BC init-kb
Initialize or update a knowledge base for a project, business, or client. Triggers on "init kb", "build kb", "create kb for X", "set up kb", "new kb" (init), and "update kb", "refresh kb", "re-scrape kb", "kb update" (update). Scrapes websites and social profiles via the Firecrawl API, runs deep analysis, asks targeted questions to fill gaps, and generates 9 structured KB files. Each KB loads on-demand (not at boot) to avoid context bloat. Files are designed to be comprehensive references for specialized agents.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-shell-rcSKILL.md:101Writes to a shell startup fileecho 'export FIRECRAWL_API_KEY=your-key-here' >> ~/.zshrc && source ~/.zshrc
-
medium Dangerous commands
cmd-shell-rcSKILL.md:121Writes to a shell startup fileecho 'export FIRECRAWL_API_KEY=your-key-here' >> ~/.bashrc && source ~/.bashrc
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6819 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 6819 tokens
- 85Steps. 112 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 21 branches, has a failure section
- 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 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 517: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 112 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.