AD social-listening
Every Monday the week's public LinkedIn posts about the problem you solve are searched, judged against your ICP, and posted to Slack as one digest: the conversations worth joining, and the commenters in them who look like buyers, each quoted with a link. Triggers: "tell me which linkedin posts we should comment on", "watch linkedin for people talking about our problem", "social listening on linkedin", "weekly digest of linkedin conversations in our space", "who is engaging with posts about our category", "monitor linkedin posts mentioning our competitors". Cargo CDK, LinkedIn fetchPosts, searchPostComments, defineModel, defineAgent, Slack postMessage. Skip when: you want named target accounts checked for hiring, news or detection-feed events, once, which is monitor-buying-signals; or you want people who just took a role you sell to, which is new-hire-detection.
Every Monday the week's public LinkedIn posts about the problem you solve are searched, judged against your ICP, and posted to Slack as one digest: the…
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 49/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 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
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3572 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 873: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.