AC lintlang-audit
Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on request. Use when the user asks to audit, lint, scan or review such a file for ambiguous tool descriptions, missing stop conditions, schema/description mismatches, or prompts embedded in Python, and names the file. Deterministic offline static analysis, no model call and no network call. Do not use for general code review, for prose documentation, or when no file has been named.
Promises static analysis of AI agent configs—catches ambiguous tool descriptions, missing exit conditions, schema mismatches, and embedded prompts in Python. Runs offline, no model or network calls.
One script, 1646 tokens, grade A, quality score 89, no critical errors. Supports nine platforms from Claude to DeepSeek. Process score 63—not high, but acceptable for a static analyzer.
Practically: feed it YAML, JSON, or a text agent config, get a report on tool description gaps and potential hangs. Deterministic, no network latency. Install if you write system prompts and agent instructions and want to catch errors before runtime.
Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on…
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 1. 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 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 100Steps. 18 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1646 tokens
- high The skill tells the model to perform an irreversible action with no human approval
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 538: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.