AC xparse-parse
Parse, read, search, navigate, summarize, and extract tables or structured evidence from PDFs, images, Office files, HTML, OFD, and other supported local documents or document URLs through xparse-cli. Use this Skill for single-document conversion, targeted section/page/fact extraction, and durable multi-document Task Runtime workflows including status checks, selective reads, exports, debugging, and password-based continuation. Prefer it over raw PDF readers or custom OCR scripts.
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, 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: 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 57/100
- 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
- 40Consistency. Frontmatter name (xparse-parse) differs from the folder (xparse-parser)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4606 tokens
- 100Steps. 39 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (45 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
- +1No license
- +2Single-language instructions
- +3Description length 485: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.