Agent skill
skill-marketplace-publisher
Publish a Codex or Claude skill to Skillstore, SkillMap, or similar public skill marketplaces. Use when you need to audit a skill for public safety, build a public package, create a public GitHub repo, or submit a repo URL to marketplace intake endpoints.
Install this agent skill to your Project
npx add-skill https://github.com/aiskillstore/marketplace/tree/main/skills/sliense-ysd/skill-marketplace-publisher
SKILL.md
Skill Marketplace Publisher
Overview
Use this workflow when a local skill should become a public, reviewable marketplace submission. It covers four things end-to-end: public-safety audit, public packaging, GitHub publication, and marketplace submission.
This skill is optimized for:
Skillstoreself-serve submissionSkillMaplisting request via its current public intake channels- any future marketplace that expects a public GitHub repo with a valid
SKILL.md
Required Inputs
Before running the workflow, confirm:
- the source skill path
- the target marketplace list
- the public GitHub repo owner/name
- whether the source skill is already public-safe or must be packaged in
publicmode first
If the user asks to publish a skill but does not say otherwise, assume:
- target mode:
public - source of truth stays in
ai-shared/skills/ - packaged output goes to
ai-shared/skill-packages/
Workflow
Step 1: Audit Public Safety
Run the local scanner first. It looks for secrets, local absolute paths, secret-hub references, and obvious non-portable material.
python3 scripts/public_skill_audit.py /absolute/path/to/skill
Interpretation:
- no
HIGHfindings: okay to continue HIGHfindings: stop and sanitize firstMEDIUMfindings: review manually before publishing
If the skill references shared secrets, local private paths, or owner-only runtime assumptions, do not publish the source folder directly.
Step 2: Decide Source vs Public Package
If the skill is already self-contained and clean, you may publish the source skill directory directly.
If the skill is not obviously portable, package it in public mode:
python3 ../../skill-package/scripts/skill_package.py analyze /absolute/path/to/skill
python3 ../../skill-package/scripts/skill_package.py build /absolute/path/to/skill --mode public
Use the packaged output as the publishable artifact for marketplaces.
Default packaged output root is the shared skill-packages/ directory configured by the local skill-package workflow.
Step 3: Validate Skill Metadata
Public submissions should include:
- a valid
SKILL.mdwith frontmatternameanddescription - supporting files referenced by the skill
agents/openai.yamlwhen available- a permissive repo-level license such as
MITorApache-2.0
Validate the skill structure before publishing:
python3 ../skill-creator/scripts/quick_validate.py /absolute/path/to/skill-marketplace-publisher
For the target skill, at minimum manually confirm:
SKILL.mdloads cleanly- referenced scripts and documents exist
- no broken relative links remain after packaging
Step 4: Publish to a Public GitHub Repo
Create a clean git repo that contains either:
- the source skill folder, or
- the public package output
Typical flow:
mkdir -p /path/to/public-repo
rsync -a /path/to/publishable-artifact/ /path/to/public-repo/
cd /path/to/public-repo
git init
git checkout -b main
git add .
git commit -m "Publish skill for marketplace submission"
gh repo create <owner>/<repo> --public --source=. --remote=origin --push
If the skill lives inside a larger repo, marketplaces that support subdirectory URLs can accept a path such as:
https://github.com/<owner>/<repo>/tree/main/path/to/skill
Step 5: Submit to Skillstore
Skillstore has a real self-serve intake endpoint. Submit the public repo or public subdirectory URL:
python3 scripts/submit_marketplace.py skillstore \
--repo-url https://github.com/<owner>/<repo>/tree/main/path/to/skill \
--notes "Public-safe skill package prepared on 2026-03-26."
Expected result:
- JSON response with
success - a
submission_id - a status URL of the form
https://skillstore.io/submissions/<id>
Save the submission ID and URL in the final delivery note.
Step 6: Send SkillMap Listing Request
As of 2026-03-26, SkillMap exposes public marketplace pages and public feedback/contact channels, but no clearly documented self-serve “publish skill” form was verified.
Use the feedback endpoint to send a listing request that includes:
- the public GitHub repo URL
- the skill summary
- installation notes if relevant
python3 scripts/submit_marketplace.py skillmap-feedback \
--repo-url https://github.com/<owner>/<repo>/tree/main/path/to/skill \
--skill-name <skill-name> \
--email you@example.com
If needed, also use the contact email listed in references/marketplaces.md.
Step 7: Record Outcome
For each marketplace, record:
- submitted URL
- submission/request timestamp
- returned submission ID or acknowledgement
- pending manual follow-up items
Formal delivery notes should be written to the user-facing outbox, not pasted only in chat.
Decision Rules
- If the source skill contains any real secrets or private business logic, do not publish the source directly.
- If the skill depends on local-only files, prefer packaged
publicoutput. - If the marketplace accepts only a repo URL, publish a dedicated clean repo.
- If the marketplace accepts a subdirectory URL, you may publish only the skill subtree.
- If a marketplace name cannot be verified with a public live submission path, mark it
unverifiedand do not pretend it is a supported route.
Current Marketplace Notes
Read these before claiming a marketplace is supported:
references/marketplaces.md
Key current state:
Skillstore: verified live submission routeSkillMap: verified live marketplace plus verified public intake channels, but no confirmed self-serve listing formCrowdHub: unverified for this workflow as of2026-03-26
Scripts
scripts/public_skill_audit.py
Checks a skill tree for:
- likely secret values
- local absolute paths
- secret-hub references
- obvious non-portable content
scripts/submit_marketplace.py
Supports:
skillstoresubmissionskillmap-feedbacklisting request
References
references/marketplaces.md: dated marketplace research and current submission paths
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
perigon-backend
Perigon ASP.NET Core + EF Core + Aspire conventions
perigon-agent
Pointers for Copilot/agents to apply Perigon conventions
perigon-angular
Angular 21+ standalone/Material/signal conventions for Perigon WebApp
fastapi-mastery
Comprehensive FastAPI development skill covering REST API creation, routing, request/response handling, validation, authentication, database integration, middleware, and deployment. Use when working with FastAPI projects, building APIs, implementing CRUD operations, setting up authentication/authorization, integrating databases (SQL/NoSQL), adding middleware, handling WebSockets, or deploying FastAPI applications. Triggered by requests involving .py files with FastAPI code, API endpoint creation, Pydantic models, or FastAPI-specific features.
context7-efficient
Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.
browser-use
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.
Didn't find tool you were looking for?