Skip to the rows

agentsclimarketplace

Ontology planning team

Skill Mokee04/ontology_research/ontology-planning-team

Hierarchical agent skills for domain ontology planning, research, construction, and validation with saved research artifacts and eval-ready workflows.

Install

npx -y skills add Mokee04/ontology_research --skill ontology-planning-team

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Plan a domain ontology effort by clarifying scope, composing the working team, defining competency questions, and setting risk and approval gates before research begins.

SKILL.md

3.2 KB, 680 tokens by cl100k_base, as published. Nobody here has run it

Ontology Planning Team

Read:

../refs/Total Guide.md
../shared/references/skill-family-architecture.md
../shared/references/templates.md

Use this skill for the planning stage only.

Planning Segments

Segment	Goal	Required user feedback
P1 Intent clarification	identify the real target outcome and constraints	yes
P2 Scope framing	define in-scope, out-of-scope, users, and success target	yes
P3 CQ drafting	turn goals into answerable questions	yes
P4 Planning package	team plan, risks, approval gates, technical plan	yes

Team Composition

Route planning work through:

ontology-domain-intake
ontology-cq-designer
ontology-technical-plan-writer when the user wants a reusable technical planning document

Tasks

Start by asking targeted clarification questions before drafting the ontology plan.
Ask the mandatory planning intake questions below unless the user has already answered them clearly.
Do not create intent-clarification.md or any other planning artifact until the user has answered enough intake questions to distinguish confirmed facts from assumptions.
Capture the answers in intent-clarification.md using a table that distinguishes confirmed facts, assumptions, and open questions.
Clarify domain, purpose, users, decisions to support, and scope boundaries.
Record out-of-scope areas and risk constraints.
Draft initial competency questions.
Identify which later team skills will be required.
Define human approval gates before research and release.
Pause after each segment and ask the user for confirmation, correction, or reprioritization.

Mandatory Planning Intake Questions

Ask for concrete answers to these topics before drafting the planning package:

What is the first business or operational outcome this ontology must unlock?
Which 3 to 5 competency-question-like business questions matter most right now?
Who are the primary users and downstream systems?
What data already exists for each core entity or axis?
What predictions, classifications, or recommendations are expected later?
What is out of scope for the first release?
What privacy, consent, licensing, or governance constraints apply?
What deliverable shape does the user want from this phase?

Outputs

Write or update:

../exe/<run-id>/planning/intent-clarification.md
../exe/<run-id>/planning/scope.md
../exe/<run-id>/planning/competency-questions.md
../exe/<run-id>/planning/team-plan.md
../exe/<run-id>/planning/risks.md
../exe/<run-id>/planning/technical-plan.md when a technical planning document is requested

Exit Criteria

Do not hand off to research until:

the user's target outcome has been clarified and acknowledged
the mandatory planning intake questions have been answered enough to bound the work
scope is bounded
at least a starter CQ set exists
required standards or constraints are named
human review gates are explicit
a planning checkpoint has been reviewed with the user

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.