Writing Plans
v1.0.1Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized task...
⭐ 0· 452·2 current·2 all-time
by@axelhu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill is an instruction-only 'writing plans' helper and its content matches that purpose: it describes how to produce detailed plans, file changes, tests, and git commits. Minor metadata mismatch: SKILL.md assumes developer tools (git, pytest) and a working repo/workspace, but the registry metadata declares no required binaries. The assumed tools are reasonable for the purpose but should be listed in metadata.
Instruction Scope
The instructions stay within the stated purpose: they direct the agent how to produce plan documents, what file paths to use, how to structure tasks, and example commands (git, pytest) for verification. They do instruct writing files under docs/superpowers/plans/, running git operations, and invoking tests — all expected for producing and validating implementation plans. The skill references other skills (brainstorming, superpowers-subagent-dev, superpowers-finishing-branch) which is consistent with a multi-skill workflow and is not unexpected.
Install Mechanism
No install spec is provided (instruction-only), which is the lowest-risk pattern. Nothing is downloaded or written by an install step.
Credentials
The skill requests no environment variables, credentials, or config paths. The SKILL.md uses git and pytest and will write plan files to the repository; those actions do not require secrets. No disproportionate credential access is requested.
Persistence & Privilege
always is false and the skill does not request system-wide persistence or elevated privileges. It recommends creating feature branches and may run git commands — normal for this domain. Autonomous invocation is allowed (platform default) but that is typical and not combined with other red flags.
Assessment
This skill appears coherent and focused on producing detailed implementation plans, but review these practical points before installing or running it:
- SKILL.md assumes developer tools (git, pytest, a Python test runner) and a writable repository workspace; the registry metadata does not list these binaries. Ensure they are available where the agent will run.
- The skill will write files under docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md and suggests running git commands (branch/commit/merge). Run it in a disposable feature branch or a sandboxed environment to avoid unintended commits to main.
- The skill references other internal skills (brainstorming, superpowers-subagent-dev, superpowers-finishing-branch). If you plan to use subagent-driven execution, ensure those skills are present and trusted.
- There are no requested secrets or installs, but the agent may modify your repository. Back up uncommitted work before letting the agent act, and consider restricting the agent's write permissions if your environment allows.
- Recommendation: update the skill metadata to declare required binaries (git, pytest) so the platform can perform eligibility checks and you know the runtime requirements.Like a lobster shell, security has layers — review code before you run it.
latestvk97f7mqt8780mxj11bc2aj9vr983mm0v
License
MIT-0
Free to use, modify, and redistribute. No attribution required.