Ask claude
Use when a Codex or generic local agent needs a focused second opinion from Claude CLI without MCP routing.From its SKILL.md
npx -y skills add yeaight7/agent-powerups --skill ask-claudeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 6 commands, including `apx ask-claude "Review this patch for correctness"` and 5 more.
SKILL.md
1.7 KB, 403 tokens by cl100k_base, as published. Nobody here has run it
Ask Claude
Purpose
Use local Claude Code CLI as an external advisor for focused questions, reviews, or design checks. The workflow is local-first and always leaves a Markdown artifact.
When to Use
- Need a Claude second opinion from Codex App or another shell-capable agent.
- Want reviewable output from
claude -psaved for later. - Do not use when Claude CLI is missing or unauthenticated.
- Do not use as an MCP fallback.
Inputs
- A specific prompt or task.
- Local
claudecommand available in PATH. - Optional artifact directory.
Workflow
Run through APX:
apx ask-claude "Review this patch for correctness"
Equivalent nested APX and direct CLI calls:
apx ask claude "Review this patch for correctness"
claude -p "Review this patch for correctness"
If claude is missing, stop and ask the user to install/configure Claude Code CLI. Verify with:
claude --version
Output
APX writes:
.apx/artifacts/claude-<slug>-<timestamp>.md
Artifact sections:
- Original user task
- Final prompt sent to Claude CLI
- Claude output (raw)
- Concise summary
- Action items / next steps
Verification
apx check ask-claude
apx ask-claude "Return OK only" --json
Confirm JSON includes provider, artifactPath, promptLength, and raw output in stdout. Open the artifact before applying advice.
Failure Modes
- Missing CLI: do not use MCP; ask user to install/configure
claude. - Auth failure: keep artifact if APX created one, report CLI stderr.
- Broad prompt: narrow the question before running to avoid noisy advice.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most context ai engineering skills give in 403 tokens
Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06
- Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
- Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
- Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
- Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
- Use the least powerful model capable of the taskin 33 of 1328, across 26 files
- Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
- Perform a task review after each implementationin 31 of 1328, across 24 files
- Extract all tasks and context from the planin 29 of 1328, across 20 files
- Provide full task text to subagentsin 28 of 1328, across 20 files
- Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
- Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
- Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files
Said here and by no other author read
- Use Claude CLI as an external advisor
- Run the command via apx
- Save output as a markdown artifact
- Narrow the prompt before running
- Open the artifact before applying advice
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.