ontology-access-kit
Skills for querying ontologies using the Ontology Access Kit (OAK). This should only be used for complex ontology operations, for basic external ontology searching use the OLS MCP
What this skill does
# OAK Guide ## Overview OAK is a powerful command line library for accessing ontologies. It can be installed via: - `uv add oaklib` - `pip install oaklib` The main command is `runoak` ## When to use OAK is generally to be used for more complex operations. - if you want to do basic search over external ontologies, you should favor the OLS MCP over OAK - if you are working with local obo files, then hacky obo tools like `obo-grep.pl` may be better ## Adapters You typically want to use the sqlite adapter. This gives you fast access to any ontology in OBO, plus a number of other commonly used ontologies, found in semantic-sql. Example: `runoak -i sqlite:obo:cl COMMAND COMMAND-OPTS ARGS` Note the `-i` comes (*before*) the command-specific opts You can also access any ontology in OLS or BioPortal: - `runoak -i bioportal:snomedct relationships SNOMEDCT:128351009` - `runoak -i bioportal:efo tree -p i EFO:0004200` But some OAK commands may not be implemented. With OLS or BioPortal you can also do searches over all ontologies: - `runoak -i bioportal: info l~NovaSeq` - `runoak -i ols: info l~NovaSeq` To work with local obo files: - `runoak -i impleobo:my_ont.obo info MY:1234 -O obo` ## Common Operations You can find a list of all commands with `runoak --help`. oak is highly fully featured, and you are encouraged to explore to find the functionality you need. We provide some examples below. We use `info` for many examples, but note that many options and arguments work across different commands * Lookup * By exact label: `runoak -i sqlite:obo:cl info neuron` (returns `CL:0000540 ! neuron`) * By exact label (multiple): `runoak -i sqlite:obo:uberon info finger toe` * Search (any match): `runoak -i sqlite:obo:cl info 'l~T cell'` * Search (starts with): `runoak -i sqlite:obo:cl info l^neuron` * Fetching detailed info * OBO format: `runoak -i sqlite:obo:cl info CL:0000540 -O obo` * relationships: `runoak -i sqlite:obo:cl relationships --direction both CL:0000540` * mappings: `runoak -i sqlite:obo:mondo mappings 'Marfan syndrome'` * tree (is-a only): `runoak -i sqlite:obo:cl tree -p i CL:0000540` * metadata: `runoak -i sqlite:obo:chebi term-metdata CHEBI:35235` * Complex queries * subclasses: `runoak -i sqlite:obo:cl info .sub CL:0000540 | head` * disjunctions (OR): `runoak -i sqlite:obo:cl info .sub neuron .sub 'T cell' | tail` * conjunctions: `runoak -i sqlite:obo:cl info .sub neuron .and .desc//p=i,p forebrain` (neurons and is-a/part-of the forebrain) * minus: `runoak -i sqlite:obo:cl info .sub neuron .minus .desc//p=i,p forebrain` (neurons and NOT is-a/part-of the forebrain) * Visualization * `cl viz -p i,p,RO:0002215 'dopaminergic neuron' -o /tmp/dn.png` - subgraph from a CL term. * note that graphviz requires installing og2dot * Subsets * list subsets: `runoak -i sqlite:obo:go subsets` - list all subsets (goslim_prokaryote etc) * terms in subsets: `runoak -i sqlite:obo:go info .in goslim_generic` - all terms in a subset * terms in subsets: `runoak -i sqlite:obo:go info .in goslim_generic .minus .in goslim_prokaryote` - all terms in a subset not in another * Other * `runoak lexmatch --help` for aligning ontologies * `runoak statistics --help` for summary stats ## Common Options and Idioms ### Graphs OAK is very graph oriented, following ontologies like GO, CL Typically for graph operations you want to operate over only is-a and part-of, so use `-p i,p` You can also specify RO/BFO ids. E.g. ```bash runoak -i sqlite:obo:ro info 'capable of' RO:0002215 ! capable of ``` ```bash cl relationships -p RO:0002215 'dopaminergic neuron' subject predicate object subject_label predicate_label object_label CL:0000700 RO:0002215 GO:0061527 dopaminergic neuron capable of dopamine secretion, neurotransmission ```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.