AB powermatrix-geo-growth-orchestrator
Unified GEO growth workflow for brand knowledge base building, LLM visibility audits, Doubao/DeepSeek readiness review, AI-GEO content asset generation, platform draft planning for Zhihu/Toutiao/CSDN/Juejin, client delivery reports, internal QA, and 7/14/30 day retests. Use when Codex needs to analyze or improve a brand's AI search visibility, generate GEO reports, diagnose model mentions/citations/rankings, create GEO-friendly content tasks, or consolidate GEO platform workflows into one human-reviewed delivery package.
As a process B 72/100 · Nearly there — weak spots: result and completion, consistency, progress reporting
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: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 72/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (powermatrix-geo-growth-orchestrator) differs from the folder (geo-growth-orchestrator)
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 96 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2256 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -35 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 526: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 96 items
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.