AC coding-lead
Smart coding skill that routes tasks by complexity. Simple tasks (<60 lines, single file) execute directly via OpenClaw agent tools. Medium/complex tasks spawn Claude Code via ACP with full project context, coding standards, and historical decisions from agent memory. Use when user asks to write code, fix bugs, build features, refactor, review PRs, deploy, or any software engineering task. Combines OpenClaw long-term memory with Claude Code deep coding ability.
Smart coding skill that routes tasks by complexity.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5324 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5324 tokens
- 85Steps. 113 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 24 top-level sections: this looks like several domains in one skill
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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 465: enough signal without eating the budget
- +4Structure: 51 headings
- +3Step-by-step instructions: 113 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.