assemble
免费Dev-Critic loop: implement, review, fix — repeat until clean
中文简介正在准备中。当前显示原文说明。
Lint, build, test, verify specs, commit, and push — one micro-commit to remote. Validates the working tree, verifies spec alignment, and creates an atomic save point.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Validate the working tree, verify spec alignment, create a micro-commit, and push it to the remote — a single atomic "save point."
When a small, bounded unit of work is completed and needs to be shipped safely.
Ensure the codebase is green (lint, build, test, typecheck), verify that changed code stays aligned with its specs, create a well-formed micro-commit, and push to the current remote branch.
dev), authoring or amending specs (spec), creating Linear issues (lead).Execute these steps in order. Stop immediately on any failure — do not skip steps or push broken code.
Run in parallel:
git status — identify changed filesgit diff --staged and git diff — understand the actual changesgit log --oneline -5 — read recent commit styleIf there are no changes (clean working tree), stop and tell the user.
Run in parallel:
pnpm lintpnpm buildpnpm test:runpnpm checkAll four must pass. On failure: report which gate failed with the error output and stop. Do not attempt to fix — that is the developer's job.
For every changed file, check whether a related spec exists under specs/. Use the file path and component name to locate relevant specs.
For each relevant spec found:
If a spec violation or missing spec update is found: report it and stop. Do not commit.
If no spec exists for the changed files: that's fine — not all files have specs. Note it and proceed.
For all changed files identified in Step 1, check if there are any related assessments in docs/assessments/ledger.jsonl with execution_status: "pending". An assessment is related if its slug, target files, or challenger title overlap with the files being committed.
If matching pending assessments are found:
docs/assessments/ledger.jsonl:
"execution_status": "success" (or "failed")"execution_retro": A brief summary of the implementation results (e.g. build results, user feedback)"lessons_learned": Any specific lessons or guidelines surfaced.docs/assessments/lessons.md with the new heuristics under ## Heuristics & Lessons.docs/assessments/ledger.jsonl and docs/assessments/lessons.md so they are automatically included in the commit.git add (specific files, not -A).type(scope): description$ARGUMENTS, use it as the basis-u origin HEAD./ship is one micro-commit. Small, reversible, traceable./ship again.$ARGUMENTS
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Dev-Critic loop: implement, review, fix — repeat until clean
中文简介正在准备中。当前显示原文说明。
Assess source material against the ASDLC Knowledge Base and produce an evidence-calibrated Content Review Report.
中文简介正在准备中。当前显示原文说明。
Perform an adversarial review of the current uncommitted changeset, validating it against project contracts and architectural intent.
中文简介正在准备中。当前显示原文说明。
Triage the content corpus against the latest GSC snapshot and produce a prioritized refresh report. Read-only: reports, never edits.
中文简介正在准备中。当前显示原文说明。
Implement features, fix bugs, and keep the codebase healthy and maintainable. Works from a defined PBI, issue, or task description.
中文简介正在准备中。当前显示原文说明。
GEO+SEO audit of asdlc.io — analyzes the codebase for Generative Engine Optimization across AI citability, technical infrastructure, content quality, schema markup, and knowledge base discoverability. Produces a composite GEO Score (0-100) with prioritized action plan.
中文简介正在准备中。当前显示原文说明。