Borrowing it
Nothing to install: this file belongs to xi-kari/crossframe-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xi-kari/crossframe-skill/main/.claude/skills/crossframe-essay/SKILL.mdgit clone --depth 1 https://github.com/xi-kari/crossframe-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-essay)<a href="https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-essay"><img src="https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-essay.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.04123 |
| Opus 5 | $0.00040 | $0.02062 |
| Sonnet 5 | $0.00016 | $0.00825 |
| Haiku 4.5 | $0.00008 | $0.00412 |
Grade A, and why
crossframe-essay scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrossFrame Essay
如果用户任务需要先诊断、再进入公共/组织/辩论/读书等专项判断，最后才成文，先读取 ../crossframe-suite/SKILL.md 做总调度；本 skill 只负责文章底稿与正文生成。
语言原则
中文为权威语义。CrossFrame Essay 只是写作入口和 skill id，不承担概念解释权；英文只用于文件名、接口、必要双语标注或对外传播名。遇到中英文理解冲突时，以中文术语、中文判断和普通中文读者可理解的表达为准。
CrossFrame Essay 是 crossframe 的平行写作 skill，不替代 crossframe。它把 CrossFrame 的结构诊断、概念保真、尺度拆分和证据边界，转成面向普通中文读者的批判性洞察文章；当主题需要更深表达时，再把结构判断提升为上位概念、思想参照和经典互文。自动成文默认使用 full-visible-v5-longform 输出档位：完整可见底稿 + 完整长文正文。声口由 crossframe-suite 传入的 voice_mode、角色和 topic_sensitivity 决定；用户显式要求亲切/编辑口吻时启用现代编辑底色，显式要求中性报告、备忘录、表格、纯诊断或学术摘要时关闭文章声口。
核心原则：先形成结构洞察底稿，再写文章正文。不要跳过推理直接成文。
长文原则：底稿不是正文的替代品。输出了完整可见底稿之后，仍必须写完整文章正文；凡来自 crossframe-suite 且未显式关闭文章层的任务，一律按完整文章处理，不压缩成摘要、短答或项目符号说明。
必须执行的顺序
- 判断写作模式：
- 自动成文：一次性输出
结构洞察底稿和文章正文，默认output_mode=full-visible-v5-longform。 - 互动打磨：给候选开头、中心命题和文章骨架，再逐段推进。
- 自动成文：一次性输出
- 读取
../crossframe/SKILL.md。 - 读取
../crossframe/references/runtime-read-policy.md和../crossframe/references/read-routing-map.md，把主题路由到相应 CrossFrame protocol。 - 读取
../crossframe/references/continuity-closure-map.md，至少确认v5-seven-gates-diagnosis-pack与v5-domain-translation-normative-source-pack，并展开它们的必须同读闭包；公共、亲密、长期演化、AI 材料或高责任主题追加对应 v5 联读包及其闭包。需要包说明时再定向读取../crossframe/references/continuity-bundles.md或具体包文件。 - 用
../crossframe/worksheets/source-continuity-check.md检查是否只读了孤立概念卡；深度文章只在源锚点不足、用户要求源审计或高责任核验时，定向读取../crossframe/references/v5-source-spine.md、../crossframe/references/v5-section-digest-index.md、../crossframe/references/v5-material-selection-map.md或../crossframe/references/v5-term-fidelity.md的相关局部。 - 复用
../crossframe/templates/read-state-capsule.md规定的v5-read-state-capsule；若上游未生成，回到../crossframe/SKILL.md补齐，不在 essay 内重新发明源路由。 - 用
../crossframe/worksheets/source-anchor-integrity-check.md检查文章中心命题、机制候选、高风险概念、行动边界和文章转译是否能回指胶囊源锚点；不能回指的内容必须标为“本文推断 / 表达转译 / 外部思想映射”。 - 读取
../crossframe/templates/claim-ledger.md和../crossframe/worksheets/claim-ledger-check.md。从上游crossframe复用或补齐claim ledger；文章中心命题、机制句、高风险概念句、行动建议、公共定性、概率排序和点睛句都必须绑定claim_id。若上游未生成，回到../crossframe/SKILL.md补齐，不在 essay 内重新发明判断。 - 读取
references/evidence-and-search-rules.md和../crossframe/references/source-ledger-workflow.md，决定本次是否需要联网或查源，并统一写入来源台账。 - 按需读取
references/critical-insight-principles.md。 - 如果主题是思想文章、公共议题、复杂关系/组织文章，或用户要求深度、概念上升、引经据典，读取
protocols/concept-elevation-protocol.md、references/reference-and-allusion-rules.md和references/concept-reference-map.md。 - 按 suite 传入的
voice_mode判断是否读取protocols/editorial-comrade-voice-protocol.md和references/editorial-voice-principles.md，并在底稿中写出正文声口方案。如果用户明确要求中性报告、备忘录、表格、纯诊断或学术摘要，才可关闭文章声口，并说明关闭原因。 - 自动成文时读取
protocols/essay-protocol.md，互动打磨时读取protocols/interactive-drafting-protocol.md。 - 先生成
结构洞察底稿，底稿中写出文章类型推荐与待选择，但不先读取写作技法文件。 - 底稿后确认文章类型：若用户或 suite 已显式指定
article_type，在底稿中记录并直接采用；若未指定且文章层开启，必须完整渲染templates/article-type-selection-dialog.md的九个选项、填入基于底稿的推荐项和推荐理由，并等待用户回复；若用户回复“默认/自动/都行”，采用选择器中的推荐项。文章类型选择器若要求用户选编号、默认项或推荐项，必须等待用户回复；若本次因用户明确授权不暂停，必须写明“继续采用推荐项”再推进。不得只写“已展示文章类型选择器（1-9）”。 - 用户选择文章类型后，再读取技法路由表和技法文件，然后生成
文章正文：读取references/article-technique-routing-map.md，默认最多读取 3 个核心技法 + 2 个辅助技法，再读取对应references/writing-techniques/*.md文件。 - 补全底稿中的
文章类型与写作技法选择字段，再从底稿转译出文章正文。
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 446 B
- evals/crossframe-essay-smoke-tests.md 9.8 KB
- examples/life-first-cause-essay-case.md 2.8 KB
- examples/organization-essay-case.md 2.2 KB
- examples/public-issue-essay-case.md 2.6 KB
- examples/relationship-essay-case.md 2.2 KB
- protocols/concept-elevation-protocol.md 2.6 KB
- protocols/editorial-comrade-voice-protocol.md 3.3 KB
- protocols/essay-protocol.md 15 KB
- protocols/interactive-drafting-protocol.md 2.1 KB
- references/article-technique-routing-map.md 7.6 KB
- references/concept-reference-map.md 2.1 KB
- references/critical-insight-principles.md 2.1 KB
- references/editorial-voice-principles.md 2.1 KB
- references/evidence-and-search-rules.md 3.9 KB
- references/reference-and-allusion-rules.md 1.7 KB
- references/writing-techniques/analogical-reasoning.md 2.5 KB
- references/writing-techniques/ancient-modern-global.md 2.6 KB
- references/writing-techniques/clouds-moon.md 2.6 KB
- references/writing-techniques/coincidence-structure.md 2.5 KB
- references/writing-techniques/direct-emotion.md 2.6 KB
- references/writing-techniques/double-bridge.md 2.6 KB
- references/writing-techniques/event-association.md 2.7 KB
- references/writing-techniques/feint-attack.md 2.6 KB
- references/writing-techniques/final-reveal.md 2.8 KB
- references/writing-techniques/fine-carving.md 2.6 KB
- references/writing-techniques/finishing-touch.md 2.9 KB
- references/writing-techniques/fixed-point-changing-scenes.md 2.6 KB
- references/writing-techniques/form-by-object.md 2.8 KB
- references/writing-techniques/guest-host-contrast.md 2.7 KB
- references/writing-techniques/hide-before-reveal.md 2.5 KB
- references/writing-techniques/index.md 2.3 KB
- references/writing-techniques/language-momentum.md 2.7 KB
- references/writing-techniques/layered-argument.md 2.7 KB
- references/writing-techniques/less-is-more.md 2.5 KB
- references/writing-techniques/life-from-dead.md 2.6 KB
- references/writing-techniques/meaning-beyond-words.md 2.6 KB
- references/writing-techniques/motion-for-stillness.md 2.5 KB
- references/writing-techniques/moving-viewpoint.md 2.6 KB
- references/writing-techniques/multi-edge-extension.md 2.7 KB
- references/writing-techniques/narration-commentary.md 2.7 KB
- references/writing-techniques/object-reason.md 2.7 KB
- references/writing-techniques/one-stone-many-birds.md 2.6 KB
- references/writing-techniques/one-word-spine.md 3.0 KB
- references/writing-techniques/personified-object.md 2.7 KB
- references/writing-techniques/point-spirit.md 2.8 KB
- references/writing-techniques/point-surface.md 2.6 KB
- references/writing-techniques/positive-negative-contrast.md 2.5 KB
- references/writing-techniques/praise-blame-interlace.md 2.5 KB
- references/writing-techniques/raise-high-drop-heavy.md 2.6 KB
- references/writing-techniques/release-to-capture.md 2.5 KB
- references/writing-techniques/remove-foundation.md 2.7 KB
- references/writing-techniques/retreat-to-advance.md 2.7 KB
- references/writing-techniques/same-different.md 2.6 KB
- references/writing-techniques/scene-emotion.md 2.6 KB
- references/writing-techniques/small-water-waves.md 2.6 KB
- references/writing-techniques/sparse-outline.md 2.5 KB
- references/writing-techniques/split-wood-reasoning.md 2.6 KB
- references/writing-techniques/stars-moon.md 2.7 KB
- references/writing-techniques/stream-consciousness.md 2.6 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 134 lines · 80 tokens per session scan A 83a19c186e2b
crossframe-essay is a skill published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 4,123 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
personalize-ai-assistant
Build or update privacy-first AI-assistant configuration and reusable preference skills for Codex, Claude Code, Cursor, Gemini CLI, and similar tools. Use when the user provides explicit preferences, existing config files, example rules, or asks to optimize AGENTS.md, CLAUDE.md, assistant rules, memory files, or…
polar-billing
This skill should be used when working on Polar billing system, Stripe integration, subscription lifecycle, checkout flows, or benefit provisioning.
dokploy-deploy
This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure Dokploy domains", or "look up Dokploy CLI commands".
simplify
This skill should be used when the user asks to "simplify", "clean up the diff", "run simplify", "simplify the changes", "review changed code for cleanup", explicitly invokes "/simplify", or asks to "commit without simplify", "skip simplify for this commit", or "commit this but skip simplify". Reviews changed code…
ultralytics-platform
This skill should be used when user asks to "upload my model to Ultralytics Platform", "push this run to the platform", "upload a dataset to platform", "download a dataset from platform", "search platform datasets", "start cloud training", "train on platform GPUs", "export a model on platform", "deploy a model…
mongodb-connection
Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling connect()), configuring connection pools, troubleshooting connection errors…