BD pharmaclaw-catalyst-design
Organometallic catalyst recommendation and novel ligand design for drug synthesis reactions. Recommends catalysts (Pd, Ru, Rh, Ir, Ni, Cu, Zr, Fe) for reaction types (Suzuki, Heck, Buchwald-Hartwig, metathesis, hydrogenation, click, etc.) from curated database with scoring. Designs novel ligand variants via RDKit (steric, electronic, bioisosteric modifications). Chains from chemistry-query/retrosynthesis (receives reaction type + substrate) and feeds into IP Expansion (novel ligands as patentable inventions). Triggers on catalyst, ligand, organometallic, cross-coupling catalyst, reaction conditions, catalyst selection, ligand design, cone angle, bite angle, phosphine, NHC, palladium catalyst, ruthenium catalyst.
As a process D 47/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions
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: 6. 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")
Process rating: all ten parameters 47/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 841 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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 721: enough signal without eating the budget
- +4Structure: 10 headings
- +4Has examples (3 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.