AD local_document_ingest
Ingest desktop-uploaded local files into the Research KB. Use for local folder scan tasks where OpenClaw must read backend shared-file paths, understand each changed file, create a type-specific entity wiki page for every readable file, archive originals under source_files, update related pages, synthesize concept/resource pages, maintain links/catalog/index metadata, and return backend task JSON.
Ingest desktop-uploaded local files into the Research KB.
As a process D 37/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:517High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"uploadBatchId": "sour…3d4",
detector
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 37/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (local_document_ingest) differs from the folder (local-document-ingest)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4599 tokens
- 100Steps. 238 steps
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (25 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -36 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 400: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 238 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.