Community recipe · Tool workflows

Infer an evolutionary tree with a traceable tool chain

Source-backed example. Practical decision guidance is proposed and untested; this is not a full implementation guide.

The problem

Evolutionary analysis needs a reproducible path from raw sequences to supported relationships rather than an unexplained tree image.

Agent job

Validate, align and trim sequences, select a model, infer a tree and export support information and replay materials.

Expected output

A Newick tree, support tables and a replay bundle for expert inspection.

Where this framing comes from

Core problem: Editorial purpose framing
Agent job: Editorial purpose framing
Expected output: Editorial purpose framing
Relevant job roles: Editorial purpose framing
Benefit type: Editorial purpose framing

Editorial framing and outcome limits

Describes the task’s purpose and intended output; measured benefit, safe unsupervised operation and successful delivery are not established by this framing.

Editorial synthesis based on the linked source. This framing does not add evidence of successful delivery or results.

Case-specific decision guidance · untested

Case-specific decision guidance and first checks are original proposals. The linked source supports the attributed task; this added guidance has not been executed.

Read the attributed source evidence and original caveats below ↓

Why use this

A researcher planning evolutionary analysis may have sequence records with inconsistent identifiers, uncertain alignment choices or undocumented tool options. A tree image alone cannot explain which inputs and analytical decisions produced the relationships.
A traceable analysis plan could define the required input checks, intermediate artifacts and expert review questions before any computation. It would preserve uncertainty in model choice and support interpretation instead of presenting a planned tool chain as validated science.

Why an agent / simpler alternative

Useful judgment: Organize the analysis specification and identify missing provenance or incompatible stage assumptions.
Simpler alternative: Use an established reviewed pipeline when its assumptions fit the study and inputs are ready.
Unsuitable when: The task requires expert biological conclusions without adequate methods or data review.

Proposed inputs

Name
Authorized sequence manifest
Owner
Researcher
Minimum scope
Non-sensitive sequence identifiers, provenance and intended comparison scope
Quality check
Confirm unique IDs, data rights and expected sequence type.
Name
Analysis specification
Owner
Domain expert
Minimum scope
Approved stage choices, candidate tools/options and intended outputs
Quality check
Mark undecided trimming, model and support settings for expert resolution.

Access and setup — proposed or unknown

Proposed minimum: Offline manifest and pipeline-plan review; no biological computation or tool installation.
Compatibility unknowns: Unknown: exact runtime, tool versions, flag compatibility and computational resources.
External actions requiring approval: Uploading datasets, installing tools, running compute or overwriting existing output directories.

Expected deliverable and review checks

Proposed artifact: Proposed stage/artifact manifest for alignment, trimming, inference, support tables and replay materials.
Critical checks: Input identifiers and provenance persist through every planned stage.
Method choices and output-directory overwrite decisions remain explicit.
Missing output evidence: No new workflow run or output inspection was performed for this overlay.

Failure signals and proposed responses

Signal
Duplicate sequence identifiers appear in the input manifest.
Why it matters
Later outputs may be difficult to attribute correctly.
Proposed response
Resolve identifier uniqueness before any analysis.
Signal
A planned option is unsupported by the specified tool version.
Why it matters
The proposed chain may fail or run with unintended assumptions.
Proposed response
Require documented compatibility verification before execution.

Effort and cost — unknown

Setup work: Define scientific scope and provenance requirements with an expert.
Ongoing review: Inspect actual intermediate/results artifacts only in separately authorized analysis.
Unknowns: Unknown: compute cost, methodological suitability and robustness of inferred relationships.

First check — proposed, unexecuted

Status: proposed_unexecuted
Synthetic fixture: An invented pipeline manifest contains duplicate IDs and a pre-existing output directory with no overwrite decision.
Acceptance checks: Both conditions block proposed execution.
No tree or scientific support claim is generated.
Stop conditions: Biological interpretation, tool execution or overwrite permission is required.

Limits

Editorial analysis planning; manifest review is not sequence validation, phylogenetic inference or scientific verification.

Tasks: General workflows

Useful for: Researcher Data analyst

Editorial relevance from the title and source-supported actions; not evidence of the operator’s occupation.

OpenClawIndependent testing: No

Editorial candidate. This is source-backed reporting or a documented workflow. BotCurrent has not independently tested this task. A proposed Canadian adaptation is not evidence of a Canadian deployment or compliance certification.

Original source

https://github.com/ClawBio/ClawBio/blob/main/skills/phylogenetics-builder/SKILL.md ↗

Attributed to: ClawBio

Community recipe

Original action type: tool_action
What the source supports: The recipe validates sequences, aligns and trims them, selects a model, performs tree inference and exports a Newick tree with support tables and a replay bundle.
Source outcome limits: This community recipe describes a procedure; it does not prove successful execution or independently reproduced results.
Evidence attribution caveat: This community recipe describes a procedure; it does not prove successful execution or independently reproduced results.
Source approval description: Warn before overwriting a nonempty output directory; supplied flags are to be validated.
Named tools: OpenClaw; ClawBio; MAFFT/MUSCLE; trimAl; IQ-TREE2/RAxML-NG; Bio.Phylo
Model or version: Unknown
Publication date: Unknown
Source last checked: 2026-10-14
Demonstrated in Canada: Unknown
Canadian availability: Unknown
Proposed Canadian adaptation: Proposed: begin with public or institution-approved research data in a Canadian-controlled workspace; obtain the institution’s privacy and research-governance review before using identifiable samples. No Canadian deployment was demonstrated.
Recommended approval boundaries: A domain expert should approve inputs, parameters and compute budget, inspect outputs, and authorize any sharing or scientific publication; do not use as an autonomous clinical decision system.