CtrlK
BlogDocsLog inGet started
Tessl Logo

alphafold2

Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer evoformer, to validate designed sequences by self-consistency pLDDT, ipTM, and RMSD, or to run a quick MSA-backed prediction using the public MMseqs2 server.

78

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A tight, high-signal body: executable commands, the two non-obvious operational gotchas that would otherwise hang the job, and an error-to-fix table with recovery loops, all without padding.

DimensionReasoningScore

Conciseness

Lean and dense with non-obvious operational knowledge (the gVisor unified-memory loop, the shared MSA-server bottleneck) without explaining basics Claude already knows; every section earns its tokens.

3 / 3

Actionability

Provides a copy-paste-ready colabfold_batch command with flags, concrete env-var overrides (TF_FORCE_UNIFIED_MEMORY=0, fraction 0.95/0.9), exact output filename patterns, and a fixes-for-each-error table.

3 / 3

Workflow Clarity

The single fold action is unambiguous, and the error-recovery table plus the MSA caching workflow (run --msa-only, reuse .a3m) provide explicit feedback loops for the fragile batch/MSA operations.

3 / 3

Progressive Disclosure

Self-contained with no bundle files, organized into clearly headed sections; the gotchas are core runtime content rather than deep-dive material that should be split into separate reference files.

3 / 3

Total

12

/

12

Passed

Description

100%

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

An excellent description: concrete multi-action capability list, explicit third-person trigger guidance, and a well-scoped niche that distinguishes it from neighbouring structure-prediction skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — fold a sequence or complex, validate designed sequences by pLDDT/ipTM/RMSD, and run an MSA-backed prediction — matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (predict/validate structures via ColabFold) and when via the 'Reach for this skill to fold… to validate… or to run…' trigger clause, not merely implied.

3 / 3

Trigger Term Quality

Covers natural terms a structural-biology user would actually say: 'protein structure', 'monomers and multimers', 'AlphaFold2', 'fold a sequence', 'pLDDT/ipTM/RMSD', 'MSA', and 'MMseqs2 server'.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear AlphaFold2/ColabFold niche with distinct triggers and explicit routing to boltz/chai1/openfold3 for non-protein cases, making wrong-skill conflicts unlikely.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
UnicomAI/wanwu
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.