CC arbor
Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI.
Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and…
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Obfuscation
obf-base64-blobreferences/arbor-upstream.md:33Long base64-looking blobcan accompany exit code 0. See its [implementation](https://github.com/RUC-NLPIR/Arbor/blob/7cda…d93/src/cli/commands/doctor_cmd.py).
-
medium Obfuscation
obf-base64-blobreferences/arbor-upstream.md:50Long base64-looking blob[setup implementation](https://github.com/RUC-NLPIR/Arbor/blob/7cda…d93/src/cli/commands/setup_cmd.py)
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Agent
Files scanned: 6. 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
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Failures and branches. 2 branches
- 70Execution cost. Instruction body is 4041 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 401: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.