AD llm-wiki
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local web viewer. Use when (1) scaffolding a new knowledge base for any research topic, (2) ingesting articles/papers/PDFs/web pages into raw/, (3) compiling or restructuring wiki articles from existing raw material, (4) answering questions against the wiki and filing durable answers back, (5) running lint passes for dead links / orphan pages / coverage gaps / audit shape, (6) processing human feedback from the audit/ directory and applying corrections. Not for general note-taking, daily journals, or non-wiki Obsidian use.
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked…
As a process D 44/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 10. 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 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 9 mutating operations with no state check
- 40Consistency. Frontmatter name (llm-wiki) differs from the folder (llm-wiki-q)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, read, python) that frontmatter does not declare
- 100Steps. 74 steps
- 100Execution cost. Instruction body is 3458 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (21 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 841: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 20 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.