In this reference, an AI skill means a reusable set of instructions and supporting material for a specific task. Product implementations vary; the governance comes from how your team defines, tests and maintains it. It defines the inputs, ordered instructions, evidence requirements, guardrails, and expected output so a team can apply the same organizational method across programs and workflows. Skills improve consistency and auditability, but people still verify evidence and own consequential decisions.
- Choose one repeated task worth standardizing.
- Define the required inputs and authoritative sources.
- Write the method and decision rules.
- Specify the output and evidence citations.
- Add privacy, fairness, and human-review guardrails.
- Test the skill on varied fictional or authorized examples and version what changes.
What is an AI skill?
An AI skill packages organizational know-how into a method that can be reused. Examples include building a data dictionary, reviewing a theory of change, mapping indicators to standards, analyzing open-ended evidence, or preparing a cited reporting brief.
A prompt can be reused too. The useful distinction here is packaging and maintaining a method with its supporting material: what information is acceptable, what steps must occur, how uncertainty is treated, what the output must contain, and what a person must verify.
What should every skill contain?
Use five parts: Definition → Instruction → Evidence → Guardrails → Output.
| Part | Question it answers | Example |
|---|---|---|
| Definition | What exact job does this skill perform? | Define one outcome indicator for use across three programs. |
| Instruction | What ordered method must it follow? | Identify construct, unit, population, calculation, cadence, and disaggregation. |
| Evidence | Which sources may support the output? | Approved program documents and the governed data dictionary. |
| Guardrails | What must it never infer or decide? | Do not invent a definition; flag conflicts for the data owner. |
| Output | What reusable artifact should it produce? | A dictionary entry with definition, formula, owner, source, and version. |
How are skills different from templates and prompts?
A template provides a reusable output structure. A prompt supplies instructions and can itself be reused. A skill package brings instructions, references and examples together; your team still supplies the ownership, evaluation and change controls. A useful skill can use prompts and templates, but also carries evidence rules, quality checks, ownership, and version history.
Worked example: one definition for employment status
Illustrative example. Three workforce programs all report “employed,” but one counts any paid work, another requires 20 weekly hours, and a third counts only employment retained for 90 days. The data-dictionary skill should not silently choose one definition. It should surface the conflict, show which reports use each version, and ask the measurement owner to approve a governed definition—or retain clearly named variants when funder contracts require them.
The resulting entry records the construct, precise definition, allowed values, effective date, data owner, collection source, reporting uses, and every exception. The skill should reference that approved entry in later work. Check the output against it; reusable instructions do not guarantee that a model will preserve the meaning correctly.
Where do AI skills help in the Academy?
Use these methods within the eight workflow courses. A case team might reuse a case-note review method; an applications team, a rubric check; a portfolio team, a standards-mapping review. Membership, training, supplier, customer and employee teams can reuse appropriate collection, coding and reporting methods. This reference does not add another course.
How do you test an AI skill?
Test whether it follows the method across ordinary, incomplete, contradictory, multilingual, and edge-case inputs. Check its citations, missing-information behavior, consistency across repeated runs, and treatment of different participant or applicant groups.
Do not approve a skill because one demonstration looks good. Keep a small evaluation set, document failures, require source citations, and record human overrides. For decisions affecting people or funding, people retain final authority.
The one thing to do this week
Choose one definition, analysis rule, or reporting method your team repeatedly reconstructs. Write its five parts—Definition, Instruction, Evidence, Guardrails, and Output—and test it against two fictional or authorized examples that disagree. The disagreement is where the reusable method becomes valuable.
Frequently asked questions
What is an AI skill in simple terms?
An AI skill is a reusable method for one task. It tells the system what inputs to use, which steps to follow, what evidence to cite, what it must not assume, and what output to produce.
Is an AI skill just a long prompt?
A long prompt can contain much of the method. A maintained skill package can also include evidence rules, decision criteria, quality checks, guardrails, output structure, ownership, testing, and version control.
Why are AI skills not an Academy course?
They are a reference used inside your chosen workflow. Return to the relevant module with one tested method rather than starting another course.
Do AI skills guarantee identical output every time?
No. Generative systems may vary. Fixed instructions, approved definitions, citations, evaluation examples, and human review make outputs more consistent and auditable; they do not create a universal guarantee of identical wording or judgment.
Who should approve an organizational skill?
The accountable method or data owner should approve it. Technical staff can implement the skill, but program, measurement, compliance, and subject-matter owners must verify definitions, evidence rules, and decision boundaries.
What should an AI skill never do?
It should not invent missing evidence, conceal contradictions, make unsupported causal claims, or take final authority for high-stakes decisions affecting applicants, grantees, participants, or investments.