BC coffee-chat
Generate a personalized coffee chat playbook for networking conversations. Use when: - User wants to prepare for a coffee chat with someone they met on LinkedIn - Need to gather intelligence on a professional contact before meeting - Creating conversation guides for networking meetings Triggers: "coffee chat", "networking prep", "coffee chat prep", "chat playbook", "meeting prep" This skill: 1. Collects target person's name and LinkedIn URL 2. Researches company and industry 3. Finds founder/employee backgrounds 4. Generates a comprehensive coffee chat playbook with detailed research
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, 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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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-shell-rcSKILL.md:66Writes to a shell startup fileecho 'export NOTION_API_KEY="secret_xxxxxxxxxxxxxxxxxxxx"' >> ~/.zshrc
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6392 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 11 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6392 tokens
- 100Steps. 70 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 592: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 70 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.