Skip to content
Apothem
流水线命令

流水线命令

Apothem 流水线命令参考——/plan 流程与审计命令目录。

Apothem 提供一个具备架构感知的 /plan 流水线、一个十三阶段的 /research 流水线,以及一个由十一条命令组成的审计评审序列——为每个项目提供一条结构化路径:从原始文字描述到生产级、经多维度评审的代码,以及从原始构想到经同行评审并已传播的论文。

流水线概览

flowchart LR
    accTitle: Plan pipeline command flow
    accDescr: Left-to-right flowchart of the apothem plan pipeline from the spec stage through the generate and review stages, then through a conditional architecture-bearing decision that either runs the design stage or skips directly to the execute stage. The orthogonal audit stage wraps the spec-through-review span as a closed remediation loop, and the re-entrant amend stage revises an existing suite and returns it to review.
    A[/plan-spec] --> B[/plan-generate]
    B --> C[/plan-review]
    AUD[/plan-audit<br/>orthogonal: wraps spec → review] -.->|closed-loop remediation| A
    AM[/plan-amend<br/>re-entrant: revises an existing suite] -.->|re-review| C
    C --> Q{Architecture-bearing suite?}
    Q -->|yes| F[/plan-design<br/>emit _inputs/design.md]
    Q -->|no| D[/plan-execute]
    F --> D
    D --> E[/plan-status]
    D --> G[Audit review sequence]
    G --> H[Completion milestone]

规划阶段

该流水线以八个一等斜杠命令的形式提供,每个阶段一个——每个都可作为 /plan-<stage> 独立调用。/plan 编排器驱动它们,从一项任务目标推进到一个已执行的套件。

阶段角色位置
/plan-spec锻造者——从文字描述到规范链首
/plan-generate生成器——从规范到计划套件链中
/plan-review审计员——取证式计划审计链中
/plan-design架构师——为承载架构的套件生成 _inputs/design.md条件闸门
/plan-execute执行器——阶段执行末端
/plan-status报告器——只读状态只读
/plan-audit守护者——对 spec → generate → review 的闭环包装正交(执行前)
/plan-amend管家——对现有套件的可重入修订可重入

/plan-audit 与线性流程正交,而不是其中的一个阶段。它将 /plan-spec → /plan-generate → /plan-review 包装为一个单一闭环,只运行缺失的上游阶段,主动修复发现项,并使套件处于可交给 /plan-execute 的就绪状态。它不同于下文的审计评审序列,后者审计的是已执行的代码库,而不是计划套件。

/plan-design 不是一道普遍适用的仪式。/plan-review 判定套件是否变更承载架构的表面。如果是,/plan-design 生成供 /plan-execute 和 /architecture-review 使用的设计踪迹。如果不是,经评审的套件直接进入执行。

研究流水线

研究流水线以十三个一等斜杠命令的形式提供,每个阶段一个——每个都可作为 /research-<stage> 独立调用,由序列闸门和交接清单串联,并受十项严谨性强制规定约束(权威来源、可复现性、可证伪性、引用完整性、预注册、伦理 / 利益冲突、统计严谨性、开放科学 / FAIR、报告指南合规、理论基础 / 影响力)。

flowchart LR
    accTitle: Research pipeline command flow
    accDescr: Left-to-right flowchart of the apothem research pipeline from the ideate stage through spec, theory, sources, synthesis, proposal, study design, experiment, analysis, paper, and peer review to publish and disseminate, with a revision loop from review back to paper.
    RI[/research-ideate] --> RS[/research-spec]
    RS --> RT[/research-theory]
    RT --> RSO[/research-sources]
    RSO --> RSY[/research-synthesis]
    RSY --> RPR[/research-proposal]
    RPR --> RD[/research-design]
    RD --> RE[/research-experiment]
    RE --> RA[/research-analysis]
    RA --> RP[/research-paper]
    RP --> RR[/research-review]
    RR --> RPU[/research-publish]
    RPU --> RDI[/research-disseminate]
    RR -.->|revision loop| RP
阶段角色位置
/research-ideate提出问题——从领域种子生成候选问题链首
/research-spec框定问题——可证伪假设 + 范围链中
/research-theory概念框架 + 变革理论链中
/research-sources带可重新运行检索记录的系统性来源收集链中
/research-synthesisSOTA 图谱 + 缺口分析链中
/research-proposal目标 + 可行性 + 应急预案 + 影响力 + 数据计划 + 预注册计划;资助方征集公告矩阵或再次申请回应链中
/research-design研究设计 + 预注册链中
/research-experiment运行 + 记录,可复现链中
/research-analysis结果 + 统计链中
/research-paper顶级论文草稿链中
/research-review同行评审级别的批评链中
/research-publish面向发表渠道的材料包 + 投稿链中
/research-disseminate传播 + 影响力 + FAIR 归档末端

/research 包装式工作流编排器驱动这些阶段,从原始问题推进到已发表的论文(它本身不是一个阶段),并在下一阶段基于每个阶段的输出继续构建之前,独立检查该输出;--quick 只运行 /research-sources + /research-synthesis,用于生成一次性的带引用报告。

实证阶段(来源、设计、实验、分析)和写作阶段(论文、评审、发表、传播)还会借助若干将严谨性付诸实施的表面——公平的多方法比较、比较对象的来源记录、实验项目脚手架、算力利用计划、可选启用的自主实验循环、完成定义推进闸门、带分阶段披露的盲法、检索记录、研究分配与检验力规划、分析规范、计划应急预案、图表完整性,以及演讲与海报规划——它们为这十项强制规定补充操作细节,而不扩展这些规定。

审计评审序列

/audit 包装式工作流编排器以单次并行扫查覆盖下列全部十一个维度——它是审计堡垒中与 /plan 和 /research 相对应的命令——并综合出一份去重、按严重级别分诊的发现项报告(仅报告;修复交由 /elevate)。每个维度也都可以单独调用。

/fortress 包装式工作流编排器闭合 /audit 所报告的回路:它通过 /audit 进行检测,核实每个发现项,在其所属表面修复每个留存的发现项,在有界循环中重新审计,并通过 /release-readiness 为结果把关——它是生产加固中与 /plan 和 /research 相对应的命令。

命令质量领域
/code-review代码质量
/code-audit代码语料
/security-auditOWASP / ASVS
/perf-audit性能
/architecture-review架构
/ux-review开发者体验
/a11y-audit无障碍
/docs-review文档
/dependency-audit依赖
/supply-chain-audit供应链
/threat-model-audit威胁模型

全部命令

每条随附的命令,均由其在 src/apothem/commands/ 下的定义生成。没有手写页面的命令会获得一个由同一定义生成的页面。

CommandSummary
/planRuns the planning pipeline (spec, generate, review, design) with independent verification, confirming at each hand-off; execute stays a manual step the …
/plan-specTurns free-form prose, notes or rough requirements into a spec-grade _spec/spec.md that keeps the author's wording and settles open questions by inquiry.
/plan-generateGenerates a full plan suite (master plan, progress log, decision notes, per-phase files) from a written spec or raw prose.
/plan-reviewReads an existing plan suite line by line for fidelity, consistency, completeness and risk, then applies only the revisions the user approves.
/plan-designWrites the architectural design for a reviewed plan suite at _inputs/design.md: components, interfaces, decisions and diagrams.
/plan-executeUse to implement one phase of a reviewed plan suite: reads the phase file and progress notes, verifies prerequisites and review scorecards, implements each …
/plan-amendChanges an existing plan suite without losing resolved decisions, re-deriving only the affected spec, phases and notes.
/plan-auditAudits a plan suite across spec, generate and review, then fixes findings in a loop without per-revision approval until none remain or the cap is hit.
/plan-statusReports plan-suite progress from its tracking files across tasks, phases and artifacts, read-only.
/researchRuns the research pipeline from idea to peer-reviewed paper, verifying each stage hand-off and halting before data collection or publication.
/research-ideateFinds a research question from zero by scanning opportunities, gaps, and invalidated hypotheses, then ranking candidates.
/research-specFrames a research question or notes into a testable spec: falsifiable hypotheses, inclusion and exclusion scope, success metrics.
/research-theoryBuilds the conceptual framework for a framed research question: theory of change, constructs with operational definitions and a conceptual-model diagram.
/research-sourcesCollects and screens the literature for a ratified research spec: deduplication, ranking and extraction with provenance.
/research-synthesisReconciles collected sources into a state-of-the-art map, a literature matrix and a research-gap statement.
/research-proposalTurns a research gap and theoretical framework into a fundable proposal: SMART aims, feasibility, risk register with contingencies, impact pathway, data …
/research-designTurns a synthesized research gap into testable predictions, a study design and a frozen preregistration.
/research-experimentRuns the preregistered study protocol and records raw data with provenance: experiment log, data, and reproducibility manifest (environment, seed, version …
/research-analysisRuns the preregistered statistical analysis on collected data: effect sizes with confidence intervals, multiple-comparison correction, robustness checks, …
/research-paperAssembles a paper draft from the synthesis, study design, and analysis, with every citation checked to resolve.
/research-reviewHostile peer review of a paper, from a research suite or a supplied PDF or text: scores novelty, rigor, reproducibility, ethics; ranks revisions.
/research-publishBuilds the venue submission package for a reviewed paper: template formatting, cover letter, data and code availability statement, ethics and conflict …
/research-disseminatePlans post-acceptance dissemination and impact: preprint announcement, FAIR data and code archive, altmetrics tracking, rebuttal loop.
/auditSweeps a repository across all eleven review dimensions in one multi-agent run and returns one verified, severity-ranked report; it never fixes anything.
/a11y-auditAudits rendered pages of a web surface against WCAG 2.2 AA and reports severity-ranked findings per page, without fixing anything.
/architecture-reviewReviews a repository against its design document and layer rules, reporting boundary violations, coupling and wiring gaps as ranked findings.
/code-auditCross-file forensic audit: hidden coupling, type-hint gaps, coverage holes, dead and duplicate code.
/code-reviewReviews source files one at a time for readability, naming, complexity, idiom fit and comment quality, and reports severity-ranked findings without editing.
/dependency-auditAudits direct and transitive dependencies for known vulnerabilities, license conflicts, deprecation and loose pins, ranking findings per dependency.
/docs-reviewReviews documentation pages for prose clarity, broken links, code-block tags, citations and public-API coverage, reporting severity-ranked findings per page.
/perf-auditAudits an Apothem installation's per-class budgets (hooks, ecosystem verification, conformity gate, tests, agents, shell, lint) with its benchmark drivers, …
/security-auditAudits a repository's security posture: secrets, injection, unsafe deserialization, path traversal, vulnerable dependencies.
/supply-chain-auditAudits a repository's release pipeline: build provenance, artifact signing, SBOM completeness, pinned CI actions and minimum permissions.
/threat-model-auditThreat-models a repository with STRIDE per element and trust boundaries, classifying actors and rating residual risk.
/ux-reviewReviews a repository's developer experience from a first-time user's view: CLI ergonomics, error messages, install flow and docs discoverability.
/fortressHardens a repository end to end: runs the audit sweep, verifies each finding, remediates survivors through the surgical-guard, secret-rotation and vuln-triage …
/elevateWhole-repository elevation: runs the audit sweep, then critiques naming, structure, storytelling and extensibility, remediates what it finds (deletions are …
/evalRuns one evaluation campaign for a language model or prompt: scores each output over a dataset and reports metrics by category plus regressions against a …
/freshifyUse when a repository must be made fresh and release-clean: purges caches and stale artifacts, removes legacy narrative and back-references, normalizes file …
/github-deploy-freshUse when a GitHub repository needs one clean first release on origin/main: a single v0.1.0 release commit, green workflow cards, a first-version changelog, and …
/github-deploy-nextUse to run the next release cycle on a GitHub repository: merge ready pull requests, resolve the issues the release addresses, derive the SemVer bump from …
/projectifyBuilds the Description, Instruction and knowledge files for a chat-app Project or custom assistant through guided questions, within the platform's context …
/release-readinessPre-release gate sweep: use before shipping a repository to check lint, format, types, tests, dependency and supply-chain risk, visibility surfaces, changelog …
/test-suiteAuthors and runs behavior-first tests for a repository, triages failures and reports coverage gaps on critical paths.
/workflowUse to run a non-trivial mission as an independent multi-agent workflow: parallel subagents under named return contracts, refute-by-default verification of …

On this page