BF call-capture
Every call the team records is collected into the cadence layer each morning, scribed into a log entry, and — once a claim repeats — promoted into the context knowledge layer, as one reviewable pull request against your GTM repo. Triggers: "our call recordings never make it into the knowledge base", "turn our call transcripts into context", "keep our context updated from sales calls", "we relearn the same objection every quarter", "scribe yesterday's calls into the repo every morning", "replace the GitHub Action that summarizes our meetings". Cargo CDK, defineAgent, harnessSlug claudeCode, repository env, GitHub, Avoma, Gong, Fireflies, cadence, context. Skip when: you want one call summarized right now, which is a read against the recorder's own API and needs nothing deployed.
Every call the team records is collected into the cadence layer each morning, scribed into a log entry, and — once a claim repeats — promoted into the context…
As a process F 46/100 · Will not run — References files that are not bundled: scripts/collect/<recorder>.ts, scripts/call-capture/package.json
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 Exfiltration
net-credential-usereferences/providers.md:62Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $CALL_RECORDER_API_KEY" \
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5500 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/collect/<recorder>.ts - warning
missing-refreference to a missing file: scripts/call-capture/package.json - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 46/100
- 0Tools and files. 2 referenced file(s) missing: scripts/collect/<recorder>.ts, scripts/call-capture/package.json
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5500 tokens
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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 (5 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 788: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 33 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.