AC llm-wiki
Build, maintain, query, archive, and audit a Markdown / Obsidian knowledge Wiki continuously maintained by an LLM. Use this skill to initialize a personal knowledge base; import raw materials grouped by source under source/ into wiki/; organize articles, papers, book notes, interviews, and meeting notes; maintain source pages, entity pages, concept pages, synthesis pages, comparison pages, and query archive pages; update index.md and log.md; answer questions based on the Wiki and archive answers with long-term value; check broken links, orphan pages, duplicate concepts, outdated conclusions, unlabeled contradictions, encoding corruption, and organizational disorder.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 3. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (llm-wiki) differs from the folder (llm-obsidian-wiki)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Failures and branches. 8 branches
- 70Execution cost. Instruction body is 4879 tokens
- 100Steps. 160 steps
- 100When it triggers. States when to use and when not to
- 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 14 top-level sections: this looks like several domains in one skill
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
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 674: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 160 items
- +4Has examples (14 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.