name	ai-literacy-assessment
description	This skill should be used when the user asks to "assess AI literacy", "run an assessment", "check literacy level", "evaluate our AI collaboration", "where are we on the framework", or wants to determine their team's AI literacy level using the ALCI instrument.

AI Literacy Assessment

Assess a team's AI collaboration literacy level by combining observable evidence from the repository with clarifying questions, then produce a timestamped assessment document and a README badge.

The Assessment Process

Phase 1: Observable Evidence

Scan the repository for signals that indicate which framework level the team is operating at. Each signal maps to a specific level:

Level 0-1 indicators (awareness + prompting):

Does the repo exist and contain code? (baseline)
Are there any AI-related configuration files at all?

Level 2 indicators (verification):

CI workflows that run tests (*.yml in .github/workflows/)
Test coverage enforcement (coverage thresholds in CI or build files)
Vulnerability scanning (govulncheck, OWASP, Docker Scout)
Markdownlint or other linting in CI
Mutation testing configuration

Level 3 indicators (habitat engineering):

CLAUDE.md or equivalent context engineering file
HARNESS.md with declared constraints
AGENTS.md compound learning memory
MODEL_ROUTING.md model-tier guidance
.claude/skills/ project-local skills
.claude/agents/ custom agent definitions
.claude/commands/ custom commands
Hooks configuration (hooks.json)
REFLECTION_LOG.md with entries
.markdownlint.json or equivalent config

Level 4 indicators (specification architecture):

specs/ directory with specification files
Implementation plans (plan.md, plan-*.md)
Agent pipeline with orchestrator
Plan approval gate in orchestrator
Loop guardrails (MAX_REVIEW_CYCLES)

Level 5 indicators (sovereign engineering):

Platform-level tooling (reusable plugins)
Cross-team harness templates
OpenTelemetry configuration
Organisational governance documentation
Multiple agent teams or cloud async agents

Phase 2: Clarifying Questions

After scanning, ask questions to fill gaps that observable evidence cannot answer. Focus on:

Workflow habits: "Do you write specs before code, or after?"
Verification practices: "Do you verify AI output systematically or trust it if it looks right?"
Cost awareness: "Do you know what your AI tools cost per month?"
Team practices: "Does your team have shared AI conventions, or does each developer work differently?"
Learning: "Do you capture what you learn from AI sessions?"

Ask 3-5 questions maximum. Each question should disambiguate between adjacent levels.

Phase 3: Assessment Document

Produce a timestamped Markdown document at assessments/YYYY-MM-DD-assessment.md with:

Header: team name, date, assessor, assessed level
Observable evidence: what was found in the repo (with file paths)
Clarifying responses: summary of answers
Level assessment: primary level with rationale
Discipline maturity: context engineering, architectural constraints, guardrail design — each rated
Strengths: what the team does well at their current level
Gaps: what's missing for the next level
Recommendations: 3-5 specific actions to progress
Immediate adjustments applied: what was fixed during this assessment
Workflow operation changes: accepted changes to how artifacts are used
Reflection: what the assessment itself revealed
Next assessment date: suggested quarterly re-assessment

Phase 4: Immediate Habitat Adjustments

After documenting the assessment, identify adjustments that can be made immediately — without changing any application code or requiring team discussion. These are habitat hygiene fixes:

Stale counts: If HARNESS.md Status section shows outdated counts, update them. If README badges show old numbers, update them.

Missing entries: If AGENTS.md GOTCHAS is empty but the assessment revealed gotchas, add them. If REFLECTION_LOG.md has no entries from this assessment, add one.

Drift detection: If HARNESS.md declares constraints that no longer match reality (tools removed, workflows renamed), update the declarations.

Mechanism map staleness: If the README mechanism map is missing components that the scan found (new agents, commands, hooks, skills), update it.

Present each adjustment to the user and apply it immediately. Record what was adjusted in the assessment document.

Phase 5: Workflow Operation Recommendations

Based on the gaps identified, recommend specific changes to how existing workflows and artifacts are operated (not built — the infrastructure exists, it just needs to be used differently):

Operating rhythm: Recommend cadences for harness audits, reflection reviews, mutation score checks, and cost monitoring. Suggest adding these to a calendar or checklist.

Habit formation: Identify which framework habits (from Part VII) are not yet automatic and suggest specific practice exercises.

Artifact activation: Identify artifacts that exist but are not actively used (e.g., AGENTS.md that isn't read at session start, MODEL_ROUTING.md that isn't consulted when dispatching agents) and recommend how to activate them.

Promotion opportunities: Identify unverified HARNESS.md constraints that could be promoted to agent or deterministic with available tooling.

Present each recommendation to the user. For accepted recommendations, apply the change (update CLAUDE.md with new cadences, promote HARNESS.md constraints, add operating notes to AGENTS.md). Record accepted and rejected recommendations in the assessment document.

Phase 6: Assessment Reflection

Capture a reflection on the assessment itself:

What did the scan reveal that was surprising?
Where did observable evidence diverge from the team's self-perception?
What should future assessments pay attention to?

Append this to REFLECTION_LOG.md as a structured entry.

Phase 7: README Badge

Add or update a badge in the project's README showing the assessed level:

[![AI Literacy](https://img.shields.io/badge/AI_Literacy-Level_N-COLOUR?style=flat-square)](assessments/YYYY-MM-DD-assessment.md)

Colour coding:

Level	Colour	Hex
L0	Grey	`808080`
L1	Light blue	`87CEEB`
L2	Blue	`4682B4`
L3	Teal	`20B2AA`
L4	Green	`2E8B57`
L5	Gold	`DAA520`

Link target: the assessment document, so anyone who clicks the badge sees the full assessment with evidence and rationale.

Scoring Heuristic

The assessed level is the highest level where the team has substantial evidence across all three disciplines. A team with L3 context engineering but L1 verification is assessed at L1 — the weakest discipline is the ceiling.

Level	Minimum evidence required
L0	Repo exists, team is aware of AI tools
L1	Some AI tool usage, basic prompting
L2	Automated tests in CI, systematic verification of AI output
L3	CLAUDE.md + at least 3 harness constraints enforced + custom agents or skills
L4	Specifications before code + agent pipeline with safety gates
L5	Platform-level governance + cross-team standards + observability

name	ai-literacy-assessment
description	This skill should be used when the user asks to "assess AI literacy", "run an assessment", "check literacy level", "evaluate our AI collaboration", "where are we on the framework", or wants to determine their team's AI literacy level using the ALCI instrument.