CD agent-sandbox
Agent skill for sandbox - invoke with $agent-sandbox
Claims to set up an isolated sandbox environment for agent experiments. Contains one 753-token module, no scripts, no critical errors. Quality score 65 and process score 41 signal sloppy documentation: the logic exists, but execution is rough. No model runs, no deployed sandbox. Safety checks pass (score 100), but that doesn't offset incomplete implementation.
Skip it. The skill works as a draft: files are clean, but undertested. If you need a Claude, Cursor, or Gemini sandbox to build on—take it and finish the job yourself. If you want something production-ready, wait for an update.
Agent skill for sandbox - invoke with $agent-sandbox
As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: RA-Skills
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
edit-residuethe text marks something as outdated (lines 59): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 41/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 85Steps. 24 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 753 tokens
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)
- +3Description length 52: 120–800 characters recommended
- +4Structure: 0 headings, hard to scan
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Step-by-step instructions: 24 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.