guided-workflows
Create reviewable, researcher-approved plans from Molemo scientific tools.
Skill by phenixace
Chalk Labs
Need help deploying guided-workflows?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/phenixace-guided-workflows
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/guided-workflows
What's inside
- Skill name
guided-workflows- Description
- Create reviewable, researcher-approved plans from Molemo scientific tools. Use when a user asks for a plan, pipeline, guided analysis, or multi-step run that should not execute before explicit approval.
- License
- MIT
- Instructions
- 7 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- openai.yaml · agents/
- handler.py · scripts/
- skill.json
SKILL.md (first lines)
# Guided Workflows Use `workflow_list_templates` to find a supported workflow, then use `workflow_create_plan` with concrete inputs. State that the plan is pending researcher approval. The Agent may create and inspect plans, but must never imply that a pending plan has run. Approval and execution are intentionally unavailable as skill tools and must happen through the local WorkBench approval control.
From phenixace/Molemo_WorkBench, MIT.
More from phenixace/Molemo_WorkBench
- 0.557score
protein-structure
phenixace
Retrieve experimental structures from RCSB PDB, predicted structures from AlphaFold DB, or parse PDB/mmCIF files in the local workspace.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
hmmer-profile-search
phenixace
Validate and run bounded local HMMER3 profile-to-protein searches with domain coordinates, explicit thresholds, researcher approval and auditable outputs.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
research-router
phenixace
Route broad life-science research questions to the smallest useful set of Molemo skills.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
scientific-visualization
phenixace
Turn molecular and protein analysis results into declarative property charts and residue-level sequence tracks.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
chembl-bioactivity
phenixace
Review source-linked ChEMBL small-molecule activity evidence for an exact UniProt single-protein target.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
sequence-search
phenixace
Search one concrete protein or nucleotide sequence against a FASTA database inside the local Molemo workspace with NCBI BLAST+.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
single-cell-analysis
phenixace
Validate local single-cell raw-count matrices and propose researcher-approved Scanpy QC, embedding, clustering, and marker exploration.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
clinical-trial-landscape
phenixace
Search ClinicalTrials.gov for a bounded trial landscape or review the posted tabular results of one exact NCT record.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
dna-variant-calling
phenixace
Preflight and run a bounded, researcher-approved paired-end short-read DNA alignment and candidate variant-calling workflow with local BWA, samtools, and…
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
functional-analysis
phenixace
Review a bounded human gene set with Reactome pathway overrepresentation and STRING identifier mapping, enrichment, functional association networks, and PPI…
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
geo-dataset-discovery
phenixace
Discover public NCBI GEO Series from a biological question with exact GSE-only query provenance, bounded metadata, study-design caveats, and an approved…
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
geo-series-matrix-import
phenixace
Inspect and import one official NCBI GEO Series Matrix through a researcher-approved, bounded local workflow while preserving sample metadata, values and…
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 29, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/phenixace/Molemo_WorkBench
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from phenixace
- 0.557score
scientific-visualization
phenixace
Turn molecular and protein analysis results into declarative property charts and residue-level sequence tracks.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
chembl-bioactivity
phenixace
Review source-linked ChEMBL small-molecule activity evidence for an exact UniProt single-protein target.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
hmmer-profile-search
phenixace
Validate and run bounded local HMMER3 profile-to-protein searches with domain coordinates, explicit thresholds, researcher approval and auditable outputs.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
research-router
phenixace
Route broad life-science research questions to the smallest useful set of Molemo skills.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
protein-structure
phenixace
Retrieve experimental structures from RCSB PDB, predicted structures from AlphaFold DB, or parse PDB/mmCIF files in the local workspace.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
ngs-qc
phenixace
Run deterministic FASTQ quality control on a file inside the constrained local workspace.
SkillBFreshness: B★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get guided-workflows running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
guided-workflows skill. Agent Mart. https://agentmart.dev/skills/phenixace-guided-workflows (last updated 2026-10-24)