BB llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
The skill promises to compile a persistent wiki from documents and papers with source citations, so your agent can retrieve evidence later without re-reading. Single file, no scripts—695 tokens of instructions. No critical issues found; quality score 85, but process score only 66. Safety check passed.
Practically: use this if you plan to ask the agent repeated questions against one document corpus or need it to cite specific sources. One-time document reads or live web searches don't need a wiki. Wide platform support: Claude, Cursor, Gemini, DeepSeek, and others. Worth installing, but note the 66 process score—expect rough edges in execution details.
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation.
As a process B 66/100 · Nearly there — weak spots: result and completion, when it triggers, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 1. 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 66/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 7 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 695 tokens
- 100Running it twice. No mutating operations
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 308: enough signal without eating the budget
- +4Structure: 4 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.