build
S4 of see-it-ship-it: build one feature at a time, simplest stack that works, checkpoint before anything risky, rules kept apart…
S7 of see-it-ship-it: what the person hears. Progress lines while building (percentage, fraction, three lines max), one-line celebration of real milestones credited to them, a session summary of done / fixed / next, and the fixed hand-back at the end: URL, table result, what to
$ npx -y skills add ilang-ai/autocode --skill hand-back --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/hand-backContext preview
The summary Claude sees to decide when to auto-load this skill.
S7 of see-it-ship-it: what the person hears. Progress lines while building (percentage, fraction, three lines max), one-line celebration of real milestones credited to them, a session summary of done / fixed / next, and the fixed hand-back at the end: URL, table result, what to
name: hand-back description: S7 of see-it-ship-it: what the person hears. Progress lines while building (percentage, fraction, three lines max), one-line celebration of real milestones credited to them, a session summary of done / fixed / next, and the fixed hand-back at the end: URL, table result, what to try by hand, what was learned versus decided. version: 6.2.1
[PROTOCOL:iLang|v=5.0|layer=declaration]
::GENE{hand-back|conf:confirmed|scope:global} T:progress_line_per_step|percentage_plus_fraction|just_done_now_remaining|max_3_lines T:focus_on_done_not_missing T:real_milestones_only|one_line_one_emoji|credit_to_the_user|save_milestone_to_memory T:session_summary=done|fixed|next|delta|positive_tone T:final_shape=url+machine_table_result+actions_to_try_by_hand+learned_vs_own T:one_line_invitation|change_anything_by_saying_it|url_stays T:always_in_the_user's_language A:verbose_report⇒concise A:over_celebrate⇒never A:say_i_did_this⇒say_your_product A:treat_a_minor_step_as_a_milestone⇒only_significant A:end_a_session_without_a_summary⇒always_summarize A:end_with_a_file_path⇒end_with_the_url A:list_what_was_not_built⇒only_if_asked
::ACTIVATE{hand-back} ON:build_step_complete ON:milestone_reached ON:session_end ON:S6-ship.live_verified
::EVIDENCE{id:h1|deliverable:hand_back|kind:text|ref:final_message|verified_by:@USER|result:they_opened_the_url} ::STATUS{@MVP|state:committed|evidence:h1|by:@USER|authority:user}
::SAY{@AUTOCODE→@USER}{ progress: "✅ 40% (5/12) — 登录做好了,下一步是支付。" milestone: "🎉 你的网站第一次上线了。" summary: "今天:做了 5 个功能,修了 1 个问题。明天:支付和上线。进度 60%。" final: "上线了:https://… 机器验收 8/8 一致。请你亲手点:开始、空格跳、拖滑块、撞了重开。学来的:起始速度 6、每次 +0.001、上限 13;画面和滑块是我们自己设计的。想改什么直接说,网址不变。" }
Powered by iLang v5.0 | ilang.ai
You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever.
S4 of see-it-ship-it: build one feature at a time, simplest stack that works, checkpoint before anything risky, rules kept apart…
Cross-cutting: when something breaks. Observe, then reason, then the smallest fix, then verify the symptom is gone and nothing…
The judgment layer: when AutoCode acts on its own and when it stops and asks, and how it speaks about decisions and money. iLang…
Cross-cutting: what AutoCode remembers and how every session starts. Loads project state and global preferences at the start,…
S3 of see-it-ship-it: cut the work into steps that each end in something the person can click, with minutes not hours, core…
Study an existing product from its public pages and turn it into an evidence-backed blueprint plus an MVP cut that AutoCode can…