菜单
Produce a standardized semantic-modeling diff report between two KG-Microbe merged-KG releases. Use when comparing KG versions to quantify changes in biolink/METPO categories, predicates, relations, CURIE prefixes, knowledge sources, and predicate × category signatures.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Knowledge modeling review of KG-Microbe transforms and merged KG for alignment with METPO, Biolink Model, and KGX specification. Use when auditing transform output quality, validating categories/predicates, checking CURIE prefix registration, or preparing a release.
Add a new data source transform to KG-Microbe end-to-end — from "should we even ingest this?" through deep research, cross-reference analysis, semantic design, code scaffold, integration, verification, and shipping the PR. Bakes in the CLAUDE.md 7-step checklist plus the research + analysis + verify phases that keep the KG coherent. Use whenever the ask is "ingest X", "add source Y", or "integrate a new database into kg-microbe".
Ship a messy topic branch as a set of clean, focused PRs. Walks through triage of committed commits + working-tree modifications + untracked files, extracts misfiled commits to their own branches, splits orthogonal changes into separate PRs, gitignores build noise, opens follow-up issues for deferred items, and merges in the correct dependency order. Use when a working branch has accumulated mixed commits, uncommitted work, and dozens of untracked scratch files and needs to reach master.
Emit a Codex-ready review prompt for the KG-Microbe repository focused on code logic, consistency, robustness, bugs, bottlenecks, and scalability. Use before delegating a deep review pass to Codex (via the codex:rescue subagent) or another external code-review agent so the target is precisely scoped and the review dimensions are enforced.
Determine whether local KG-Microbe transform outputs (data/transformed/<source>/) and merged KG (data/merged/) are current relative to origin/master. Compares latest commit times on origin/master touching each transform's code directory against local output mtimes; also checks merge stage against merge_utils/, merge.yaml, and every transform output. Use before cutting a release, before running kg-release, or when triaging "why did my merged KG change".
Work with KG-Microbe's unified chemical mapping system (`mappings/kgmicrobe_unified_entity_mappings.sssom.tsv.gz` and `kg_microbe/utils/chemical_mapping_utils.py`). Use when adding a new mapping source, regenerating the unified file, debugging a missing ChEBI lookup, validating mappings against OLS, or reasoning about which source wins when sources disagree.
| name | kg-release-diff |
| description | Produce a standardized semantic-modeling diff report between two KG-Microbe merged-KG releases. Use when comparing KG versions to quantify changes in biolink/METPO categories, predicates, relations, CURIE prefixes, knowledge sources, and predicate × category signatures. |
Compare two merged-KG releases (e.g. data/merged/20260120 vs data/merged/20260422_nometatraits) along the axes that matter for semantic modeling, not just row counts:
The report is a single Markdown file suitable for PRs, release notes, or hand-off to ontology reviewers.
# Two release directories under data/merged/
poetry run python .claude/skills/kg-release-diff/kg_release_diff.py \
--old data/merged/20260120 \
--new data/merged/20260422_nometatraits \
--out data/merged/release_diff_20260120_vs_20260422_nometatraits.md
# Or provide explicit TSV paths (either can be gzipped)
poetry run python .claude/skills/kg-release-diff/kg_release_diff.py \
--old-nodes data/merged/old/merged-kg_nodes.tsv \
--old-edges data/merged/old/merged-kg_edges.tsv \
--new-nodes data/merged/new/merged-kg_nodes.tsv \
--new-edges data/merged/new/merged-kg_edges.tsv \
--old-label 20260120 \
--new-label 20260422_nometatraits \
--out release_diff.md
| Flag | Default | Purpose |
|---|---|---|
--old PATH / --new PATH | — | Directory containing merged-kg_nodes.tsv + merged-kg_edges.tsv (accepts .gz) |
--old-nodes/--old-edges/--new-nodes/--new-edges | — | Explicit file paths (overrides directory lookup) |
--old-label STR / --new-label STR | directory name | Human-friendly labels that appear in the report header |
--out PATH | stdout | Write the Markdown report here |
--max-rows N | 0 (no cap) | Row cap per file — useful for smoke tests |
--no-signatures | false | Skip the predicate × category signature pass (saves ~150 MB RAM on large releases) |
When run interactively, after the script finishes:
The script emits progress lines to stderr ([scan] old nodes: …) so long runs don't look hung.
kg_release_diff.py — streams both TSVs with csv.DictReader (reads by column name, tolerating column order / count differences).id → category map used for predicate × category signatures (~150 MB for a 2 M-node release; disable with --no-signatures if memory-constrained).BIOLINK_DEPRECATED_CATEGORIES near the top of the script — update as the Biolink Model evolves.The generated Markdown has exactly these sections:
primary_knowledge_source distributionprovided_by distribution on nodes--no-signatures)Each added/removed/delta table is capped at 40 rows with a …and N more footer.