Agent skill

Crossframe Review

by sickn33 in sickn33/agentic-awesome-skills

A skill your agent uses when explicit CrossFrame output needs review for reasoning fidelity, evidence boundaries, source anchors, concept drift, article collapse, or repair steps.

MITAuto-check passed

Install Crossframe Review

skills CLI
$ npx skills add sickn33/agentic-awesome-skills --skill crossframe-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sickn33/agentic-awesome-skills crossframe-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/crossframe-review .claude/skills/crossframe-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
crossframe-review
GitHub stars
47k
Used in
1 other repo
Token cost
~1.3k tokens
SKILL.md length
335 words
Files
13 (incl. references)
Skills in repo
1,497
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when explicit CrossFrame output needs review for reasoning fidelity, evidence boundaries, source anchors, concept drift, article collapse, or repair steps.

  • Works in 10 steps: 读取 ../crossframe/SKILL.md。 → 读取… → 读取… → …
  • Explicit CrossFrame output needs review for reasoning fidelity
  • SKILL.md covers When to Use This Skill, Packaged Source Note, Limitations and 轻入口规则, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Crossframe Review is an agent skill from sickn33/agentic-awesome-skills. Use when explicit CrossFrame output needs review for reasoning fidelity, evidence boundaries, source anchors, concept drift, article collapse, or repair steps.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including reference files (for example `agents/openai.yaml`, `evals/crossframe-review-smoke-tests.md` and `examples/boundary-review-case.md`).

The repository describes itself as: AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes… The licence is MIT.

When your agent uses it

  • Explicit CrossFrame output needs review for reasoning fidelity
  • Evidence boundaries
  • Article collapse

Example prompts

  • “/crossframe-review”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. 读取 ../crossframe/SKILL.md。
  2. 读取 ../crossframe/references/read-routing-map.md。
  3. 读取 ../crossframe/references/runtime-read-policy.md 与 ../crossframe/references/continuity-closure-map.md,判断本应触发哪些 v5.0…
  4. 若评审对象是深度、审计、高责任、公共制度、亲密关系、长期演化或文章类输出,读取或检查 ../crossframe/templates/read-state-capsule.md 规定的 v5-read-state-capsule 是否存在并被下游复用。
  5. 按需读取 ../crossframe/worksheets/source-continuity-check.md 与 ../crossframe/worksheets/source-anchor-integrity-check.md,检查闭包是否完整、中心命题和行动边界是否能回…
  6. 若评审对象是文章、长文、评论、思想文章、报刊答复或“现代编辑同志口吻”输出,按需读取 ../crossframe-essay/SKILL.md。
  7. 读取本目录的 protocols/review-protocol.md 和 templates/review-report.md。
  8. 若涉及文章底稿、引用、检索材料或声口,追加读取 protocols/article-review-protocol.md。
  9. 若涉及公共事实、真实机构、平台、政策、人物、公司、最新事实、AI/过程性产物、批判文章或来源使用,读取 ../crossframe/references/source-ledger-workflow.md,检查来源台账字段是否完整。
  10. 按需读取本目录 references/ 中的评分表、失败类型表和证据边界清单。

What it can do on your machine

Read from SKILL.md and the folder at commit b84d35a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Crossframe Review loads about 1.3k tokens when it runs, and up to ~7.6k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 335 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sickn33/agentic-awesome-skills at commit b84d35a, republished under its MIT licence (© sickn33). 335 words, ~1,287 tokens.

Download SKILL.mdSave it as .claude/skills/crossframe-review/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
crossframe-review
description
Use when explicit CrossFrame output needs review for reasoning fidelity, evidence boundaries, source anchors, concept drift, article collapse, or repair steps.
category
workflow
risk
safe
source
community
source_repo
xi-kari/crossframe-skill
source_type
community
date_added
2026-06-16
author
xi-kari
license
MIT
license_source
https://github.com/xi-kari/crossframe-skill/blob/main/LICENSE
tools
Agent Skills, Codex, Claude

CrossFrame Review

When to Use This Skill

  • Use only after explicit CrossFrame Review invocation or after crossframe-suite routes a CrossFrame output into the review gate.
  • Use to check reasoning fidelity, evidence boundaries, source anchors, concept drift, article-body collapse, and repair steps.
  • Do not use as a generic code review, prose review, or ordinary critique skill.

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-suite routing; 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.

如果评审对象来自多个 CrossFrame skill 的连续工作流,先读取 ../crossframe-suite/SKILL.md 还原应有调度链,再判断是否有漏触发、误触发或跳过质量闸。

本 skill 只做评审与修复建议,不替代 crossframe 生成诊断,也不替代 crossframe-essay 写文章。中文为权威语义;英文只作 skill id、文件名和接口说明。

轻入口规则

每次触发后,先读取 canonical skill,而不是复制它们的正文:

  1. 读取 ../crossframe/SKILL.md。
  2. 读取 ../crossframe/references/read-routing-map.md。
  3. 读取 ../crossframe/references/runtime-read-policy.md 与 ../crossframe/references/continuity-closure-map.md,判断本应触发哪些 v5.0 连续联读包;只有需要包说明、源锚点或闭包细节时,再定向读取 ../crossframe/references/continuity-bundles.md 或具体包文件。
  4. 若评审对象是深度、审计、高责任、公共制度、亲密关系、长期演化或文章类输出,读取或检查 ../crossframe/templates/read-state-capsule.md 规定的 v5-read-state-capsule 是否存在并被下游复用。
  5. 按需读取 ../crossframe/worksheets/source-continuity-check.md 与 ../crossframe/worksheets/source-anchor-integrity-check.md,检查闭包是否完整、中心命题和行动边界是否能回指胶囊源锚点。
  6. 若评审对象是文章、长文、评论、思想文章、报刊答复或“现代编辑同志口吻”输出,按需读取 ../crossframe-essay/SKILL.md。
  7. 读取本目录的 protocols/review-protocol.md 和 templates/review-report.md。
  8. 若涉及文章底稿、引用、检索材料或声口,追加读取 protocols/article-review-protocol.md。
  9. 若涉及公共事实、真实机构、平台、政策、人物、公司、最新事实、AI/过程性产物、批判文章或来源使用,读取 ../crossframe/references/source-ledger-workflow.md,检查来源台账字段是否完整。
  10. 按需读取本目录 references/ 中的评分表、失败类型表和证据边界清单。

不要把 CrossFrame 主 skill、文章 skill、eval、examples 或完整案例复制到本 skill 输出中。评审时只引用必要规则名、触发点和证据位置。若 v5-read-state-capsule 已存在,下游默认复用胶囊,不得为了评审而重复整块读取源索引。

评审目标

判断一个输出是否真的完成了 CrossFrame 的最低推理链:

  • 明确诊断或写作对象。
  • 区分事实、解释、证据缺口和判断档位。
  • 经过对象闸、证据闸、尺度闸、责任闸、观测闸。
  • 至少形成两个机制候选,或说明为什么只能有一个。
  • 对承担判断作用的高风险概念做保真检查,而不是把术语当结论。
  • 对属于 v5.0 连续板块的高风险概念做源结构连续性检查,而不是只读单张概念卡。
  • 对中心命题、机制候选、高风险概念、行动边界、文章类型转译和写作技法做源锚点完整性检查;不能回指胶囊的内容不得写成 CrossFrame v5 原义。
  • 给出可撤回条件、下一步观察或低条件行动边界。
  • 文章类输出必须先有结构洞察底稿,再写正文。

必抓失败

以下问题一旦出现,要在评审中明确定位;严重时直接判为不合格:

  • 概念堆砌:只堆“承接、回流、尺度、反俘获”等词,没有落回事实和行为。
  • 伪推理:先给结论,再用术语装饰;没有机制候选、反向条件或证据闸。
  • 事实边界缺失:把传闻、AI 报告、自评、搜索摘要或解释当事实。
  • 跳过底稿:文章类输出直接成文,没有结构洞察底稿或等价内部骨架。
  • 人格审判:把结构诊断变成“这个人坏、懒、无能、病态”等定性。
  • 伪造引用:编造原文、页码、出处、作者观点;不确定原句却写成直接引用。
  • 查源接管命题:检索材料决定文章立场,CrossFrame 只变成资料拼贴外壳。
  • 强判断越级:处分、名誉、权利、资源、公共记忆类判断没有命题验证和申诉/反证入口。
  • 尺度洗白:用宏观叙事取消低尺度痛苦、责任链或具体失职。
  • AI 合规剧场:把 AI 生成材料、漂亮报告或自评文本当作独立强证据。
  • 连续性保真失败:本应触发 continuity-bundles.md 的联读包,却只读单个概念卡、单个 protocol 或单个摘录就下判断。
  • 胶囊缺失:应由 crossframe 生成 v5-read-state-capsule 的任务没有胶囊,导致 essay/review 各自重读源索引或发明路由。
  • 源锚点失败:中心命题、机制候选、高风险概念、行动边界或文章转译无法回指胶囊源锚点,却写成 CrossFrame v5 原义。
  • 下游重复整块读源:已有胶囊时,essay 或 review 又整块读取 v5 源索引、完整连读包或材料选择图,造成源边界漂移。
  • 选择器压缩失败:模式/角色或文章类型选择器没有完整渲染选项、推荐项和等待用户回复。
  • 技法越界失败:写作技法新增事实、强判断、点睛句或隐喻证明,越过底稿和胶囊源边界。
  • 来源用途越界失败:把热度、机构声明、PR 文案、AI 生成材料、自评文本或二手转述写成已核验事实。
  • 来源台账缺失:公共、批判、文章或高责任输出涉及真实对象,却没有来源、时间、来源类型、支持命题、不能证明什么、证据档位、使用位置、降档理由和仍需补证处。
  • v5 现实保护失败:涉及 AI 过程性产物、弱信号、不透明、无制度基础设施、无法退出、恶意合规、隐喻漂移、工具化或开放断言退场,却没有读取对应 v5 概念卡和联读包。

输出协议

默认使用 templates/review-report.md。最终评审必须包含:

  • 评审对象
  • 事实边界
  • 触发规则
  • 评分/等级
  • 关键问题
  • 证据定位
  • 修复建议
  • 是否合格

若用户只要一句话结论,也要保留“是否合格 + 主要失败点 + 下一步修复”的最小结构。

Suite 调度可见性

当本 skill 经 crossframe-suite 作为默认质量闸调用,而用户没有明确要求“只要评审/完整评审报告/不要文章”时,评审不接管最终输出:

  • 评审对象是已经形成的 结构洞察底稿 与 文章正文。
  • A/B 或小修可过时,把问题反馈给上游修正,最终可见交付仍是 # 结构洞察底稿 + # 文章正文,最多追加一行短质量闸摘要。
  • C/D/F 或硬失败时,阻断发布并要求回到对应上游补底稿、补证据边界或重写正文;若用户没有要求只看评审,不得只输出评审报告来替代修复后的文章。
  • templates/review-report.md 只在用户显式要求完整评审报告、只评审已有输出,或硬失败需要说明阻断原因时作为主输出。

合格判定

评分只是辅助,硬失败优先:

  • A:90-100,合格。
  • B:75-89,条件合格,小修后可用。
  • C:60-74,不合格,需要大修。
  • D:40-59,不合格,需要重做主要推理。
  • F:0-39 或触发硬失败,高风险失败。

触发人格审判、伪造引用、跳过文章底稿、强判断越级、证据边界完全缺失、连续性保真失败时,即使文字流畅,也不能判为合格。

修复原则

评审输出优先给可执行修复,不默认重写全文。除非用户要求“直接改写”,否则只给:

  • 应补的事实边界。
  • 应读取或声明的路由。
  • 应新增的机制候选。
  • 应降档的判断。
  • 应删除或改写的人格审判、伪引用和术语堆砌句。
  • 文章应补的结构洞察底稿项目。

© sickn33, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (references) in skills/crossframe-review of sickn33/agentic-awesome-skills.

  • SKILL.md
  • agents/openai.yaml
  • evals/crossframe-review-smoke-tests.md
  • examples/boundary-review-case.md
  • examples/failure-review-case.md
  • examples/normal-review-case.md
  • protocols/article-review-protocol.md
  • protocols/review-protocol.md
  • references/case-law.md
  • references/evidence-boundary-checklist.md
  • references/failure-taxonomy.md
  • references/review-rubric.md
  • templates/review-report.md

Open the folder on GitHubat commit b84d35a

Used in 1 other repository

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in sickn33/agentic-awesome-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Crossframe Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Crossframe Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Crossframe Review this skillsickn33/agentic-awesome-skills47k1 repos~1.3kAutomated safety check: PassMIT
Deepseek Reasonruvnet/ruflo74k—~626Automated safety check: NotesMIT
Fidel API AutomationComposioHQ/awesome-claude-skills77k3 repos~738Automated safety check: PassNone
Nowait Reasoning Optimizerdavila7/claude-code-templates33k2 repos~1.2kAutomated safety check: PassMIT
Citation Fidelitybrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~638Automated safety check: PassCustom licence
Recall Reasoningparcadei/Continuous-Claude-v33.9k1 repos~758Automated safety check: PassMIT

Similar skills

  • Deepseek Reason

    ruvnet/ruflo

    Reasoning-mode completion against DeepSeek's deepseek-reasoner model (R1) via /v1/chat/completions.

    74k GitHub stars~626 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Fidel API Automation

    ComposioHQ/awesome-claude-skills

    Automate Fidel API tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~738 tokens
    Productivity & AutomationAuto-check passed
  • Nowait Reasoning Optimizer

    davila7/claude-code-templates

    Implements the NOWAIT technique for efficient reasoning in R1-style LLMs.

    33k GitHub starsUsed in 2 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed
  • Citation Fidelity

    brycewang-stanford/Auto-Empirical-Research-Skills

    学术引用核查Skill。要求每条引用必须定位到PDF原页,区分直接引用/间接引用,找不到原文则标注"待核"。触发词:引用核查/检查引用/citation check/核实文献/引用 fidelity

    4.6k GitHub stars~638 tokensUpdated 5 days ago
    Research & ScienceAuto-check passed
  • Recall Reasoning

    parcadei/Continuous-Claude-v3

    Search past reasoning for relevant decisions and approaches. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~758 tokens
    DevelopmentAuto-check passed
  • Nv Reason Cxr

    NVIDIA/skills

    Official

    Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests.

    3.6k GitHub stars~3.9k tokensUpdated today
    Testing & QAAuto-check: notes

More from sickn33/agentic-awesome-skills

All 1,497 skills in this repo
  • Liuguang Banlan UI

    sickn33/agentic-awesome-skills

    Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • User Thoughts Memory

    sickn33/agentic-awesome-skills

    Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • Find Complementary Founders

    sickn33/agentic-awesome-skills

    Guides an agent through assessing its own owner for cofounder fit, publishing an approved profile, and ranking complementary profiles other agents published for their owners.

    47k GitHub starsUsed in 1 repo~4.8k tokens
    Auto-check passed
  • Whatsapp Cloud API

    sickn33/agentic-awesome-skills

    Integracao com WhatsApp Business Cloud API (Meta). An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~4.5k tokens
    Auto-check passed
  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

Questions about Crossframe Review

What does Crossframe Review do?

A skill your agent uses when explicit CrossFrame output needs review for reasoning fidelity, evidence boundaries, source anchors, concept drift, article collapse, or repair steps. Crossframe Review is an agent skill from sickn33/agentic-awesome-skills. Use when explicit CrossFrame output needs review for reasoning fidelity, evidence boundaries, source anchors, concept drift, article collapse, or repair steps.

When should I use Crossframe Review?

Crossframe Review fits situations like: explicit CrossFrame output needs review for reasoning fidelity; evidence boundaries; article collapse.

How do I install Crossframe Review in Claude Code?

Run `npx skills add sickn33/agentic-awesome-skills --skill crossframe-review -a claude-code`. Or copy the skill folder (skills/crossframe-review in sickn33/agentic-awesome-skills) into .claude/skills/crossframe-review in your project. Claude Code loads it when a task matches its description.

How do I install Crossframe Review in Codex?

Run `npx skills add sickn33/agentic-awesome-skills --skill crossframe-review -a codex`. Or copy the skill folder (skills/crossframe-review in sickn33/agentic-awesome-skills) into .agents/skills/crossframe-review in your project. Codex loads it when a task matches its description.

Can I use Crossframe Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sickn33/agentic-awesome-skills --skill crossframe-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/crossframe-review, .gemini/skills/crossframe-review, .github/skills/crossframe-review and .opencode/skills/crossframe-review in your project.

What does Crossframe Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Crossframe Review is instructions for the agent only.

Does Crossframe Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Crossframe Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Crossframe Review use?

Crossframe Review is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Crossframe Review use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.3k tokens, read only when the agent opens those files.

What are the alternatives to Crossframe Review?

Skills that share tags, products or a category with Crossframe Review: Deepseek Reason (ruvnet/ruflo, 74k stars), Fidel API Automation (ComposioHQ/awesome-claude-skills, 77k stars), Nowait Reasoning Optimizer (davila7/claude-code-templates, 33k stars) and Citation Fidelity (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Crossframe Review?

sickn33 (a GitHub user) maintains it in sickn33/agentic-awesome-skills, which has 47,405 GitHub stars. The repository holds 1,497 skills in this directory. The repository was last updated on October 9, 2026.

Source: sickn33/agentic-awesome-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.