om-implement-feature

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Implement Feature for Human Review

为人工审查实现功能

Drive a feature from brief through specification, implementation, testing, and review while keeping publication as a separate explicit user decision.
推动一项功能从 brief 贯穿 specification、implementation、testing 和 review,同时将发布保留为由用户另行明确决定的事项。

Arguments

参数

  • --interactive
    (default) or
    --autonomous
    — apply the execution mode throughout this workflow; never enable publication. Reject both together.
  • {brief}
    (required) — feature goal, constraints, and acceptance criteria.
  • --profile <standard|optimized|multi|multi-optimized|high-assurance>
    (optional) — default
    standard
    .
  • --slug <kebab-case>
    (optional) — override the worktree branch and spec slug.
  • --interactive
    (默认)或
    --autonomous
    ——在整个工作流中应用所选的执行模式;绝不启用发布。 若同时指定两者,则予以拒绝。
  • {brief}
    (必填)——功能目标、约束条件和 acceptance criteria。
  • --profile <standard|optimized|multi|multi-optimized|high-assurance>
    (可选)——默认为
    standard
    。
  • --slug <kebab-case>
    (可选)——覆盖 worktree branch 和 spec slug。

Chaining

链式调用

Consume the issue or brief and requested profile. Invoke the base workflow and its lower-level companions by name; stop with the missing name if one is unavailable. Emit the staged handoff, optional
Issue:
/
Spec:
references, and final
WORKTREE=
line. Publication is a separate human-authorized step.
读取 issue 或 brief 以及请求的 profile。按名称调用基础工作流及其底层配套工作流;如果其中任何一项不可用,则报告缺失的名称并停止。输出已暂存的交付结果、可选的
Issue:
/
Spec:
引用和最终的
WORKTREE=
行。发布是一个单独且经人工授权的步骤。

Workflow

工作流

ALWAYS check first: Apply
.ai/skills/om-implement-feature/SKILL.md
when present; safety rules still win.
  1. Agentic setup — follow
    references/agentic-setup.md
    before any action: load approved configuration, apply local extensions and shared rules, and preserve the untrusted-content boundary.
始终先检查:如果存在
.ai/skills/om-implement-feature/SKILL.md
,则应用该 skill;安全规则仍然优先。
  1. Agent 初始化——在任何操作之前,按照
    references/agentic-setup.md
    执行:加载已批准的配置,应用本地扩展和共享规则,并保持不可信内容边界。

1. Preflight and isolate

1. 预检与隔离

Follow
references/feature-workflow.md
to detect duplicate or in-flight work, resolve a trusted harness profile, create an isolated worktree from the configured base, and capture the harness start-state artifact before writing the spec.
按照
references/feature-workflow.md
执行,以检测重复或正在进行的工作,解析可信的 harness profile,从配置的 base 创建隔离的 worktree,并在写入 spec 之前捕获 harness start-state artifact。

2. Specify and audit

2. 规格与审计

Run
om-spec-writing
in the isolated worktree. Resolve answerable open questions from repository evidence and surface only genuine product decisions. Use a repo-local
om-pre-implement-spec
when available. For
multi
,
multi-optimized
, and
high-assurance
, follow the
om-harness
bound
om-code-review
council contract: prepare an exact-spec packet, delegate
om-code-review
to a new Claude context with no implementation transcript, and run every configured advisor concurrently on that same packet. Fix confirmed design blockers before implementation.
在隔离的 worktree 中运行
om-spec-writing
。根据仓库证据解决可回答的开放问题,并且只提出真正需要作出的产品决策。可用时使用 repo-local
om-pre-implement-spec
。对于
multi
、
multi-optimized
和
high-assurance
,遵循由
om-harness
绑定的
om-code-review
council contract:准备 exact-spec packet,将
om-code-review
委派给一个不包含 implementation transcript 的全新 Claude context,并在同一个 packet 上并发运行所有已配置的 advisor。在 implementation 之前修复已确认的设计 blockers。

3. Implement

3. 实现

Implement the audited phases using the lower-level specification, test, and review skills named here.
om-auto-implement-spec
is the publication driver; reserve it for an explicitly authorized PR workflow because its normal engine creates commits and PRs. Do not invoke it inside this staged-only run. For
optimized
profiles, dispatch bounded, file-disjoint packets through configured workers and verify every packet before integration. For
high-assurance
, use versioned packet manifests and require blind review, fresh finding verification, separate fixer context, and deterministic exact-diff acceptance evidence before integration. Create no checkpoint commits.
使用这里指定的底层 specification、test 和 review skills 实现经过审计的各阶段。
om-auto-implement-spec
是发布驱动器;仅将其用于获得明确授权的 PR 工作流,因为其常规引擎会创建 commits 和 PRs。在此次 staged-only 运行中不要调用它。对于
optimized
profiles,通过已配置的 workers 分派范围有界且文件集合互不重叠的 packets,并在集成前验证每个 packet。对于
high-assurance
,使用版本化的 packet manifests,并要求 blind review、在全新上下文中进行 finding 验证、独立的 fixer context,以及确定性的 exact-diff acceptance evidence,然后才能集成。不要创建 checkpoint commits。

4. Test and preview

4. 测试与预览

Add unit and integration coverage for every changed behavior. Run
om-integration-tests
when the repository supports it. Run the full configured validation gate. For UI changes, enforce the repository's design system on every touched UI line before review — run the repo-local design-system guardian skill when the repository ships one, otherwise apply its documented design-system rules and checklist — and run local
om-auto-qa-pr
without a PR number, keeping its artifacts outside the stage allowlist.
为每一项发生变更的行为添加 unit 和 integration 测试覆盖。在仓库支持时运行
om-integration-tests
。运行已配置的完整 validation gate。对于 UI 变更,在 review 之前确保所有涉及 UI 的代码行都符合仓库的 design system:如果仓库提供 repo-local design-system guardian skill,则运行它;否则应用其文档化的 design-system 规则和 checklist。并在不带 PR number 的情况下运行本地
om-auto-qa-pr
,同时确保其 artifacts 位于 stage allowlist 之外。

5. Review and reconcile

5. 审查与协调

Run
om-code-review
against the complete uncommitted implementation and spec. For
standard
and
optimized
, create a new Claude context with no inherited implementation transcript and run the skill there. For
multi
,
multi-optimized
, and
high-assurance
, follow the
om-harness
bound council contract: freeze the exact diff, validation evidence, and repository rules; start fresh Claude and every configured advisor concurrently with the same complete
om-code-review
rubric and packet; then require Claude's matching artifact before reconciliation. Preserve minority findings, fix confirmed blockers, and repeat validation, packet preparation, and all reviews until no confirmed blocking finding remains or the loop reaches three iterations; then stop and report every surviving finding. Every configured council reviewer must complete: the runtime retries failures with backoff and timeout escalation, and a council missing any required reviewer yields no verdict — re-run it, repair the binding, or stop for the user's decision; never proceed on a partial council.
针对完整的未提交 implementation 和 spec 运行
om-code-review
。对于
standard
和
optimized
,创建一个不继承 implementation transcript 的全新 Claude context,并在其中运行该 skill。对于
multi
、
multi-optimized
和
high-assurance
,遵循
om-harness
绑定的 council contract:冻结 exact diff、validation evidence 和 repository rules;同时启动一个全新的 Claude context 和所有已配置的 advisors,让它们使用同一份完整的
om-code-review
rubric 和 packet;随后必须先获得 Claude 对应的 artifact,才能进行 reconciliation。保留少数评审提出的 findings,修复已确认的 blockers,并重复 validation、packet preparation 和所有 reviews,直到不再存在已确认的 blocking finding,或循环达到三次迭代;然后停止并报告所有仍然存在的 findings。每个已配置的 council reviewer 都必须完成:runtime 会使用 backoff 重试失败,并在超时后进行升级处理;如果 council 缺少任何 required reviewer,则不会产生 verdict——重新运行、修复 binding,或停止并交由用户决定;绝不能在 council 不完整的情况下继续。

6. Stage the handoff

6. 暂存交付结果

Follow the shared
om-harness
stage-only contract: supply the final implementation
--review-packet
and approved
--host-review
artifacts even in
standard
mode, stage only intended files, assert refs and reflogs still match the captured start state, require a clean staged diff, render the report from
references/report-templates.md
, and stop for human review.
遵循共享的
om-harness
stage-only contract:提供最终 implementation 的
--review-packet
和已批准的
--host-review
artifacts,即使在
standard
模式下也是如此;仅暂存预期文件;断言 refs 和 reflogs 仍与捕获的 start state 相符;要求 staged diff 保持干净;根据
references/report-templates.md
渲染报告;然后停止以等待人工审查。

7. Abort or failure cleanup

7. 中止或失败清理

After capture, follow the
om-harness
stage-only contract to stop active processes and invoke
end-run
on abort or terminal failure. Preserve files and packet leases for deliberate recovery. Keep the guard active while repairing or retrying the same run; successful staging ends it.
完成捕获后,遵循共享的
om-harness
stage-only contract,在 abort 或 terminal failure 时停止活跃进程并调用
end-run
。保留 files 和 packet leases,以便进行有意图的恢复。在修复或重试同一次运行时,保持 guard 处于活动状态;成功暂存后结束 guard。

Rules

规则

  • Shared communication, marker, label, and safety rules:
    references/rules.md
    . They always apply.
  • For any non-
    standard
    profile, show the user the probe readiness table (model, binding, role, ✅ ready / ❌ missing-or-failed) before invoking any model.
  • After every council round, paste the reviewer-status table and the findings-by-model matrix from the generated
    review-summary.md
    verbatim into the conversation; the final report repeats the final round's tables.
  • Never invoke
    om-auto-create-pr
    ,
    om-open-pr
    , or another publication-oriented skill.
  • Never commit, push, publish, or execute the tracker
    create-pr
    operation.
  • Never use intermediate commits as checkpoints; use run artifacts and spec progress instead.
  • Never count the implementation worker's model family as independent review.
  • Never run a required Claude review in the conductor's implementation context; inability to create a fresh Claude context is blocking.
  • Never weaken tests, architecture rules, or compatibility contracts to finish the run.
  • Never modify or clean the user's primary-worktree changes.
  • 共享的 communication、marker、label 和安全规则:
    references/rules.md
    。这些规则始终适用。
  • 对于任何非
    standard
    profile,在调用任何 model 之前,向用户展示 probe readiness table(
    model
    、
    binding
    、
    role
    、✅ ready / ❌ missing-or-failed)。
  • 每轮 council 结束后,将生成的
    review-summary.md
    中的 reviewer-status table 和 findings-by-model matrix 原样粘贴到对话中;最终报告重复最后一轮的表格。
  • 绝不调用
    om-auto-create-pr
    、
    om-open-pr
    或其他面向发布的 skill。
  • 绝不执行 commit、push、publish,或 tracker 的
    create-pr
    操作。
  • 绝不将 intermediate commits 用作 checkpoints;改用 run artifacts 和 spec progress。
  • 绝不将 implementation worker 的 model family 计为独立 review。
  • 绝不在 conductor 的 implementation context 中运行必需的 Claude review;无法创建全新的 Claude context 即为阻塞项。
  • 绝不为完成本次运行而削弱 tests、architecture rules 或 compatibility contracts。
  • 绝不修改或清理用户的 primary-worktree changes。