BB text-classification
Designs and validates LLM-based text classification for research data — codebook construction, choice of learning regime, model selection and reproducibility, prompt construction, pilot validation against human coding with agreement statistics (kappa, F1), hybrid human-LLM workflows, and reporting model-coded data. Also carries a resumable batch pipeline with a rule-based baseline for coding large sets of repeated free-text values against a closed codebook — occupation, institution, and registry text, and open-text survey responses — with a frozen input set, incremental output, residual buckets, stratified hand validation, a regex or dictionary comparison, and a published lookup table. Use when the user asks to classify, code, or label text at scale. Discovering categories rather than applying them goes to topic-modeling.
Designs and validates LLM-based text classification for research data — codebook construction, choice of learning regime, model selection and reproducibility…
As a process B 77/100 · Nearly there — weak spots: 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5506 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 42): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 77/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5506 tokens
- 100Tools and files. No external tools needed
- 100Steps. 76 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
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 833: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 76 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.