AC post-experience-rater
Capture a fast, casual rating right after the user finishes something -- a restaurant, hotel, trip, event, or meeting a new person -- and store it in Fulcra as a structured annotation that builds their long-term taste/preference graph. Use this whenever the user says things like "rate that restaurant", "how was dinner", "log a rating", "rate the hotel", "that place was a 4", or otherwise reacts to an experience they just had. Keep it to ~15 seconds, like texting a friend. For a deeper per-event capture with attendees and follow-ups use event-debrief; for a whole-day wrap-up use evening-debrief. Do NOT use it for objective health/calendar data pulls.
Capture a fast, casual rating right after the user finishes something -- a restaurant, hotel, trip, event, or meeting a new person -- and store it in Fulcra…
As a process C 56/100 · Has gaps — weak spots: result and completion, failures and branches, consistency
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
- 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-redirectable-api-keyscripts/lib/fulcra_annotations.py:24Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 11. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (post-experience-rater) differs from the folder (fulcra-post-experience-rater)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 6 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 715 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 657: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.