AC gstack-pro
Transform your AI assistant into a structured virtual software engineering team with 10 specialist roles — inspired by Garry Tan's GStack (YC CEO, 16K GitHub Stars) and adapted for OpenClaw's subagent architecture. Covers the full development lifecycle: product thinking → architecture → design → code review → QA → ship → retro. Generator-Evaluator pattern included. Health Score (0-100) for every sprint. Automated browser QA. Activate when: starting a new feature, preparing to ship, doing code review, running QA, or needing a product rethink. Works with: OpenClaw subagents (coder/tester/architect/writer/operator/designer/progress/requirer).
As a process C 64/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "tagline"
Process rating: all ten parameters 64/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1536 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- -226 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 647: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 12 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.