BB Journal
Runs a personal journaling practice: capturing entries, prompts for a blank page, weekly and yearly reviews, and patterns across years of writing. Use when the user wants to write, vent, dictate, or get something out of their head; when they ask for a prompt or say they are stuck; for morning pages, bullet journal, five-minute, interstitial, dream, travel, decision, or work journaling; for a weekly, monthly, or annual review; when they ask what they have been writing about, whether a mood or theme keeps recurring, or what they wrote a year ago; when the practice lapsed and they want to restart; when entries need naming, tagging, searching, encrypting, backing up, or migrating out of Day One, Notion, or an Obsidian vault; when writing through grief, anger, shame, or a decision that will not settle; or when a work journal must become performance-review evidence. Not for retrieval-oriented notes (`notes`), gratitude logging alone (`gratitude`), or live emotional support (`psychologist`).
As a process B 76/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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
-
low Risky intent
intent-wallet-secretsSKILL.md:217Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)**Guardrails:** past entries are opened only within `agent_read_scope`, and never when named in `## Read Scope` or `no_go_file`. Entry content is never copied into a shared box or any file outside the
detector
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 6588 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 76/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 11 branches
- 70Execution cost. Instruction body is 6588 tokens
- 100Tools and files. No external tools needed
- 100Steps. 41 steps
- 100When it triggers. States when to use and when not to
- 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 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 999: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 41 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.