BC calendar-extractor
Extract calendar events from recent recording and keyboard transcripts and push them to your iOS chat as one markdown card per event, each landing in its own Agent Chat thread. Use on demand when the user asks for "today's meetings" / "calendar extract" / "今日会议" / "提取日历", and fetch the last 24 hours of transcript data by default. The javis-server dispatcher also invokes this skill directly for every completed unit — no classifier, no route matching; this skill's own agent decides relevance itself, using this SKILL.md, and may use a deliverable hint passed in the run prompt alongside the transcript; extracted events are written PENDING and become solid only when the user taps Confirm in the iOS calendar table. If the user asks for "today's meetings", use the local day defined by the fetched reference_date field. Triggers: 'today's meetings', 'calendar extract', '今日会议', '提取日历'.
Extract calendar events from recent recording and keyboard transcripts and push them to your iOS chat as one markdown card per event, each landing in its own…
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 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.
- 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-usescripts/calendar-extractor.js:319Credential used in a network call (verify the destination is the intended service)const res = await fetch(url, { headers: { Authorization: `Bearer ${token}` } });
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Extract calendar events from recent recording and keyboard transcr… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 5101 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "keywords"
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 25 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5101 tokens
- 100Steps. 29 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 (13 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 888: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 7 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.