Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI spec (before implementation) or refactoring an existing CLI’s surface area for consistency, composability, and discoverability.
Security Analysis
high confidenceThis is an instruction-only skill that cleanly describes how to design a CLI surface and only relies on bundled guidance; it requests no credentials, installs, or unrelated system access.
The name/description (Create Cli) matches the SKILL.md content and the included cli-guidelines reference; no extra binaries, credentials, or unrelated capabilities are requested.
Instructions are narrowly scoped to designing CLI specs and to reading the included guideline file. Minor mismatch: SKILL.md tells the agent to read 'agent-scripts/skills/create-cli/references/cli-guidelines.md' while the manifest provides 'references/cli-guidelines.md' — this is a local path discrepancy that could cause the agent to fail to locate the file but is not a security concern. There are no steps that read unrelated system files or exfiltrate data.
No install spec (instruction-only). Nothing is written to disk or downloaded by the skill itself.
The skill declares no required environment variables, credentials, or config paths — proportional to its described purpose.
always is false and the skill does not request persistent system privileges or to modify other skills/config; autonomous invocation is allowed by default (normal platform behavior).
Guidance
This skill is instruction-only and internally consistent with its stated purpose. It doesn't request credentials or install anything, but a few practical notes before use: (1) the SKILL.md references a longer path for the bundled guideline file (agent-scripts/…) while the manifest lists references/cli-guidelines.md — if the agent can't find the file you may need to supply the guideline content or correct the path; (2) the agent may ask clarifying questions — avoid pasting secrets or private credentials into those prompts; and (3) although the skill can be invoked autonomously (the platform default), it has no extra privileges or network calls described. If you want absolute assurance, review the guideline file contents included in the skill (references/cli-guidelines.md) and confirm you’re comfortable with the agent having access to those local instruction files.
Latest Release
v1.0.0
More by @steipete
Published by @steipete on ClawHub
