All skills
jwynia avatar

/competency

@6ac6c30
by J Wyniajwynia/agent-skills160 stars
20

Guide competency framework development and operation. Use when building training that produces capability, when existing training doesn't produce competence, when structuring knowledge for multiple audiences, or when setting up feedback loops to surface gaps.

  • 5 files
  • 30.9 KB
  • MIT
  • Updated 8 months ago
  • GitHub

Use this Skill: https://skilld.dev/gh/jwynia/agent-skills/competency

This session only. Nothing lands on disk.

templatescompetency-definition.md

≈497 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Competency Definition Template

Use this template to define competencies. Each competency must be an observable capability.

Template

## [Cluster Name] Competencies

| ID | Competency | Description |
|----|------------|-------------|
| [PREFIX]-1 | [Action verb phrase] | Can [observable capability that you could watch someone demonstrate] |
| [PREFIX]-2 | [Action verb phrase] | Can [observable capability] |

Checklist

Before finalizing each competency, verify:

  • Starts with "Can" + action verb
  • Describes something you could observe
  • Two people could agree/disagree whether someone has it
  • Not too broad (applies to too many situations)
  • Not too narrow (only applies to one exact situation)
  • Connected to a real decision or action

Good vs. Bad Examples

Bad (knowledge state) Good (observable capability)
"Understands data policies" "Can classify data according to organizational categories"
"Knows the approval process" "Can determine required approval level for a given expense"
"Familiar with the tool" "Can configure the tool to accomplish [specific task]"
"Aware of security requirements" "Can identify security implications of a proposed change"

ID Conventions

  • Use 2-4 letter prefix based on cluster name (e.g., DP- for Data Privacy)
  • Sequential numbers within cluster
  • Keep IDs stable once assigned (don't renumber)

Deriving Competencies from Failure Modes

  1. List mistakes people make
  2. For each mistake, identify what someone would need to DO to avoid it
  3. Write that as a competency
  4. Verify it's observable

Example:

  • Failure: "People put customer data in public AI tools"
  • What would prevent it: Recognizing that data is sensitive + knowing which tools are approved
  • Competencies:
    • "Can classify data according to sensitivity levels"
    • "Can identify which AI tools are approved for which data types"

Source: SKILL.md on GitHub

No third-party reports yet.

Signed by skilld at 6ac6c30. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Dormantupdated 8 months ago
Other metadata
metadata
{
  "author": "jwynia",
  "version": "1.0",
  "domain": "competency",
  "cluster": "methodology",
  "type": "diagnostic",
  "mode": "assistive"
}

README badge

README badge for jwynia/agent-skills/competency