Skip to content
Development
Skill

/run

Execute a named script defined in .aiwg/aiwg.config or list all available scripts

From plugin
aiwg
229200 skills199 agents26 commands

Claude Code

$ npx -y skills add jmagly/aiwg --skill run --agent claude-code

SKILL.md

run.SKILL.md
namespace: aiwg
name: run
platforms: [all]
description: Execute a named script defined in .aiwg/aiwg.config or list all available scripts

Run

You execute a named script defined in `.aiwg/aiwg.config`, or list all available scripts when no name is given.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

  • "what scripts are available" → list scripts
  • "run the deploy script" → run `deploy`
  • "execute test script" → run `test`
  • "aiwg run" → list if no name; run if name given

Trigger Patterns Reference

| Pattern | Example | Action | |---------|---------|--------| | Named run | "run the test script" | Run `aiwg run test` | | Explicit list | "list aiwg scripts" | Run `aiwg run` (no args) | | With args | "run deploy with flag --prod" | Run `aiwg run deploy --prod` | | Unknown name | "run the build script" | Run `aiwg run build`; report if not found |

Behavior

When triggered:

1. **Verify config exists**:

  • Read `.aiwg/aiwg.config` to confirm `scripts` block is present.
  • If no config found, suggest `aiwg init` to create one.

2. **Extract arguments**:

  • Is a script name specified? If yes, run it.
  • If no name, list all registered scripts with their shell commands.
  • Are additional arguments passed through? Append them to the shell invocation.

3. **Run the appropriate command**:

   # List all available scripts
   aiwg run

   # Run a named script
   aiwg run <script-name>

   # Run with pass-through arguments
   aiwg run <script-name> -- <extra-args>

4. **What "run" does**:

  • Reads the script's shell command from `.aiwg/aiwg.config`
  • Executes it in the project root
  • Streams output to the terminal
  • Reports exit code on completion

5. **Report the result** — show the command that was executed, stream output, and confirm success or failure with exit code.

Examples

Example 1: List available scripts

**User**: "What scripts do I have registered in aiwg?"

**Extraction**: List request, no script name

**Action**:

aiwg run

**Response**:

Registered scripts (from .aiwg/aiwg.config):

  test    → npm test
  lint    → npm run lint
  deploy  → ./scripts/deploy.sh --env staging

Run a script with: aiwg run <script-name>

Example 2: Run a named script

**User**: "Run the lint script"

**Extraction**: Script name `lint`

**Action**:

aiwg run lint

**Response**: Executes `npm run lint`, streams output, then reports: "Script `lint` completed (exit 0)."

Example 3: Run with pass-through arguments

**User**: "Run the deploy script with --env production"

**Extraction**: Script name `deploy`, extra args `--env production`

**Action**:

aiwg run deploy -- --env production

**Response**: Executes `./scripts/deploy.sh --env staging --env production` (or however the script merges args), then reports exit status.

Example 4: Script not found

**User**: "Run the build script"

**Extraction**: Script name `build`, not present in config

**Action**:

aiwg run build

**Response**: "No script named `build` found in `.aiwg/aiwg.config`. Available scripts: test, lint, deploy. Register `build` with `aiwg init --interactive` or edit `.aiwg/aiwg.config` directly."

Example 5: No config present

**User**: "aiwg run test"

**Extraction**: No `.aiwg/aiwg.config` found

**Response**: "`.aiwg/aiwg.config` not found. Run `aiwg init` to create one and register scripts."

Clarification Prompts

If the user's intent is ambiguous:

  • "Which script would you like to run? Available: test, lint, deploy."
  • "No script name given — should I list all registered scripts?"

References

  • @$AIWG_ROOT/src/cli/handlers/run.ts — `run` command handler
  • @$AIWG_ROOT/docs/cli-reference.md — CLI reference
  • @$AIWG_ROOT/agentic/code/addons/aiwg-utils/skills/init/SKILL.md — Registering scripts via init
Read more
@jmagly
Ships withaiwg

Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.

229200 skills199 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
229
Star history of jmagly/aiwg on GitHub, a chart by star-history.com

Other skills on aiwg.

agent-loop-ext

agent-loop-ext

Crash-resilient external agent loop with state persistence and CI/CD integration

@jmagly@jmaglyInstall Skill
agent-loop

agent-loop

Detect requests for iterative autonomous agent loops and route to the appropriate loop executor

@jmagly@jmaglyInstall Skill
auto-test-execution

auto-test-execution

Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern

@jmagly@jmaglyInstall Skill

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills12d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc13d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react2d252k
@facebook@facebookInstall Skill

Questions about run.

Which coding agents can use run?
run installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.