aiskillstore/marketplace / skills/359392475-blue-sky/too-long-to-read
too-long-to-read
Verified仅在用户明确说“太长不看”“先讲结论”“把这个讲得好读一点”“压成一屏重点”,或表达同等的快速阅读意图时使用。把用户提供的文本、文章链接、普通网页、金山文档、飞书文档或由宿主 Agent(智能体)解析出的文件内容,转成结论优先的短消息,同时保留会改变判断的条件、风险、数字、行动项和原文歧义。不要只因为内容很长、附有链接或文件就触发;普通总结、翻译、改写请求也不自动触发本 Skill。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.0 KB |
| skill-report.json | config | 12.3 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-11-08T14:46:30.759Z",
"slug": "359392475-blue-sky-too-long-to-read",
"source_url": "https://github.com/359392475-blue-sky/too-long-to-read/tree/d47abe585c45b87736763888ea7ca26da2c37a59/skill/too-long-to-read",
"source_ref": "d47abe585c45b87736763888ea7ca26da2c37a59",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "146a4e4077d2fb19c38774f363acda33c455ffe0d78036e46025a438276619b9",
"tree_hash": "83a2523c2edc0b0fe7f51d5552c376920dabe47b7f7e94bf2f8eaf95d90d3e5e",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
},
"upstream_version_raw": null,
"upstream_version_normalized": null,
"upstream_version_source": "none",
"upstream_version_status": "missing",
"upstream_commit_sha": "d47abe585c45b87736763888ea7ca26da2c37a59"
},
"skill": {
"name": "too-long-to-read",
"description": "仅在用户明确说“太长不看”“先讲结论”“把这个讲得好读一点”“压成一屏重点”,或表达同等的快速阅读意图时使用。把用户提供的文本、文章链接、普通网页、金山文档、飞书文档或由宿主 Agent(智能体)解析出的文件内容,转成结论优先的短消息,同时保留会改变判断的条件、风险、数字、行动项和原文歧义。不要只因为内容很长、附有链接或文件就触发;普通总结、翻译、改写请求也不自动触发本 Skill。",
"summary": "Turn readable source material into short, conclusion-first messages while preserving conditions, risks, numbers, uncertainty, and next steps.",
"icon": "📦",
"author": "359392475-blue-sky",
"category": "productivity",
"tags": [
"summarization",
"quick-reading",
"document-reading",
"action-items",
"source-fidelity"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
]
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "Both static findings are false positives: Markdown backticks enclose punctuation examples, and the entropy alert concerns readable Chinese prose. No evidence found of executable payloads, obfuscation, exfiltration, or prompt injection in SKILL.md. The instructions restrict link access, preserve existing permissions, and treat embedded source instructions as untrusted content.",
"remediation": [],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 70,
"line_end": 70
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 70,
"line_end": 70,
"snippet": "中文保持聊天式短句,默认不机械添加句末句号 `。`;需要语气时保留 `?`、`!`、`......`,句中的必要标点照常使用。不要用全局删点号的方式处理,以免破坏小数、版本号、网址、代码或专有名词"
},
{
"id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-8-09-bits-possible-b",
"category": "obfuscation",
"severity": "high",
"pattern": "[HEURISTIC] High file entropy (8.09 bits) - possible binary/encrypted content",
"file": "SKILL.md",
"line_start": 1,
"line_end": 1,
"snippet": "File: SKILL.md"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "SKILL.md:70 uses Markdown backticks to quote punctuation while discussing Chinese sentence formatting. No shell commands, Ruby code, or execution instructions appear there."
},
{
"id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-8-09-bits-possible-b",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "All 95 lines are readable Chinese Markdown, including YAML front matter and explicit summarization rules. No evidence found of encrypted content, encoded payloads, or binary data; the entropy heuristic does not establish obfuscation."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 95,
"audit_model": "codex",
"audited_at": "2026-11-08T14:46:30.759Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Read Long Materials as Short, Clear Conclusions",
"value_statement": "Long documents can hide the conditions, risks, and actions that matter. This skill turns readable material into conclusion-first messages while preserving facts that affect decisions.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"conclusion-first summaries",
"document summarization",
"quick reading",
"action item extraction",
"source fidelity",
"short-form summaries"
],
"actual_capabilities": [
"Reorganizes readable material into short, conclusion-first paragraphs when the user explicitly requests quick reading.",
"Preserves critical conditions, risks, numbers, responsibilities, deadlines, dependencies, and uncertainty.",
"Processes pasted text and user-provided links through the host agent's existing reading capabilities and permissions.",
"Handles extracted file content after the host agent reads documents, screenshots, or other supported formats.",
"Answers follow-up requests for reasons, source evidence, action items, shorter explanations, or further detail.",
"Follows the user's current language and discloses incomplete reading instead of inventing missing information."
],
"limitations": [
"Provides instructions, not independent browsing tools, document connectors, or file parsers.",
"Cannot bypass login requirements, permission restrictions, paywalls, or unreadable source content.",
"Does not search for alternative sources or follow additional links within a supplied page.",
"Does not replace original contracts, code, formulas, or tables, and does not maintain reading history across conversations."
],
"use_cases": [
{
"title": "Review Project Updates",
"description": "Read lengthy project notes as short messages that preserve decisions, blockers, owners, deadlines, and dependencies.",
"target_user": "Project managers"
},
{
"title": "Understand Dense Articles",
"description": "Read the main argument first while retaining essential evidence, competing interpretations, and unresolved uncertainty.",
"target_user": "Researchers"
},
{
"title": "Review Policy Conditions",
"description": "Identify important obligations, exceptions, limits, and risks without treating a compressed explanation as a replacement for the source.",
"target_user": "Operations staff"
}
],
"prompt_templates": [
{
"title": "Get the Conclusion First",
"prompt": "Give me the conclusion first in short messages. Preserve important conditions, risks, and numbers from this text: [paste text].",
"scenario": "Beginner: shorten one readable passage."
},
{
"title": "Read One Linked Article",
"prompt": "Give me a quick, conclusion-first reading of [article URL]. Use only that page and state any reading limits.",
"scenario": "Intermediate: read a user-provided page through available host tools."
},
{
"title": "Extract Decisions and Actions",
"prompt": "Compress these project notes into short, conclusion-first messages. Preserve decisions, risks, owners, deadlines, dependencies, and blockers. Mark missing owners or dates: [paste notes].",
"scenario": "Intermediate: identify actionable information in work materials."
},
{
"title": "Preserve Conflicting Evidence",
"prompt": "Give me a conclusion-first reading of this material. Preserve conflicting evidence, exceptions, and uncertainty. Then provide source evidence when I ask: [paste material].",
"scenario": "Advanced: examine complex material and verify conclusions through follow-up questions."
}
],
"output_examples": [
{
"input": "Conclusion first: Launch is planned for Friday. Security approval is pending. Maya must submit the checklist Thursday. Approval delays move launch to Monday.",
"output": "Launch is planned for Friday, but only if security approval arrives.\n\nMaya must submit the checklist Thursday. If approval is delayed, launch moves to Monday."
},
{
"input": "Quick reading: A six-week pilot with 20 volunteers reported 12% faster task completion. There was no control group. Accuracy stayed unchanged.",
"output": "The pilot reported 12% faster task completion, with no change in accuracy.\n\nOnly 20 volunteers participated for six weeks. Without a control group, the result does not establish what caused the improvement."
},
{
"input": "Conclusion first: Staff may work remotely two days weekly after manager approval. New hires must complete 30 days onsite. Customer support coverage takes priority.",
"output": "Staff may work remotely two days each week, but manager approval is required.\n\nNew hires must first complete 30 days onsite. Customer support coverage can limit remote arrangements."
}
],
"best_practices": [
"Explicitly request quick reading or conclusion-first messages, and provide the source material.",
"Provide readable text or authorized access, and resolve missing content before relying on a full conclusion.",
"Ask for source evidence or targeted expansion when a condition, number, or uncertainty affects your decision."
],
"anti_patterns": [
"Assuming every long document or ordinary summary request automatically activates this skill.",
"Requesting confident conclusions from inaccessible, truncated, or partially parsed material.",
"Treating compressed explanations as exact replacements for original contracts, formulas, tables, or code."
],
"faq": [
{
"question": "When does this skill activate?",
"answer": "It activates when you explicitly request quick reading, conclusions first, easier reading, or a screen of key points."
},
{
"question": "Which materials can it process?",
"answer": "It handles pasted text, supplied webpages, and authorized Jinshan or Feishu documents. Other files require the host agent to extract readable content first."
},
{
"question": "What happens if a link cannot be read?",
"answer": "It states what was readable and what is missing, then requests pasted text or a readable export. It does not bypass access restrictions."
},
{
"question": "How short is the default output?",
"answer": "It targets up to ten short paragraphs, usually 400 to 700 Chinese characters. Critical facts can justify longer output."
},
{
"question": "Can I ask for evidence or action items afterward?",
"answer": "Yes. Follow-up requests can retrieve readable source evidence, explain a specific point, extract actions, or shorten the response without resubmitting visible material."
},
{
"question": "Does it save my reading history?",
"answer": "The skill instructs the agent to use only current chat context and not maintain reading history. Host platform storage policies remain separate."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 95
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |