crossframe-critical
Use only when the user explicitly names crossframe-critical for a Chinese structural critique dossier, article plan, or long-form critical essay.
- License 许可
- MIT
- 最近更新
- 2026-11-08
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- crossframe-critical
- risk
- safe
- tags
- [ "crossframe", "chinese", "critique", "essay", "structural-analysis" ]
- tools
- [ "Agent Skills", "Codex", "Claude" ]
- author
- xi-kari
- source
- community
- license
- MIT
- category
- content
- date_added
- 1781568000000
- description
- Use only when the user explicitly names crossframe-critical for a Chinese structural critique dossier, article plan, or long-form critical essay.
- source_repo
- xi-kari/crossframe-skill
- source_type
- community
- license_source
- https://github.com/xi-kari/crossframe-skill/blob/main/LICENSE
02 资源文件 6
- 参考文档agents/openai.yaml406 B
- 参考文档evals/crossframe-critical-smoke-tests.md4.2 KB
- 参考文档protocols/critical-article-protocol.md3.1 KB
- 参考文档references/critical-matrix.md2.5 KB
- 参考文档references/example-and-evidence-rules.md2.0 KB
- 参考文档templates/critical-output-template.md2.0 KB
03 SKILL.md 正文
CrossFrame Critical
When to Use This Skill
- Use only when the user explicitly names
crossframe-critical,$crossframe-critical, or asks to test this critical parallel skill. - Use for Chinese structural critique dossiers, critique matrices, article plans, and long-form critical essays.
- Do not include it in the default
crossframe-suiteroute.
Packaged Source Note
This AAS-ready copy preserves the original CrossFrame skill body below. Chinese remains the canonical semantic layer; English metadata is only for discovery, installation, and repository review.
Limitations
- The skill body is intentionally Chinese-canonical; English metadata is for discovery and does not replace the original Chinese terms.
- Use only after explicit CrossFrame invocation or
crossframe-suiterouting; do not apply it as a generic default reasoning layer. - It structures analysis, drafting, and review, but does not replace source verification, domain expertise, or legal, medical, or financial judgment.
本 skill 不独立触发。 所有 CrossFrame 任务统一从
crossframe-suite入口调度。用户无需直接调用本 skill;suite 根据路由规则在需要时自动加载。
This is a parallel local test skill. It does not replace crossframe, crossframe-essay, crossframe-public, or crossframe-suite.
Position
crossframe-critical writes critical Chinese essays that first use CrossFrame to establish structure, evidence boundaries, scale, mechanism candidates, and judgment grade, then sharpen the output into critique.
The critique may absorb Marxist problem awareness: interests, cost transfer, alienation, commodification, ideology, naturalized domination, and reproduction of conditions. It must not mechanically force every topic into class/capital language.
Required Reading
On every trigger, read:
../crossframe/SKILL.md../crossframe/references/read-routing-map.md- If the critique touches high-responsibility, public, AI/process artifact, lifecycle, trapped-subject, or article-output scenarios, reuse
../crossframe/templates/read-state-capsule.mdasv5-read-state-capsuleand run../crossframe/worksheets/source-anchor-integrity-check.md; if the capsule is missing, return to../crossframe/SKILL.mdinstead of inventing source routing here. protocols/critical-article-protocol.mdreferences/critical-matrix.mdreferences/example-and-evidence-rules.md- 若涉及真实公共对象、最新事实、机构、平台、政策、人物、公司、数据、AI/过程性产物或强判断,读取
../crossframe/references/source-ledger-workflow.md并建立来源台账。 templates/critical-output-template.md
If the topic needs long-form style control, also read ../crossframe-essay/SKILL.md and reuse only its article discipline, not its whole output contract.
Workflow
- Build the CrossFrame base: object, fact boundary, scale window, mechanism candidates, judgment grade, and evidence gaps.
- Apply the critical matrix: cost chain, benefit chain, power/resource distribution, concept concealment, reproduction mechanism, weak signals, and counterconditions.
- Plan the article: central thesis, reader position, examples, section sequence, word allocation, and ending aftertaste.
- Write the full essay from the dossier. Default body length is 1800-2800 Chinese characters unless the user overrides it.
- Run a final boundary check: no personality judgment, no hat-labeling, no conspiracy claim, no unverified strong judgment, no slogan replacing analysis.
Output
Default output has exactly three visible sections:
# 批判底稿
# 篇章方案
# 正文
Do not collapse the result into a short answer, checklist, memo, or diagnosis summary unless the user explicitly asks for that.
Hard Rules
- Start from CrossFrame structure, then become critical; do not begin from indignation and decorate it with structure words.
- Critique mechanisms, interests, rhetoric, institutions, and responsibility chains; do not turn structural critique into personal condemnation.
- A real or recent public event requires source checking before factual claims, with a visible source ledger summary. Unverified examples must be labeled as analogy, hypothesis, or common pattern.
- Use at least two concrete examples in the essay body unless the user provides a single narrowly bounded case and asks not to expand.
- Include at least one countercondition, evidence gap, or withdrawal condition.
- Do not use Marxist terms as prestige vocabulary. If a term cannot be translated into who pays, who benefits, what is hidden, and how the condition repeats, remove it.
04 同仓库更多 Skills
vss-summarize-video
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.
vss-setup-video-analytics-api
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
vss-setup-behavior-analytics
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
vss-search-archive
Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).
vss-query-analytics
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.
vss-manage-video-io-storage
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.