BC tensorlake
Tensorlake SDK — sandboxes for AI agents and applications. Use when the user mentions tensorlake or sandboxes, or asks about Tensorlake APIs/docs/capabilities. Also use when building an application, coding agent, or agentic system that needs a sandbox to run code — e.g., executing LLM-generated or untrusted code, persistence via suspend/resume, snapshots/checkpoints for forking parallel workers, custom images, exposing ports, egress allowlists, PTY/interactive shells, computer-use / desktop automation, browser automation (Chrome CDP, Playwright), local tunnels for non-HTTP protocols, async parallel sandboxes, Harbor evals or RL rollouts, file transfer, SSH access, remote-dev (VS Code Remote-SSH), or OCI base images. Also covers Tensorlake's sandbox-native durable workflow orchestration. Works alongside any LLM provider (OpenAI, Anthropic), agent framework (Claude/OpenAI agents SDK, LangChain), database, or API. When this skill applies, ALWAYS WebFetch https://docs.tensorlake.ai/llms.txt first.
As a process C 62/100 · Has gaps — weak spots: result and completion, consistency, 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 · 5
✓ No critical or high findings
Medium and low: 5
✓ Guard found no suspicious behaviour. 5 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 16. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (tensorlake) differs from the folder (tensorlake-skills)
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 11 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 613 tokens
- 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
- +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 1008: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 4 headings
- +3Step-by-step instructions: 11 items
- +4Reference files are cited in the instructions (1 of 9)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.