AC pharmaclaw-cheminformatics
Advanced cheminformatics agent for 3D molecular analysis, pharmacophore mapping, format conversion, RECAP fragmentation, and stereoisomer enumeration. The "senior cheminformatician" upgrade to Chemistry Query. Use for 3D conformer generation/ensembles (ETKDG + MMFF/UFF), pharmacophore feature extraction and fingerprints, molecular format conversion (SMILES/SDF/MOL/InChI/PDB/XYZ), RECAP retrosynthetic fragmentation for library design, stereoisomer enumeration (R/S, E/Z), and cheminformatics profiling. Chains from chemistry-query (receives SMILES) and feeds into pharmacology, catalyst-design, ip-expansion. Triggers on conformer, 3D structure, pharmacophore, SDF, MOL file, format conversion, RECAP, fragmentation, stereoisomer, chirality, enantiomer, cheminformatics, library design, building blocks, docking prep.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 0
✓ No critical or high findings
Files scanned: 8. 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 52/100
- 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
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1628 tokens
- 100Running it twice. No mutating operations
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 820: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (12 code blocks)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.