BC llm-wiki
Use when an AI Agent (Claude Code, Codex, OpenClaw, or similar) needs to operate an llm-wiki knowledge base: ingest source files into Markdown wiki pages, answer questions from wiki/index.md and linked pages, run agent-bridge status/lint/link/relink/merge/query/index/Zotero relocation tasks, preserve provenance and temporal metadata, or use Zotero as a literature-discovery layer.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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
- 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-autorun-instructiondocs/ZOTERO_MCP_INTEGRATION.md:559Instructs the agent to auto-run a script on every session- Always run `scripts/zotero_sources.py --dry-run` before materializing aliases.
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:29Pipe-to-shell installer from a well-known host (still executes remote code)# macOS/Linux: curl -LsSf https://astral.sh/uv/install.sh | sh
Files scanned: 70. 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 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (llm-wiki) differs from the folder (041-llm-wiki)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 35 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 2776 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- -35 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 382: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.