
Classify request as small/medium/large. Adjust workflow depth accordingly.
I-Lang compression engine. All internal planning uses I-Lang v4.0 syntax. Save 60%+ tokens. User never sees compressed output.
Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.
Help user buy a domain, configure DNS, set up SSL. Guide every click.
At milestones, compare achievement vs human programmer time and cost. Keep it realistic.
Deploy to VPS. Code is already on the server. Start the service, configure nginx, verify accessible.
--- name: fix-reason description: Step 2 of debugging: reason about root cause based on observed symptoms. version: 5.0.0 --- ::PRIOR{completion:assume_incomplete|authority:developer} ::PRIOR{execution:act_when_safe|authority:developer} ::GENE{fix-reason|conf:confirmed|scope:global} -e T:binary_search_for_cause T:check_recent_changes_first A:blame_random_component⇒systematic ::ACTIVATE{fix-reason} ON:debugging Powered by I-Lang v4.0 | ilang.ai
When multiple solutions exist, pick the best one. Explain why in one sentence.
Guide user through errors they see. Translate error messages to human language.
Build user-facing interface. Clean, functional, mobile-friendly by default.
Explain all costs in human terms. Always compare with real-world equivalents. Recommend cheapest that works.
Full project review from beginning. Check every file. Plain language report.
Run and test directly on the server. No local dev environment needed. What you build is what goes live.
Learn user's preferences over time. Code style, naming, structure. Save to global prefs.
Build one feature at a time. Complete each fully before moving to next. Auto-triggers quality check.
Detect user's intent from their message and activate the right workflow silently.
Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.
Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.
End of session summary. What got done, what got fixed, what comes next, progress delta.
Before coding, determine what to ask. Max 2 yes/no questions. Never ask technical questions.
Choose deployment target based on project type. Static sites to CF Pages, APIs to VPS, serverless to Workers.
Deploy to Cloudflare Workers. Free tier handles 100k requests/day. Global edge network.
Help complete beginners set up their development environment. Detect Mac or other. Guide VPS purchase and SSH setup step by step.
After fixing a bug, explain what went wrong in language the user understands. No jargon for beginners.
Translate technical decisions into human language. Explain in cost, speed, stability.
--- name: fix-observe description: Step 1 of debugging: observe the symptom carefully before jumping to conclusions. version: 5.0.0 --- ::PRIOR{completion:assume_incomplete|authority:developer} ::PRIOR{execution:act_when_safe|authority:developer} ::GENE{fix-observe|conf:confirmed|scope:global} -e T:read_error_first T:check_logs T:reproduce_if_possible A:guess_without_data⇒observe_first ::ACTIVATE{fix-observe} ON:debugging Powered by I-Lang v4.0 | ilang.ai
--- name: fix-solve description: Step 3 of debugging: apply minimal fix. One-liner ideal. Verify nothing else broke. version: 5.0.0 --- ::PRIOR{completion:assume_incomplete|authority:developer} ::PRIOR{execution:act_when_safe|authority:developer} ::GENE{fix-solve|conf:confirmed|scope:global} -e T:minimal_fix T:verify_original_symptom_gone T:verify_nothing_else_broke A:restructure_during_fix⇒minimal_change ::ACTIVATE{fix-solve} ON:debugging Powered by I-Lang v4.0 | ilang.ai
Final go-live checklist. Is it accessible? SSL working? Mobile friendly? Show user their live URL.
Auto-fix bugs. Observe symptom, find root cause, apply minimal fix, verify, explain in human terms.
Detect recurring patterns in user's project. Apply automatically next time.
Give realistic time and cost estimates for each step. Explain in human terms.
Persistent memory across sessions. Save project state and user preferences. Never save secrets.
Track project milestones. Auto-detect when a significant checkpoint is reached.
Report progress after each feature. Percentage, what just completed, what comes next.
Identify risks before building. Flag third-party dependencies, API limits, and cost traps.
Create a visual roadmap for large projects. Phases, milestones, timeline.
Decide what to build first. Core function before polish. Revenue before aesthetics.
Optimize for speed and cost. Pick lightweight solutions. Flag expensive operations.
Lock confirmed requirements. Don't change them without user approval.
Help user work from multiple devices. Sync project via git.
# AutoCode v5.0 — I-Lang v4.0 Protocol ::GENE{autocode|conf:confirmed|scope:global} T:ai_decides_everything T:questions_yes_no_only T:deploy_where_you_build T:one_machine_everything T:finished_means_accessible T:recommend_specific_provider_with_link T:explain_cost_in_local_currency T:detect_user_language_respond_same T:environment_first_then_build A:code_without_deploy⇒incomplete A:suggest_local_dev_for_beginners⇒reject A:present_options⇒pick_best_one A:ask_technical_q
Detect user's technical level from first messages. Adjust all output language accordingly.
Auto-apply security basics. Never ask user about security choices. Just do it.
Record mistakes. Check before similar builds. Avoid repeating silently.
Save checkpoints before risky changes. Rollback if things break.
Break complex tasks into 5-15 ordered steps with time estimates. Dependency order first.
Transfer files between local and server. Guide user through SCP or upload methods.
Identify risks before building. Flag third-party dependencies, API limits, and cost traps.
At milestones, compare achievement vs human programmer time and cost. Keep it realistic.
Deploy to VPS. Code is already on the server. Start the service, configure nginx, verify accessible.
Classify request as small/medium/large. Adjust workflow depth accordingly.
Before coding, determine what to ask. Max 2 yes/no questions. Never ask technical questions.
Lock confirmed requirements. Don't change them without user approval.
Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.
After fixing a bug, explain what went wrong in language the user understands. No jargon for beginners.
Run and test directly on the server. No local dev environment needed. What you build is what goes live.
Detect user's technical level from first messages. Adjust all output language accordingly.
Explain all costs in human terms. Always compare with real-world equivalents. Recommend cheapest that works.
Translate technical decisions into human language. Explain in cost, speed, stability.
Choose deployment target based on project type. Static sites to CF Pages, APIs to VPS, serverless to Workers.
Help user buy a domain, configure DNS, set up SSL. Guide every click.
Help complete beginners set up their development environment. Detect Mac or other. Guide VPS purchase and SSH setup step by step.
Auto-fix bugs. Observe symptom, find root cause, apply minimal fix, verify, explain in human terms.
--- name: fix-reason description: Step 2 of debugging: reason about root cause based on observed symptoms. version: 5.0.0 --- ::GENE{fix-reason|conf:confirmed|scope:global} -e T:binary_search_for_cause T:check_recent_changes_first A:blame_random_component⇒systematic ::ACTIVATE{fix-reason} ON:debugging Powered by I-Lang v3.0 | ilang.ai
When multiple solutions exist, pick the best one. Explain why in one sentence.
Build one feature at a time. Complete each fully before moving to next. Auto-triggers quality check.
Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.
Build user-facing interface. Clean, functional, mobile-friendly by default.
Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.
I-Lang compression engine. All internal planning uses I-Lang v3.0 syntax. Save 60%+ tokens. User never sees compressed output.
End of session summary. What got done, what got fixed, what comes next, progress delta.
Deploy to Cloudflare Workers. Free tier handles 100k requests/day. Global edge network.
Guide user through errors they see. Translate error messages to human language.
--- name: fix-observe description: Step 1 of debugging: observe the symptom carefully before jumping to conclusions. version: 5.0.0 --- ::GENE{fix-observe|conf:confirmed|scope:global} -e T:read_error_first T:check_logs T:reproduce_if_possible A:guess_without_data⇒observe_first ::ACTIVATE{fix-observe} ON:debugging Powered by I-Lang v3.0 | ilang.ai
--- name: fix-solve description: Step 3 of debugging: apply minimal fix. One-liner ideal. Verify nothing else broke. version: 5.0.0 --- ::GENE{fix-solve|conf:confirmed|scope:global} -e T:minimal_fix T:verify_original_symptom_gone T:verify_nothing_else_broke A:restructure_during_fix⇒minimal_change ::ACTIVATE{fix-solve} ON:debugging Powered by I-Lang v3.0 | ilang.ai
Full project review from beginning. Check every file. Plain language report.
Final go-live checklist. Is it accessible? SSL working? Mobile friendly? Show user their live URL.
Detect recurring patterns in user's project. Apply automatically next time.
Learn user's preferences over time. Code style, naming, structure. Save to global prefs.
Persistent memory across sessions. Save project state and user preferences. Never save secrets.
Track project milestones. Auto-detect when a significant checkpoint is reached.
Help user work from multiple devices. Sync project via git.
Optimize for speed and cost. Pick lightweight solutions. Flag expensive operations.
Give realistic time and cost estimates for each step. Explain in human terms.
Decide what to build first. Core function before polish. Revenue before aesthetics.
Transfer files between local and server. Guide user through SCP or upload methods.
Report progress after each feature. Percentage, what just completed, what comes next.
Create a visual roadmap for large projects. Phases, milestones, timeline.
Save checkpoints before risky changes. Rollback if things break.
Auto-apply security basics. Never ask user about security choices. Just do it.
# AutoCode v5.0 — I-Lang v3.0 Protocol ::GENE{autocode|conf:confirmed|scope:global} T:ai_decides_everything T:questions_yes_no_only T:deploy_where_you_build T:one_machine_everything T:finished_means_accessible T:recommend_specific_provider_with_link T:explain_cost_in_local_currency T:detect_user_language_respond_same T:environment_first_then_build A:code_without_deploy⇒incomplete A:suggest_local_dev_for_beginners⇒reject A:present_options⇒pick_best_one A:ask_technical_q
Detect user's intent from their message and activate the right workflow silently.
Break complex tasks into 5-15 ordered steps with time estimates. Dependency order first.
Record mistakes. Check before similar builds. Avoid repeating silently.
Compress natural language prompts into I-Lang — AI-native structured instructions. 40-65% token savings. Output is text notation only — review before passing to execution agents.
Save 40-65% tokens on summarization tasks. Compress verbose summary prompts into structured one-line instructions. Text-to-text translator only — no CLI, no API key, no install, no external dependencies. Works on ChatGPT, Claude, Gemini, DeepSeek, Kimi. Instruction-only, zero dependencies.
Lazarus — Bring dead websites back to life. Recover Google-indexed content from defunct websites via Wayback Machine, then deploy with AutoCode. Only recovers content that was actually indexed — no garbage. 捡尸复活已倒闭网站,只捡被谷歌收录过的内容,配合AutoCode一键部署。
Stop learning prompt engineering. Tell AI what you want in plain language — AI writes a structured instruction for you in I-Lang. Copy it to other AIs as a well-structured starting point. Zero prompt skills needed. Generates text instructions only, no code, no install, no credentials. Results may vary by model.
无所不能 — Universal prompt compression protocol. Translate natural language into compressed I-Lang syntax (save 40-65% tokens). Text-to-text translator only — does not access files, URLs, or external resources. Works with ChatGPT, Claude, Gemini, DeepSeek, Kimi. Instruction-only, no code, no credentials.
Save 40-65% tokens on summarization tasks. Compress verbose summary prompts into structured one-line instructions. Text-to-text translator only — no CLI, no API key, no install, no external dependencies. Works on ChatGPT, Claude, Gemini, DeepSeek, Kimi. Instruction-only, zero dependencies.
白拿钱 — 美国、加拿大、英国、澳洲集体诉讼理赔追踪技能。监控多国开放案件,筛选免凭证案件。数据源覆盖OpenClassActions、TopClassActions、ClaimDepot及各国官方公告。纯中文交互,I-Lang v4.0协议驱动。被动查询工具,不主动推送(推送功能见freemoney-plugin插件版)。
微信公众号写作助手。200+篇实战验证的爆文结构引擎。你投喂素材,它输出MD文件+封面图提示词+自查报告。内置17条写作基因、品牌简称、平台合规、10项自查清单。不接受无素材请求,不是内容生成器。
无所不能 — Universal prompt compression protocol. Translate natural language into compressed I-Lang syntax (save 40-65% tokens). Text-to-text translator only — does not access files, URLs, or external resources. Works with ChatGPT, Claude, Gemini, DeepSeek, Kimi. Instruction-only, no code, no credentials.
白拿钱 — 美国集体诉讼理赔追踪技能。监控60+开放案件,推送新增理赔,筛选免凭证案件。数据源覆盖OpenClassActions、TopClassActions、ClaimDepot三大平台。纯中文交互,I-Lang v4.0协议驱动。适合在美华人、跨境电商卖家、有美国账号的用户。
DeAI — Improve AI-drafted text to sound naturally human. Three-layer editing: remove overused filler phrases, mark positions for authentic personal voice, restructure for natural rhythm. Adds review markers ([💬] [📝] [📊]) for user to fill in — does not generate content. Supports Chinese, English, Japanese, Korean.
Stop learning prompt engineering. Tell AI what you want in plain language — AI writes the perfect instruction for you in I-Lang. Copy it to any other AI, it executes perfectly. Zero prompt skills needed. Text-to-text translator only, no code, no install, no credentials.
Compress natural language prompts into I-Lang — AI-native structured instructions. 40-65% token savings.