build
S4 of see-it-ship-it: build one feature at a time, simplest stack that works, checkpoint before anything risky, rules kept apart…
S5 of see-it-ship-it: prove it works before saying so. Silent quality checks after every feature, a full review of every file before save and deploy, and the acceptance table (check / expected / actual / match) run on the local build and again on the live URL. Never 'tests
$ npx -y skills add ilang-ai/autocode --skill verify --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/verifyContext preview
The summary Claude sees to decide when to auto-load this skill.
S5 of see-it-ship-it: prove it works before saying so. Silent quality checks after every feature, a full review of every file before save and deploy, and the acceptance table (check / expected / actual / match) run on the local build and again on the live URL. Never 'tests
name: verify description: S5 of see-it-ship-it: prove it works before saying so. Silent quality checks after every feature, a full review of every file before save and deploy, and the acceptance table (check / expected / actual / match) run on the local build and again on the live URL. Never 'tests passed'. version: 6.2.1
[PROTOCOL:iLang|v=5.0|layer=declaration]
::PRIOR{dimension:completion|default:assume_incomplete|authority:system|scope:@JOURNEY} ::PRIOR{dimension:completion|default:not_live_until_url_opened_and_acceptance_rerun|authority:system|scope:@JOURNEY}
::GENE{verify|conf:confirmed|scope:global} T:check_after_every_feature|silently|fix_minor_things_without_saying T:run_tests_if_a_framework_exists|never_claim_a_run_that_did_not_happen T:full_review_before_save_and_deploy|every_file|logic|edges|security|hardcoded_values T:acceptance_runner_is_a_fixed_build_output|tool:product-study/scripts/acceptance_run.py T:checks_file_next_to_the_build|acceptance.js|acceptance.py|one_json_row_per_check T:table=check|expected|actual|match|readable_by_a_non_technical_person T:user_checks_listed_as_actions_to_perform|not_as_tests_passed T:fix_then_rerun_until_all_match|before_ship T:rerun_on_the_live_url_after_ship T:human_readable_commit_messages A:report_tests_passed⇒show_expected_vs_actual A:claim_tests_passed_without_running⇒reject A:announce_that_you_are_checking⇒silent A:say_tests_failed_to_the_user⇒fix_first_then_report A:partial_review⇒full_review A:skip_review_on_save⇒never A:no_headless_browser⇒rules_block_checks_in_node_or_python
::ACTIVATE{verify} ON:feature_complete ON:before_save ON:before_deploy ON:S4-build.step_complete ON:S6-ship.url_live ON:session_end
::STATE{@ACCEPT, the acceptance table}
[TEST:@ACCEPT|src=@LOCAL]=>[CHEK:@ACCEPT|whr=all_match]=>[Ω:@USER|fmt=text|typ=table]
::EVIDENCE{id:v1|deliverable:site|kind:test_output|ref:acceptance_table_local|verified_by:@TOOL|result:all_match} ::EVIDENCE{id:v2|deliverable:site|kind:test_output|ref:acceptance_table_live|verified_by:@TOOL|result:all_match} ::STATUS{@MVP|state:claimed_complete|evidence:v1|by:@AGENT|authority:proposal} ::STATUS{@MVP|state:verified|evidence:v2|by:@TOOL|authority:runtime}
python3 skills/product-study/scripts/acceptance_run.py <site_dir> # local build python3 skills/product-study/scripts/acceptance_run.py <site_dir> --url <live> # after ship
::SAY{@AUTOCODE→@USER}{ table: "5 自动加速 10000 次更新后速度 13.001 13.001 ✓ 一致 … 8/8 一致" to_user: "机器能查的 8 项全部一致。剩下请你亲手点:开始、空格跳、拖滑块、撞了重开。" }
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…
S7 of see-it-ship-it: what the person hears. Progress lines while building (percentage, fraction, three lines max), one-line…
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…