AD harness
AI harness for stable LLM workflows. Topics — pipeline (clarify → ground → plan → generate → verify, dispatches to code-workflow) [pipeline.md], guardrails (denylist + scope + conditional-reject, self-contained for openclaw headless) [guardrails.md], recovery (fail-analyze → adapt → fallback, self-contained) [recovery.md]. Use when enforcing stable AI agent workflows, applying guardrails to autonomous execution, or recovering from verification failures. "harness", "AI harness", "pipeline guardrails", "fail recovery", "workflow stability", "agent harness" triggers
AI harness for stable LLM workflows.
As a process D 48/100 · 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 · 0
✓ No critical or high findings
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "depends-on"
Process rating: all ten parameters 48/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1450 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 569: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.