Strategy Review
v1.0.1Use when reviewing, critiquing, or stress-testing an existing strategy document. Evaluates seven dimensions — diagnosis quality, guiding policy strength, act...
⭐ 0· 77·1 current·1 all-time
byKevin Anderson@anderskev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
The skill name and description (strategy review / pressure-testing a strategy) match what the SKILL.md and reference files ask the agent to do: read strategy documents, apply evaluation lenses, and produce prose and optional JSON reports. There are no unrelated binaries, environment variables, or external credentials requested.
Instruction Scope
Runtime instructions are self-contained and focused on reading user-supplied strategy documents and internal reference files to produce a review. The SKILL.md explicitly instructs the reviewer to write output files (strategy-review.md and optionally strategy-review.json) to the user's working directory and, if durable state is active, to a review state directory. Writing these artifacts is reasonable for this skill, but users should be aware the skill will create files in the working directory and may write durable state if that mode is used. There are no instructions to read unrelated system files or environment variables.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to execute. That minimizes installation risk. Nothing is downloaded or installed.
Credentials
The skill requires no environment variables, credentials, or config paths. The references and SKILL.md do not attempt to access secrets or unrelated service tokens. The declared requirements are minimal and proportionate to the stated purpose.
Persistence & Privilege
always:false (normal). The skill can write review artifacts (markdown and optional JSON) to the working directory and may write to a 'review state directory' when durable state is active; this is expected for a review/reporting skill but is a form of persistence the user should consent to. The skill does not request to modify other skills or system-wide agent settings.
Assessment
This skill appears coherent and focused on strategy review. Before installing or running it, confirm you are comfortable with the skill creating files in your working directory (it will write strategy-review.md and, only if you request judge mode, strategy-review.json). If you do not want durable state written, avoid enabling durable review state or judge artifact mode. There are no credential or network requests in the instructions, but verify any files produced (especially JSON outputs) before sharing externally. If you want stronger containment, run the skill interactively (user-invocable) rather than allowing autonomous invocation.Like a lobster shell, security has layers — review code before you run it.
latestvk97408jk139k5yy027ba851dbx84paz4
License
MIT-0
Free to use, modify, and redistribute. No attribution required.