, internal data, reserved screenshots, sensitive URLs, unauthorized names, unverified claims). Concrete doubt = leave that piece out and flag it.
Bookkeeping
On success update the source project's project.json (publication.published = true, target, publishedAt) and pipeline.json (publishedToRepository, portfolioBuildPassed, lastStep, updatedAt). Report to the user: what was created/updated in the target repo, build result, how to preview, and that no production deploy was performed.
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.

