Turn a real workflow into a tested, installable agent skill—then publish it safely to your team. Website · Installation · Worker runbook · Team marketplace · Agent Skills Platform turns the way people already work into tested, installable agent skills.
> /plugin marketplace add FrancyJGLisboa/agent-skills-platform> /plugin install agent-skills-platform@agent-skills-platform
What's inside
Turn a real workflow into a tested, installable agent skill—then publish it safely to your team.
Website · Installation · Worker runbook · Team marketplace · Product scope
Agent Skills Platform turns the way people already work into tested, installable agent skills. Give it a prompt plus the evidence behind the work—spreadsheets, reports, emails, screenshots, transcripts, links, or scripts—and it builds a reusable workflow that a person can inspect, an organization can review, and a team can safely reuse.
/agent-skills-platform
Turn my monthly revenue-variance review into a reusable internal skill.
I attached past reports and the source spreadsheets. The decision is whether to
escalate a material variance. It must not modify source data.
The result is not just a prompt: it is an installable skill package with instructions, functional scripts when needed, evals, security checks, a representative-run record, and a correction path for real-world learning.
After release, a skill can retain maintenance evidence without turning every log
into runtime prompt context: classified run evidence is captured in raw/, recurring
findings become evidence-linked draft patterns in wiki/, and only a separately
validated change may update the executable skill. This is a governed maintenance
record, not autonomous self-modification.
Choose the path that matches what you need today.
First question: is this skill just for you, or will teammates install or reuse the skill itself?
Teammates receiving a report or queue does not require a marketplace. Use the team path only when teammates will install or reuse the skill.
Open the AI agent you already use, attach examples of the work, and paste this:
/agent-skills-platform
Turn my monthly revenue-variance review into a reusable internal skill.
I attached past reports and the source spreadsheets. The decision is whether to
escalate a material variance. It must not modify source data.
The creator asks for the business decisions only you can authorize, builds and tests the skill, and shows a representative result. When it is correct, say: “Publish this to the Finance marketplace.”
When the workflow uses an API, database, MCP, codebase, or structured file, Semantic
Recon runs automatically before implementation and creates a pinned data contract.
Use ./install.sh --without-semantic-recon only for a deliberately local,
source-free installation.
Do not use Git, edit registry files, or run marketplace commands. If the creator is not installed in your agent, send this section to your marketplace operator.
Give them the desktop app: download, paste the team-library link, click Install. Skills land in GitHub Copilot (or the tool they pick) with no terminal, Python, or Git involved. The same page shows admins how to create a library in four commands.
Use the governed team marketplace guide to admit, approve, release, distribute, update, quarantine, and roll back tested skills.
Read the product scope, organizational acceptance protocol, and technical implementation guide.
reliability).SME supplies examples and approves the result
↓
Creator builds and verifies a skill
↓
Marketplace operator governs and publishes it
↓
Colleagues install an approved version and use it
The SME owns business meaning. The marketplace operator owns distribution and policy. See roles and handoffs.
The repository includes a live, read-only weather briefing example with a source-linked result and verification evidence. Start with the verification record, then inspect the skill package.
| Need | Read |
|---|---|
| Install on a supported AI tool | Installation |
| Let non-technical teammates browse and install skills | Desktop app |
| Create, correct, and hand off a first skill | Worker runbook |
| Run a governed internal marketplace | Team marketplace |
| Test a skill inside a real agent and certify it per runtime | Caliper pilot |
| Understand scope and product boundaries | Product scope |
| Review architecture, validation, and technical controls | Technical overview |
| Contribute | Contributing |
An Agent Skill is a reusable workflow package that guides an agent from a recognized situation to a verified outcome. It can use retrieved knowledge, MCP tools, APIs, deterministic scripts, and agent judgment, but it is not itself a RAG system, MCP server, or agent runtime.
RAG supplies knowledge. MCP supplies capabilities. The harness supplies execution. A skill organizes them into a governed path toward a verified outcome.
Reason where interpretation is necessary. Execute and verify with deterministic controls where reproducibility matters. External models, APIs, and changing data may vary rather than promising identical outputs.
Humans establish meaning. The factory does not expect you to know the correct prompt or semantic contract; it asks one bounded question at a time. The flow is:
Every skill is checked as one connected system. The skill graph links its
instructions, scripts, evaluations, and expected outputs. Two structural
requirements confirm that every expected result is tested and every predictable
multi-step workflow has one reliable entry point. Four checks—specification,
pipeline, security, and evaluation schema—run in parallel. Finally, a
representative run proves that the skill produces a useful result. The graph also
enforces every_expected_is_reachable and deterministic_multistep_has_orchestrator.
After intake, team_marketplace.py reliability can run the skill inside each installed
agent runtime k times and certify only what an agent actually discovered and followed
(Caliper).
See CONTRIBUTING.md and CODE_OF_CONDUCT.md. Contributions require the contributor assignment.
MIT. See LICENSE. Copyright © 2026 Francy J G Lisboa, also known as Charuto. See ownership.
View @francyjglisboa’s profileTurn a real workflow into a tested, installable agent skill—then publish it safely to your team. Website · Installation · Worker runbook · Team marketplace · Agent Skills Platform turns the way people already work into tested, installable agent skills.
@francyjglisboaFAQ
francyjglisboa-agent-skills-platform-2 is a Claude Code plugin with 1 hand-picked skill for skill authoring work, indexed on Flowy. Install it with the command on its page. It includes agent-skills-platform. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it