AC super-marketing-pro
Full-stack B2B marketing execution skill equivalent to a 10-person agency team. Use for: building ICP and brand messaging, generating multi-platform content matrices, writing cold email sequences, SEO topic cluster strategy, competitor battle cards, content repurposing (1 long-form → LinkedIn/X/TikTok/Xiaohongshu), and monthly/quarterly marketing reports. Covers Chinese platforms (抖音, 小红书, 微信) and Western platforms (LinkedIn, YouTube, Instagram, X). Triggers on: marketing strategy, social media content, SEO analysis, competitor research, email sequence, content calendar, hashtag, ICP, 营销策略, 社媒内容, 竞品分析, 内容日历, 邮件序列.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-autorun-instructionSKILL.md:16Instructs the agent to auto-run a script on every sessionFull-stack B2B marketing skill. Always run `strategy_builder.py` first to define ICP before generating any content.
Files scanned: 22. 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 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 75Steps. 3 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 703 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 621: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 3 items
- +4Reference files are cited in the instructions (9 of 9)
- +3All 9 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.