AC harness-engineer
A persistent autonomous engineering harness runtime that transforms any repository into a self-improving software system. Use this skill whenever the user wants to: build or run an autonomous coding agent, set up a self-healing engineering loop, orchestrate multi-agent software development, implement harness engineering principles, create a doc-driven development workflow, or run long-horizon autonomous software tasks. Trigger on phrases like "autonomous agent", "self-healing codebase", "harness engineering", "multi-agent pipeline", "continuous improvement loop", "OpenClaw skill", or any request for an agentic engineering system that runs without constant human input. Primarily designed for Claude Code and OpenClaw environments.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 Broad scope
meta-agent-memory-dumpMEMORY.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensMEMORY.md
-
low Concealment
en-hide-from-useragents/reviewer.md:131Instruction to hide actions from the user (negated — the text forbids it)3. Recommend removal (but ask, don't silently delete)
negated
Files scanned: 54. 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 61/100
- 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. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 22 steps
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2119 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 738: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 22 items
- +4Reference files are cited in the instructions (8 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.