Framework from existing material
Convert scattered role documents into a single structured framework with consistent language.
— Talent & Leadership
Build a competency framework
Groups and merges skills from role profiles, standards and existing drafts into a single structured, consistently worded competency framework.
- Talent & Leadership
- Traceable reasoning
- Runs anywhere
2–3 weeks → ~15 minutes
For one complete, review-ready pass
No coding required
- Input
- Role profiles, standards or existing framework material
- Output
- A structured, grouped competency framework
- Runs in
- Skillsize · ChatGPT · Claude · Copilot
- Export
- SKILL.md · MCP
- Time saved
- ~2–3 weeks per run
— USE CASES
What people use Build a competency framework for
Modernising a dated framework
Refresh wording and structure while retaining the competencies the business already recognises.
Function-specific frameworks
Build a framework for one function that still fits the wider architecture.
What it works from
- Role profiles, standards or existing framework material
- Your level and behaviour conventions
- The population the framework must cover
What you get back
- A structured, grouped competency framework
- Merged duplicates and consistent naming
- A framework you can extend rather than replace
— HOW IT BEHAVES
How Build a competency framework produces its result
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Criteria-based analysis
Material is assessed against explicit criteria you control, so the same standard is applied on every run.
Structured extraction
Facts, fields and entities are lifted out of unstructured material and held in a consistent shape.
Grounded in your own material
The run works from documents and data you supply, so conclusions are anchored to your evidence rather than to general model knowledge.
Reshaped for use
Content is restructured into the form your deliverable or downstream system expects.
Why this is expensive by hand
Build a competency framework is routine in name only: the inputs are messy, the standard is unwritten, and two people rarely reach the same answer. Framework from existing material is the typical trigger — convert scattered role documents into a single structured framework with consistent language. Done properly it is defensible; done at pace it becomes a judgement call nobody can retrace. And "properly" usually means 2–3 weeks of manual work.
How this Skill produces it
Here the same job runs as a Skill. Your material goes in; a structured, grouped competency framework comes out, alongside merged duplicates and consistent naming. The criteria, ordering and review points that make the answer trustworthy are encoded in the Skill itself — which is the difference between a structured method and a prompt someone pastes in. The practical effect: 2–3 weeks of manual work becomes a ~15 minutes run, held to an identical standard on the tenth engagement as on the first.
Who it's for
- Independent consultants codifying their own methodology
- Strategy and transformation teams standardising delivery
- Internal advisory functions under pressure to produce faster
- Operators who need defensible output, not a one-off chat answer
Run it in Skillsize — or export it anywhere
Build a competency framework exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
ChatGPTClaudeCopilotAI Products (MCP)
More Talent & Leadership Skills
Browse the full library →Talent & Leadership
Role benchmark research
Researches how a role is defined externally and reshapes the findings into a structured benchmark you can hold your own definition against.
Talent & Leadership
Potential and readiness
Assesses potential and readiness separately against calibrated criteria, showing the supporting evidence behind each bucket for talent review discussions.
Talent & Leadership
Screen against a Blueprint
Screens candidate evidence against a saved Blueprint, applying the same calibrated bar and traceable reasoning to every applicant.