CtrlK
BlogDocsLog inGet started
Tessl Logo

boltz-small-molecule-design

Design new small-molecule binders with Boltz. Use when generating novel ligands or hits for a target without a fixed compound library. Not for screening existing molecules or one-off docking.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers highly actionable, well-sequenced guidance with strong validation checkpoints and correctly placed one-level-deep references to real bundle files. Its main weakness is conciseness: runtime background-handling and a few policy points are repeated across the workflow and the 'Always Do This' checklist.

Suggestions

Consolidate the runtime background/download handling (Codex yield_time_ms, nohup warning, heartbeat cadence) into one place — keep it in the 'Always Do This' section and shorten step 7 to a pointer, or move the full runtime matrix into a references/runtimes.md file.

Remove restated facts from 'Always Do This' that already appear in the workflow steps (the 10–1,000,000 range and the flat $0.025/molecule cost), keeping the checklist to non-obvious rules only.

Move the Codex heartbeat-automation specifics (cadence tiers, session_id polling) to a reference file so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The body is operational and free of basic-concept padding, but the runtime background-handling guidance is stated at length in step 7 and then largely repeated in the 'Always Do This' bullets (Codex yield_time_ms, nohup, heartbeat cadence), and the num_molecules range / flat $0.025 cost points are restated — fitting 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not a 4 because the redundancy is more than minor.

3 / 5

Actionability

Quotes a copy-paste-ready command block with concrete flags ('estimate-cost', 'start --idempotency-key ... --raw-output --transform id', 'download-results --poll-interval-seconds 60') and explicit placeholder-substitution instructions, covering the common submit-and-download flow — matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

Quotes an 8-step sequenced workflow with explicit validation checkpoints ('Enforce 10 <= num_molecules <= 1,000,000 before calling estimate-cost', 'show the USD cost, wait for explicit confirmation'), an 'Always Do This' checklist, and feedback loops for auth/sandbox failures and detached-download restart — matching 'Clear sequence with explicit validation steps; feedback loops for error recovery; checklists'; the batch-operation cap does not apply because validation is present.

5 / 5

Progressive Disclosure

Quotes well-signaled one-level-deep references to real files ('Read [references/api.md](references/api.md) for exact shapes', '[references/results.md](references/results.md) for output layout') with API shapes and results layout appropriately split out, but the verbose runtime-specific heartbeat/background instructions live inline in SKILL.md rather than a dedicated reference, fitting 'Good structure; most content is appropriately placed; minor organization gaps'; not a 5 because of that inline bulk.

4 / 5

Total

17

/

20

Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-constructed: it states a concrete capability, gives explicit positive and negative trigger guidance, and draws a clear boundary against adjacent screening skills. Its only weakness is that it names a single primary action rather than enumerating several specific capabilities.

DimensionReasoningScore

Specificity

Quotes 'Design new small-molecule binders with Boltz' — it names the domain and one concrete action, but lists only a single primary verb rather than multiple specific actions, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'; it is not a 4 because no additional distinct actions are enumerated.

3 / 5

Completeness

Quotes 'Design new small-molecule binders with Boltz' (what) and 'Use when generating novel ligands or hits for a target without a fixed compound library' (when) with an explicit negative boundary 'Not for screening existing molecules or one-off docking' — clearly and explicitly answers both what and when with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Quotes 'novel ligands or hits for a target', 'fixed compound library', 'screening existing molecules', and 'one-off docking' — good natural keyword coverage including negative triggers, but missing common synonyms like 'drug candidates' or 'lead compounds', fitting 'Good keyword coverage; a few natural terms missing'; not a 5 because coverage is not comprehensive.

4 / 5

Distinctiveness Conflict Risk

Quotes 'without a fixed compound library' and 'Not for screening existing molecules or one-off docking' — a clear niche with an explicit boundary against the sibling screening/docking skills, minimal conflict risk, matching 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.