Use when reviewing UI for accessibility — WCAG 2.2 AA, keyboard nav, focus, ARIA, contrast, screen-reader semantics — even on 'is this a11y-OK?' or 'mach das barrierefrei'.
The English summary is being prepared. Showing the original description.
Use when creating or editing a persona in src/agent-src/personas/ — voice / focus / unique questions / output expectations — even when the user just says 'add a reviewer voice for X'.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
src/agent-src/personas/{id}.mdDo NOT use this skill when:
skill-writingrule-writingdocs/guidelines/agent-infra/role-contracts.md, not in personas| Intent | Artifact |
|---|---|
| "Agent should review through a specific lens" | Persona |
| "Agent should run a multi-step workflow" | Skill |
| "Agent's closing contract differs by role" | Role-mode (contract file) |
A persona is passive reference content — it never triggers by
description, never appears in <available_skills>. Skills cite
personas via the personas: frontmatter key.
Creating or materially rewriting a persona must go through
Understand → Research → Draft per the
artifact-drafting-protocol
rule. Inspect existing personas under
src/agent-src/personas/ for overlap before writing a new
one.
A persona owns one focus: automation-readiness, adversarial challenge, product-owner priorities, etc. If the focus needs three sentences, it is two personas.
Required sections:
## Focus — one paragraph, what this lens cares about and what
it ignores.## Unique questions — 4–7 questions only this persona would ask.
Each question must be decidable against the artifact under review.## Output expectations — what the persona produces (verdict
format, severity vocabulary, citation discipline).Optional: ## Anti-patterns this persona catches — concrete examples
the persona is calibrated to flag.
A persona that is not cited by any skill via the personas:
frontmatter key is dead code. Either wire it into an existing skill
or do not ship it.
---
id: <kebab-case-id>
role: <Human-Readable Role>
description: "One sentence: what this voice catches that others miss."
tier: core | specialty
mode: developer | product-owner | qa | stakeholder | none
version: "1.0"
source: package
---
The mode: field is advisory only — it suggests which role-mode the
persona pairs naturally with; it does not bind.
A single Markdown file at src/agent-src/personas/{id}.md:
id, role, description, tier, mode,
version, source)## Focus — one paragraph, what the lens cares about and ignores## Unique questions — 4–7 decidable questions## Output expectations — verdict format, severity vocabularyLength: ≤ 120 lines for a tier-core persona (specialists ≤ 100; wings 3–4: ≤ 140); longer signals the focus is too broad.
personas: never loads. Wire it in or do not ship.## Focus
is the first symptom of a second persona hiding inside the first.docs/guidelines/agent-infra/role-contracts.md, not in the persona
body.Apply the Frugality Charter to every persona you author.
Examples in this artifact:
## Focus opens with what
the persona cares about, not "This persona was created to…".## Unique questions lists decidable
questions only — drop any that read like vibe checks.Pre-save self-check:
## Focus open with the lens, or with persona meta-narrative?personas:?## Output expectations.kernel-membership
list.See src/agent-src/personas/ai-agent.md (automation
readiness) and critical-challenger.md (adversarial review) for
canonical structure.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when reviewing UI for accessibility — WCAG 2.2 AA, keyboard nav, focus, ARIA, contrast, screen-reader semantics — even on 'is this a11y-OK?' or 'mach das barrierefrei'.
The English summary is being prepared. Showing the original description.
Use when defining or auditing the activation event — aha-moment selection, retention correlation, falsifiable definition. Triggers on 'what is our aha moment', 'redefine activation'.
The English summary is being prepared. Showing the original description.
Use when capturing an architectural decision — file naming, next ADR number, Status / Context / Decision / Consequences, index regen; fires even without saying 'ADR'.
The English summary is being prepared. Showing the original description.
Adversarial critique — devil's advocate, stress-test, honest teardown ('poke holes', 'be brutal', 'was hältst du davon'); explicit request only. Routine code or design review → code-review.
The English summary is being prepared. Showing the original description.
Use when reading, creating, or updating agent documentation, module docs, roadmaps, or AGENTS.md. Understands the full .augment/, agents/, and copilot-instructions structure.
The English summary is being prepared. Showing the original description.
Use for an adversarial red-team / blue-team / auditor review of an AI agent's CONFIG + behaviour (rules, skills, MCP, hooks, permissions) — attack-chain → defensive-gap list, not a code audit.
The English summary is being prepared. Showing the original description.