ilang-ai
110 verified skills7,503 total stars
memory
Persistent memory across sessions. Save project state and user preferences. Never save secrets.
tools83
go-live
Final go-live checklist. Is it accessible? SSL working? Mobile friendly? Show user their live URL.
development83
skills/fix-observe
--- 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 v5.0 | ilang.ai
development83
skills/fix-reason
--- 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 v5.0 | ilang.ai
development83
learn-mistake
Record mistakes. Check before similar builds. Avoid repeating silently.
development83
plan-estimate
Give realistic time and cost estimates for each step. Explain in human terms.
data-ai83
requirement-lock
Lock confirmed requirements. Don't change them without user approval.
tools83
progress-report
Report progress after each feature. Percentage, what just completed, what comes next.
business83
plan-priority
Decide what to build first. Core function before polish. Revenue before aesthetics.
development83
project-roadmap
Create a visual roadmap for large projects. Phases, milestones, timeline.
tools83
plan-risk
Identify risks before building. Flag third-party dependencies, API limits, and cost traps.
development83
save-rollback
Save checkpoints before risky changes. Rollback if things break.
testing83
security
Auto-apply security basics and block deploys that would leak secrets. Never ask the user about security choices — just do it, and run a real secret scan before going live.
development83
run-on-server
Run and test directly on the server. No local dev environment needed. What you build is what goes live.
development83
performance
Optimize for speed and cost. Pick lightweight solutions. Flag expensive operations.
tools83
multi-device
Help user work from multiple devices. Sync project via git.
development83
learn-pattern
Detect recurring patterns in user's project. Apply automatically next time.
tools83
fix-guide
Guide user through errors they see. Translate error messages to human language.
documentation83
deploy-global
Choose deployment target based on project type. Static sites to CF Pages, APIs to VPS, serverless to Workers.
development83
auto-quality
Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.
testing83
best-choice
When multiple solutions exist, pick the best one. Explain why in one sentence.
data-ai83
fix-explain
After fixing a bug, explain what went wrong in language the user understands. No jargon for beginners.
development83
full-review
Full project review from beginning. Check every file. Plain language report.
testing83
plan-breakdown
Break complex tasks into 5-15 ordered steps with time estimates. Dependency order first.
tools83
skills/session-start
# AutoCode v5.0 — I-Lang v5.0 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
development83
user-level-detect
Detect user's technical level from first messages. Adjust all output language accordingly.
tools83
build-feature
Build one feature at a time. Complete each fully before moving to next. Auto-triggers quality check.
development83
deploy-cf-workers
Deploy to Cloudflare Workers. Free tier handles 100k requests/day. Global edge network.
devops83
env-setup
Help complete beginners set up their development environment. Detect Mac or other. Guide VPS purchase and SSH setup step by step.
development83
fix-auto
Auto-fix bugs. Observe symptom, find root cause, apply minimal fix, verify, explain in human terms.
testing83
understand-intent
Detect user's intent from their message and activate the right workflow silently.
tools83
ask-smart
Before coding, determine what to ask. Max 2 yes/no questions. Never ask technical questions.
tools83
compress
I-Lang compression engine. All internal planning uses I-Lang v5.0 syntax. Save 60%+ tokens. User never sees compressed output.
tools83
cost-explain
Explain all costs in human terms. Always compare with real-world equivalents. Recommend cheapest that works.
data-ai83
clarify-scope
Classify request as small/medium/large. Adjust workflow depth accordingly.
tools83
celebrate
Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.
data-ai83
build-ui
Build user-facing interface. Clean, functional, mobile-friendly by default.
development83
efficiency-compare
At milestones, compare achievement vs human programmer time and cost. Keep it realistic.
testing83
build-scaffold
Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.
development83
file-transfer
Transfer files between local and server. Guide user through SCP or upload methods.
documentation83
decision-translate
Translate technical decisions into human language. Explain in cost, speed, stability.
testing83
daily-summary
End of session summary. What got done, what got fixed, what comes next, progress delta.
development83
milestone
Track project milestones. Auto-detect when a significant checkpoint is reached.
testing83
domain-bind
Help user buy a domain, configure DNS, set up SSL. Guide every click.
tools83
deploy-vps
Deploy to VPS. Code is already on the server. Start the service, configure nginx, verify accessible.
development83
judge-when-to-ask
Decide when AutoCode acts on its own and when it must stop and ask the user. Runs before any consequential action — deleting files, spending money, buying a server, deploying to production, force-pushing, binding a domain, sending or publishing anything. Ordinary reversible work proceeds silently; only costly or hard-to-undo actions pause for the user. Powered by I-Lang v5.0 vector judgment.
development83
skills/fix-solve
--- 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} 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 v5.0 | ilang.ai
development83
learn-preference
Learn user's preferences over time. Code style, naming, structure. Save to global prefs.
development83
learn-mistake
Record mistakes. Check before similar builds. Avoid repeating silently.
development69
efficiency-compare
At milestones, compare achievement vs human programmer time and cost. Keep it realistic.
testing69
deploy-vps
Deploy to VPS. Code is already on the server. Start the service, configure nginx, verify accessible.
development69
clarify-scope
Classify request as small/medium/large. Adjust workflow depth accordingly.
tools69
ask-smart
Before coding, determine what to ask. Max 2 yes/no questions. Never ask technical questions.
tools69
requirement-lock
Lock confirmed requirements. Don't change them without user approval.
tools69
auto-quality
Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.
testing69
fix-explain
After fixing a bug, explain what went wrong in language the user understands. No jargon for beginners.
development69
run-on-server
Run and test directly on the server. No local dev environment needed. What you build is what goes live.
development69
user-level-detect
Detect user's technical level from first messages. Adjust all output language accordingly.
tools69
cost-explain
Explain all costs in human terms. Always compare with real-world equivalents. Recommend cheapest that works.
data-ai69
decision-translate
Translate technical decisions into human language. Explain in cost, speed, stability.
testing69
deploy-global
Choose deployment target based on project type. Static sites to CF Pages, APIs to VPS, serverless to Workers.
development69
domain-bind
Help user buy a domain, configure DNS, set up SSL. Guide every click.
tools69
env-setup
Help complete beginners set up their development environment. Detect Mac or other. Guide VPS purchase and SSH setup step by step.
development69
fix-auto
Auto-fix bugs. Observe symptom, find root cause, apply minimal fix, verify, explain in human terms.
testing69
plugins/autocode/skills/fix-reason
--- 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
tools69
memory
Persistent memory across sessions. Save project state and user preferences. Never save secrets.
tools69
milestone
Track project milestones. Auto-detect when a significant checkpoint is reached.
testing69
multi-device
Help user work from multiple devices. Sync project via git.
development69
performance
Optimize for speed and cost. Pick lightweight solutions. Flag expensive operations.
tools69
plan-estimate
Give realistic time and cost estimates for each step. Explain in human terms.
data-ai69
plan-priority
Decide what to build first. Core function before polish. Revenue before aesthetics.
development69
plan-risk
Identify risks before building. Flag third-party dependencies, API limits, and cost traps.
development69
progress-report
Report progress after each feature. Percentage, what just completed, what comes next.
business69
project-roadmap
Create a visual roadmap for large projects. Phases, milestones, timeline.
tools69
save-rollback
Save checkpoints before risky changes. Rollback if things break.
testing69
security
Auto-apply security basics. Never ask user about security choices. Just do it.
testing69
plugins/autocode/skills/session-start
# 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
tools69
understand-intent
Detect user's intent from their message and activate the right workflow silently.
tools69
plan-breakdown
Break complex tasks into 5-15 ordered steps with time estimates. Dependency order first.
tools69
file-transfer
Transfer files between local and server. Guide user through SCP or upload methods.
documentation69
best-choice
When multiple solutions exist, pick the best one. Explain why in one sentence.
data-ai69
build-feature
Build one feature at a time. Complete each fully before moving to next. Auto-triggers quality check.
development69
build-scaffold
Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.
development69
build-ui
Build user-facing interface. Clean, functional, mobile-friendly by default.
development69
celebrate
Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.
data-ai69
compress
I-Lang compression engine. All internal planning uses I-Lang v3.0 syntax. Save 60%+ tokens. User never sees compressed output.
tools69
daily-summary
End of session summary. What got done, what got fixed, what comes next, progress delta.
development69
deploy-cf-workers
Deploy to Cloudflare Workers. Free tier handles 100k requests/day. Global edge network.
devops69
fix-guide
Guide user through errors they see. Translate error messages to human language.
documentation69
plugins/autocode/skills/fix-observe
--- 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
tools69
plugins/autocode/skills/fix-solve
--- 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
tools69
full-review
Full project review from beginning. Check every file. Plain language report.
testing69
go-live
Final go-live checklist. Is it accessible? SSL working? Mobile friendly? Show user their live URL.
development69
learn-pattern
Detect recurring patterns in user's project. Apply automatically next time.
tools69
learn-preference
Learn user's preferences over time. Code style, naming, structure. Save to global prefs.
development69
lazarus
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。
development25
WeChat-Awesome
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。
tools25
SEO-Awesome
--- slug: ilang-seo-awesome name: SEO-Awesome displayName: SEO-Awesome version: 1.2.5 summary: First-party Google API data-driven pSEO automation framework. From keyword research to bulk page generation to auto-review. author: ilang-ai license: MIT tags: [seo, pseo, monetization, google-api, automation] homepage: https://ilang.ai --- # SEO-Awesome First-party data. Zero third-party tools. Full automation. 一手数据驱动，零第三方工具费，全链路自动化。 --- ## What this skill does | 这个技能干什么 Build an SEO automation
tools22
Niche-Awesome
Niche-Awesome — Solve the #1 problem for beginners building AI products: not knowing what to build. A complete 6-step BRD (Business Requirements Document) research process for niche product selection and market validation. You do the searching, AI does the analysis. Works with any AI, no coding required.
development18
no-prompt
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.
development17
everything-is-ok
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.
development17
DeAI
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.
data-ai17
everything-is-ok
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.
development17
less-token
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.
tools17
freemoney
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。
data-ai17
no-prompt
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.
development17
freemoney
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）。
tools17
ilang-compress
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.
data-ai17
less-token
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.
tools17
ilang-compress
Compress natural language prompts into I-Lang — AI-native structured instructions. 40-65% token savings.
data-ai16