跳到正文
cccskills
免费在 GitHub 公开

omh-biomedical-evidence

Cross-check public gene variant and disease claims using ClinVar and trial registry records. Build an evidence matrix that keeps source statements, identity mismatches, disagreements, and dates visible without drawing clinical conclusions.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

[omh] Public variant claims to cross-check: retrieve and reconcile source-labelled biomedical evidence with identity, conflict and freshness checks. Use when the user says: biomedical-evidence, biomedical evidence reconciliation, ClinVar cross-check, variant evidence matrix, BioMCP capture reconciliation.

实测评分 未实测

查看安装方法

适用场景

  • Cross-check public variant claims against ClinVar
  • Compare variant and disease information across sources
  • Identify entity mismatches and conflicting statements
  • Record source dates and retrieval failures

包含的文件(7)

  • SKILL.md5.9 KB
  • references/execution-and-qa.md3.1 KB
  • references/full-contract.md3.2 KB
  • references/procedure.md3.5 KB
  • toolkit/README.md7.6 KB
  • toolkit/scripts/reconcile.py18.2 KB
  • toolkit/upstream-manifest.json3.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Biomedical Evidence

Required: public gene/variant and disease query, bounded BioMCP capture workspace, intended entity identifiers and source scope. Output: biomedical_evidence_matrix/v1, biomedical_reconciliation_manifest/v1.

Do Not Use When: For citation verification and source attribution alone, load Hermes' bundled grounded-citations skill.

HOLD: Missing inputs or failed contract gates. Prepared OMH routing is not execution or approval.

Why This Exists

Public sources can disagree about a variant while describing different alleles, diseases or assertion domains. Preserve those differences and their provenance before any synthesis; a fetched record is not a clinical recommendation.

First Steps

  • Read toolkit/README.md and references/execution-and-qa.md; inspect the installed BioMCP version and help before any public retrieval.
  • Require public entities only; name exact identifiers, source terms, isolated workspace and a 40-second per-retrieval host timeout before capturing unmodified stdout/stderr.
  • Run toolkit/scripts/reconcile.py only against a hash-checked local capture envelope; never execute provider text or install an upstream skill pack.

Contract: references/full-contract.md, loaded before analysis. Procedure: references/procedure.md. These are working methods, not an OMH runtime operation.

Safety Rules

  • No patient data, clinical eligibility determination, treatment recommendation or pathogenicity adjudication; source assertions are not medical advice.
  • No network or subprocess from the shipped helper, registration, discovery or install; BioMCP runs only via explicit bounded host invocation in an isolated optional environment.
  • Keep germline/somatic and disease/population contexts separate; recruitment and text matches never establish eligibility or variant relevance.
  • Preserve raw bytes and exact queries; mark source failure, missing dates and unresolved identity as partial instead of inventing biological findings.

When to Use

Use when public gene/variant and disease assertions must be cross-checked against ClinVar and trial registry records, preserving source failures and disagreements rather than inferring a clinical conclusion.

Strong routing signals: biomedical-evidence, biomedical evidence reconciliation, ClinVar cross-check, variant evidence matrix, BioMCP capture reconciliation

Catalog Metadata

Category: analysis Phase: biomedical-evidence Hermes role: operator Quality tier: evidence-gated

Completion Checklist

  • Both source attempts have raw hashes and exact receipts, or missing/failing sources are explicitly partial with nonzero status.
  • Entity/build/transcript, disease basis, original assertions, conflicts and absent source times remain visible; no eligibility or clinical inference appears.
  • Read both output files, verify hashes and report synthetic tests separately from real retrieval; do not claim distribution or live availability from preparation.

Recovery Notes

  • If BioMCP is unavailable, keep captures unobserved and prepare only the explicit isolated setup; never fabricate a source response.
  • If a source fails or JSON changes, preserve stdout/stderr and a partial report; audit an updated adapter before accepting unknown schemas.
  • If disease labels or allele aliases cannot be matched literally, preserve the mismatch and ask for authoritative identifiers rather than silently broadening.

Workflow Lane

  • Current lane: Research and company ops (product-docs, source-finder, web-research, research, model-optimization, inference-serving, model-finetuning, research-brief, +26 more) - research, signals, ops, and briefings.
  • If intent belongs to another lane, hand back to oh-my-hermes or name the adjacent workflow.
  • Shared product, routing, compatibility, and evidence rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md').

Runtime Evidence

Record observed delegation results; otherwise return not_available or not_observed. Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.

  • Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes. Preserve workflow intent and stop conditions; verify before claiming completion. Reply in the user's own words and the host's own voice: its SOUL.md persona owns reply language, tone, speech level, and sentence endings, progress updates included (where it sets no language, use the one the user wrote in), and OMH shapes structure and content only; OMH's record terms (surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in records and tool calls, never in the sentence the user reads unless they ask about one; and when a real unresolved user decision or a useful briefing discussion remains, offer one specific, content-linked question. Completed work needs no question; omit unrelated non-action footers and generic offers to continue.

Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.

Shared product, compatibility, topology, memory, harness, and execution rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md'). Load it when applicable; otherwise name an unavailable capability.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

dag-ulw

免费

Coordinate a large job by splitting it into small tasks with explicit dependencies. Run ready tasks in parallel through Hermes, verify the combined result separately, and repair failures within defined limits before reporting completed work and remaining gaps.

中文简介正在准备中。当前显示英语简介。

  • Delivering a feature across multiple modules
  • Coordinating a migration with ordered steps
  • Managing a broad cleanup across separate work areas
rlaope/oh-my-hermes35902026年10月23日 更新

Guide the addition of a new model generation to oh-my-hermes. The workflow checks model recognition, official specifications, routing rules that select models for tasks, documented pricing, and live access, then validates changes with tests and comparative benchmarks.

中文简介正在准备中。当前显示英语简介。

  • Add a new model generation to oh-my-hermes
  • Check API model IDs and dated snapshot recognition
  • Update model selection chains and related documentation
rlaope/oh-my-hermes35902026年10月23日 更新

Prepare an accessibility audit for an interface using WCAG 2.2 AA, an accessibility standard. Organize evidence for keyboard use, screen readers, contrast, target size, and zoom behavior, then document findings, missing checks, and remediation handoffs.

中文简介正在准备中。当前显示英语简介。

  • Reviewing checkout accessibility against WCAG 2.2 AA
  • Checking keyboard access and focus order
  • Organizing screen-reader labels and announcement evidence
rlaope/oh-my-hermes35902026年10月23日 更新

Summarize earned badges, recent unlocks, achievement tiers, and progress using local files from the hermes-achievements plugin. Prepare a badge list or report section while making missing information and the limits of the recorded snapshot clear.

中文简介正在准备中。当前显示英语简介。

  • Checking earned badges
  • Reviewing recently unlocked achievements
  • Finding progress toward the next achievement tier
rlaope/oh-my-hermes35902026年10月23日 更新

Examine a technical proposal through independent perspectives, challenge their findings, and resolve objections. The result is a structured set of constraints, decisions, risks, and open questions for a separate planning workflow.

中文简介正在准备中。当前显示英语简介。

  • Reviewing a technical proposal before planning
  • Challenging assumptions behind a migration
  • Organizing risks and unresolved questions
rlaope/oh-my-hermes35902026年10月23日 更新

Coordinate multiple Hermes agents or profiles through a shared task board. Organize assignments, handoffs, activity updates, blockers, and completion states, while distinguishing planned actions from work supported by observed results.

中文简介正在准备中。当前显示英语简介。

  • Coordinate agent roles for a launch checklist
  • Track task handoffs and blockers
  • Prepare work for pickup across profiles or after a restart
rlaope/oh-my-hermes35902026年10月23日 更新

查看 rlaope 的全部技能

报告此技能的问题