AC linkedin-content
Every Monday three LinkedIn post drafts for one author land in the GTM repo as one pull request, built only from what context/ and the cadence log already say, each with its hook and the files it draws on; nothing is ever published. Triggers: "draft our founder's LinkedIn posts every week", "weekly LinkedIn drafts from our proof points", "turn our wins and insights into LinkedIn posts", "keep a LinkedIn content pipeline", "ghostwrite LinkedIn posts from our context", "content calendar for the CEO on LinkedIn". Cargo CDK, defineAgent, harness claudeCode, GitHub, context/, cadence/content. Skip when: you want the company website and news read into context/, which is web-capture; or you want one post written now, in this chat, with nothing deployed.
Every Monday three LinkedIn post drafts for one author land in the GTM repo as one pull request, built only from what context/ and the cadence log already…
As a process C 51/100 · Has gaps — 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: 9. 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 51/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 13 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. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3369 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (7 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 756: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 24 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: 92.