Skip to content
Back to skills

As

ASecurity

Run any registered role from the repo's evolving role repository (.claude/roles/) against a target — the generic solo dispatcher for roles without a wrapper skill. Use when the user says "/roles:as <role>", "run the <role> role on X", "act as the <role>", or names a registry role that has no skill of its own.

  • 9 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 5, 2026
ai-agentsgo

Works with

  • claude code
  • cli

Security analysis

A100/100

Scanned September 21, 2026

npx -y skills add alexmond/alexmskills --skill as --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of As?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for As
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/alexmond-alexmskills/badge)](https://www.skillsdirectory.com/skills/alexmond-alexmskills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: as
description: Run any registered role from the repo's evolving role repository (.claude/roles/) against a target — the generic solo dispatcher for roles without a wrapper skill. Use when the user says "/roles:as <role>", "run the <role> role on X", "act as the <role>", or names a registry role that has no skill of its own.
argument-hint: "[role] [target]"
disable-model-invocation: true
---

**Codex:** Read [the client path](references/clients.md) before applying this workflow.


# Run a role solo

Input: $ARGUMENTS — the **first word** is the role name; the rest is the target.

1. **Resolve the role.** Prefer the repo's instantiated copy `.claude/roles/<role>.md` (the
   canonical, evolving one; `registry.md` indexes these). If it's absent, check this plugin's
   bundled seeds alongside this skill at `../<role>/role.md` — if found, copy it verbatim to
   `.claude/roles/<role>.md` and use that. If the role exists in neither, list the available roles
   (repo `.claude/roles/*.md` plus the bundled `../*/role.md`, excluding `crew.md`/`panel.md`/
   `registry.md`/this `as` skill) and stop — don't improvise a persona.
2. **Apply it.** Adopt the role's Charter and Body; honor every entry under `## Learnings (core)`
   and `## Learnings (solo)`. Note `crew.md` and `panel.md` are consumer registries, not roles —
   never load them as personas.
2.5 **Anchor in the Prompt Library (optional).** Each engineering persona maps to a category of
   Anthropic's [Claude Code Prompt Library](https://code.claude.com/docs/en/prompt-library) —
   `architect`→Plan, `builder`→Implement, `debugger`→Debug, `optimizer`→Debug, `refactorer`→Refactor,
   `reviewer`→Review, `skeptic`→Review (the role's Body also names its category). If the
   `prompt-coach` plugin is installed, run its `config.py library --category <Category>` for
   gold-standard prompt shapes in this role's domain and let them inform your opening. Degrade
   silently — this is enrichment, not a dependency; skip it if the plugin/command isn't present.
3. **Work the target** following the Body's method and deliverables.
4. **Capture a learning.** If the run surfaced a durable, reusable lesson (a fix that took more
   than one cycle, a stack- or repo-specific gotcha, a stated user preference), append one line
   under `## Learnings (solo)` in the role file: `- YYYY-MM-DD — <one sentence>`. Don't log
   routine one-pass outcomes.

Charter and Body edits are **never** made during a run — propose them to the user instead
(identity changes are deliberate, user-gated).

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…