BC javis-brainstorming
Turn a brainstorm-worthy voice/keyboard unit into a generic "to-do card" whose ready-to-paste prompt hands off to Claude's content-brainstorming skill (with javis_mcp pulling the source transcript). This skill does NO brainstorming itself — it composes a hand-off prompt and writes a type="todo" card stamped with the source session's start/end times (journal semantics). Use on demand when the user asks to "brainstorm this" / "整理成簡報" / "帮我腦力激盪", 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 — passing a deliverable hint in the run prompt that the agent may use alongside the transcript; this skill's own agent decides for itself whether the unit is worth acting on, and if not, does nothing. The card is written PENDING and a markdown digest of it is delivered to the Agent Chat via POST /api/agent/push (the chat shows [push:javis-brainstorming] + the card summary); the human gate is Confirm/Discard in the iOS Calendar tab (Confirm saves the card on the calendar as a solid event; tapping the card body opens its Agent Chat session). Triggers: 'brainstorm this', '整理成簡報', '帮我腦力激盪'.
Turn a brainstorm-worthy voice/keyboard unit into a generic "to-do card" whose ready-to-paste prompt hands off to Claude's content-brainstorming skill (with…
As a process C 57/100 · 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
- Shorten the description to 1024 characters.
- 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/brainstorming.js:265Credential used in a network call (verify the destination is the intended service)const res = await fetch(url, { headers: { Authorization: `Bearer ${token}` } });
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1221 chars, limit 1024 - 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: Turn a brainstorm-worthy voice/keyboard unit into a generic "to-do… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "keywords" - note
edit-residuethe text marks something as outdated (lines 178): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 57/100
- 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. 14 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3215 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (14 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 1221: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -32 of 5 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: 23 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 46.