AC superpowers
Agentic software development methodology — 13 integrated skills for disciplined AI-assisted development covering brainstorming, planning, TDD, debugging, code review, git worktrees, and branch management.
As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, consistency, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9437 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (superpowers) differs from the folder (claw-superpowers)
- 40Execution cost. Instruction body is 9437 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Failures and branches. 12 branches
- 85Steps. 222 steps, 1 vague phrases
- 100Result and completion. Output format and completion criterion are stated
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 204: enough signal without eating the budget
- +4Structure: 86 headings
- +3Step-by-step instructions: 222 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.
External checks
ClawHub: suspicious
This is a legitimate software-development workflow skill, but it tries to make its process mandatory too broadly and can steer agents into repository changes, commits, subagents, and worktree actions even for simple tasks.
LLM: suspicious (high) · VirusTotal: · 29 May 2026