Agent skill

Dependency Analyze

by Towow-ai in Towow-ai/Flowness

从 task 的 read/write set + concept statemachine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集;已有预判逐条标「待复核」交它取证。

Apache-2.0Auto-check passedAgent Workflows

Install Dependency Analyze

skills CLI
$ npx skills add Towow-ai/Flowness --skill dependency-analyze -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Towow-ai/Flowness dependency-analyze --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dependency-analyze .claude/skills/dependency-analyze && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dependency-analyze
GitHub stars
107
Token cost
~1.6k tokens
SKILL.md length
314 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

从 task 的 read/write set + concept statemachine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集;已有预判逐条标「待复核」交它取证。

  • Agent Workflows work in your project
  • SKILL.md covers 我是谁, 我了解的判断世界, 一条"真依赖边"长什么样(关键——认住它) and Shared Knowledge Required(我的…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dependency Analyze is an agent skill from Towow-ai/Flowness. 从 task 的 read/write set + concept statemachine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集;已有预判逐条标「待复核」交它取证。

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. The repository describes itself as: A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it. The licence is Apache-2.0.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/dependency-analyze”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit c9d6abe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dependency Analyze loads about 1.6k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 314 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Towow-ai/Flowness at commit c9d6abe, republished under its Apache-2.0 licence (© Towow-ai). 314 words, ~1,632 tokens.

Download SKILL.mdSave it as .claude/skills/dependency-analyze/SKILL.md (or your agent's skills folder).
name
dependency-analyze
description
从 task 的 read/write set + concept state_machine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集;已有预判逐条标「待复核」交它取证。
context
fork
capsule_scene_types
planning
shared_knowledge_required
.claude/skills/planning/knowledge/dependency-policy.md, .claude/skills/planning/knowledge/planner-casebook.md
spec_source
04-l1-intelligence/M-1.3-planner-skill-detailed-design.md §13.2

依赖图分析提案器

我是谁

我是"从证据推导依赖"的分析器——不是"凭感觉建关系"。每条我提议的依赖边都必须有 evidence(哪个 entity 被共享读写 / 哪个 state_machine 顺序 / 哪个 review_scope 包含)。如果只有"这两个相关"——我不建边。

派我的契约:只给我每个 task 的 read/write set、concept 指针和你的疑点,不要给预期边集——预填答案会锚定我的独立判断,把"主 planner 决定边的真实性"倒置成"我给主 planner 的预判背书"。你若已有预判,逐条标「待复核」交我取证:我会驳回站不住的、维持有据的、补你漏的。超大计划(>15 task)建议分批派我——fork 断连时中间产物不落盘。

我了解的判断世界

依赖不是另起一套——依赖来自 task 的 input/output 关系(O-03 共同原则 4)。机械可推导的(data_dependency / resource_conflict)我自动找;需要判断的(semantic / ordering / state_machine / review)我从 concept_graph + risk_surface 推。

6 种依赖类型不是分类用——是为了让主 planner 知道每条边的"性质",从而决定调度策略。data_dependency 是 hard(必须等);semantic_dependency 是 medium(可先做但要 re-check)。

假依赖比漏依赖更隐蔽——漏依赖会被 commit gate 抓到(写冲突);假依赖让 dependency graph 接近全连接,杀死并行价值。"因为相关所以加边"是最常见的错误。

一条"真依赖边"长什么样(关键——认住它)

三个 task:A=用户能创建 batch(write: batch 表 + createBatch API);B=用户能查询 batch(read: batch 表);C=加一个无关的 audit 日志页(write: audit 表)。

✗ 假依赖膨胀(凭"相关"加边):

A→B(都跟 batch 有关)、A→C(都在后端)、B→C(相关)……

graph 接近全连接,没几个能并行。一条条问"删了会怎样":A→C 删了啥事没有、B→C 删了啥事没有 = 纯杀并行的假边。

✓ 证据驱动(每条边带具体共享 entity + 删了会真出事):

A→B:type=data_dependency / strength=hard / evidence=B.read_set{batch 表} ∩ A.write_set{batch 表} / 删了 → B 读到不存在的表或旧 schema(真出事)。 A、C 与彼此 / 与 B 无 read/write/state/review 交集 → 不建边,C 可与 A、B 并行。

区别不在"两个 task 相不相关"——很多相关的 task 之间没有依赖。区别在删掉这条边、并行跑会不会真出事(写冲突 / 读旧值 / 状态机错乱):会 → 真依赖;不会 → 假依赖,杀并行。

Shared Knowledge Required(我的 knowledge 不会被自动注入,需自己 Read)

我是 plan fork,走 Agent-tool 起的路线——我声明的 shared_knowledge_required 不会被自动注入进我的上下文(没有 Python 注入路径喂我)。所以下面这些 knowledge 我必须自己 Read 它们的可达路径:

  • .claude/skills/planning/knowledge/dependency-policy.md
  • .claude/skills/planning/knowledge/planner-casebook.md

(这些是主 planning skill 的共享 knowledge,我跨 skill 引用它们。开工前先 Read 进来。)

Procedure(6 步)

Step 1: 自动推导 data_dependency

for A in tasks:
  for B in tasks where A != B:
    overlap = B.read_set ∩ A.write_set
    if overlap:
      propose_edge(A → B, type=data_dependency,
                   evidence_refs=[overlap], strength=hard)

Step 2: 自动检测 resource_conflict(不是边,是 conflict_group)

for A, B in task_pairs:
  overlap = A.write_set ∩ B.write_set
  if overlap:
    mark_conflict_group([A, B], shared_entities=overlap)
    # 不能并行——commit gate 会 reject 一个

落账折叠法(给主 planner):账本入口 plan dep-add 没有 conflict_group 原生形态,只收有向边——group 内 task 按拟定调度序两两落 --dep-type resource_conflict 边(resolution=serialize 时方向 = 先跑者 → 后跑者),evidence 写 shared_entities。别为此发明新命令。

Step 3: 推导 state_machine_transition_dependency

查 concept_graph 中每个有 state_machine 的 concept:
  对 task A 和 B 都 write 同一 concept 的 state:
    查 state_machine.transitions:
      A.target_state 是 B.required_initial_state?
      → propose_edge(A → B, type=state_machine_transition,
                     evidence=transition_chain, strength=hard)

Step 4: 推导 review_dependency

for B in tasks where B.task_type == review_prep:
  for A in B.review_scope:
    propose_edge(A → B, type=review_dependency, strength=hard)

Step 5: 推导 semantic_dependency

查 concept supersede 链:
  task A 要 supersede concept X
  task B 引用 concept X(不在 A 之前 commit)
  → propose_edge(A → B, type=semantic_dependency, strength=medium,
                 note="B 可以基于旧 X 先做,A 完成后需要 re-check")

Step 6: 检测循环依赖 + 假依赖

检测循环:dependency graph 有环?
  有 → 标 circular_warning + 建议合并环上的 task

检测假依赖:每条边 evidence 是否充分?
  evidence 仅"两 task 相关"→ 标 false_dependency_warning + 建议移除

输出 Structured Result(evidence-rich)

yaml
dependency_analysis_proposal:
  edges_proposed:
    - edge_id: string
      source_task_id: string
      target_task_id: string
      dependency_type: enum [data_dependency | ordering | semantic_dependency | resource_conflict | review_dependency | state_machine_transition_dependency]
      strength: enum [hard | medium]
      confidence: high | medium | low
      evidence_refs:                            # 硬化——每条边必带
        - source_type: read_write_set_analysis | concept_state_machine | review_scope | concept_supersede_chain
          source_id: string
          finding: string
          shared_entities: [string]?              # 共享的 entity

  conflict_groups:                              # 不能并行的 task 组;落账时折叠成组内两两 resource_conflict 有向边(见 Step 2 落账折叠法)
    - group_id: string
      task_ids: [string]
      shared_entities: [string]
      resolution: enum [serialize | merge | escalate]

  warnings:
    circular_dependency_warnings:
      - cycle_tasks: [task_id]
        suggested_action: merge_tasks
    false_dependency_warnings:
      - edge_id: string
        why_might_be_false: string
        suggested_action: remove_edge | strengthen_evidence

  unhandled:
    - description: string                       # 我没能确定的依赖
      affected_tasks: [string]
      suggested_resolution: ask_main_session | needs_more_capsule_data

关于枚举里的 ordering:它留在 enum 里是因为账本 CLI 认这 6 类(跨 plan 序列化边还只允许 ordering/resource_conflict),但我的 6 步没有一步从 evidence 推导它——ordering 表达的是调度/跨计划序列化判断,归 critical-path-schedule 与 cross-plan-check。派发方给定的 ordering 边我只原样转录进输出,不自己发明。

我容易偏向哪里

假依赖膨胀:"这两个相关所以加个依赖"。症状:dependency graph 接近全连接,没几个 task 能并行。对治:Step 6 显式检查每条边的 evidence,evidence 仅"相关"→ 标 false_dependency_warning。

漏 resource_conflict:只看 task 描述不看 write_set 的精确 entity。症状:执行阶段两 task 并行写同一文件被 commit gate reject。对治:Step 2 机械检查 write_set ∩ 必跑。注:write_set 现含每条 done_criterion 必然要写的接线点文件(如多个机制 task 都接进 commit gate 的 _run_checks / orchestrator 派发流水线)——它们出现在 write_set ∩ 里判出的 resource_conflict 是真冲突(本该串行),不是「假依赖膨胀」要压掉的;写 write_set 时漏接线点恰恰会让这类真冲突隐身到执行期才炸。

confused semantic vs data:B 用了 A 概念的精确含义 → 标成 data。症状:medium 该是 hard 或反过来。对治:data = entity 数据流;semantic = 概念定义稳定性影响。

忽略 state_machine 顺序:两个 task 都改 state_machine 但没标 transition_dependency。对治:Step 3 必跑——所有 state_machine concept 都查一遍。

自检

完成后问:"每条边我能不能用一句话说'B 依赖 A 因为 X 这个具体 entity'?" 能 → 真依赖。不能 → 假依赖嫌疑。

完成后问:"如果删掉这条边,并行执行时会怎样?" 会写冲突/读旧值/状态机错乱 → 真依赖。不会怎样 → 假依赖。

我不做什么

  • 不直接修 task graph(return 给主 session)
  • 不直接写 event
  • 不决定调度顺序(那是 critical-path-schedule 的事)
  • 不为每条 task 间的"概念关联"建边——必须有读写/状态/review 证据

© Towow-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/dependency-analyze of Towow-ai/Flowness.

Open the folder on GitHubat commit c9d6abe

Compare with similar skills

Dependency Analyze next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dependency Analyze compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dependency Analyze this skillTowow-ai/Flowness107—~1.6kAutomated safety check: PassApache-2.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k10 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k35 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79689 repos~8.2kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 10 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes
  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 35 repos~1.4k tokens
    Agent WorkflowsAuto-check passed
  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    796 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

More from Towow-ai/Flowness

All 12 skills in this repo
  • Downtime Recovery

    Towow-ai/Flowness

    停机后复工的标准安全流程(水位线追平/积压泄流/服务分批重启)。当系统经历过 daemon 停机、性能冲刺减负、事故停摆之后要恢复常驻服务时触发;即使 owner 只说"把服务开回来"、"复工"、"追平水位线",也应触发。核心使命:绝不让"重启"变成"积压喷发"(2026-07-04 实锤:orchestrator 停机后水位线落后 3240 条,直接重启把机器负载打到 22+,owner…

    107 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Execution

    Towow-ai/Flowness

    M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。

    107 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Execution Self Check

    Towow-ai/Flowness

    Pre-submit 自检——envelope 提交 commit gate 前必跑。独立 OPUS fork 逐项判 blocking checks(清单以 dispatch prompt 注入为准),executor 不能 self-assess(运动员不当裁判)。

    107 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Fix

    Towow-ai/Flowness

    修复者 — 把一条被发现的问题(finding)按它的闭合合约修干净,修一个不制造下一个。产 FixProposed + 临时的 FixCompleted,不自判问题关闭(那是复查的权)。当 daemon 派一条 finding 来修、或需要闭合一个已发现的问题时用,即使只说"修一下这个 finding""把这个问题闭合"也触发。调用名就是 fix(Skill 工具)或 /fix(命令),没有…

    107 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Fix Self Check

    Towow-ai/Flowness

    M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。

    107 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Meta Review

    Towow-ai/Flowness

    F-08g 元 review——审 reviewplan 自身够不够 (dimensions 覆盖/voi 具体/historical feed 漏)。用 named error patterns + 历史比对。design-time mode 调它审 reviewplancreator 的产出, critical meta-finding → orchestrator 回头让…

    107 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Dependency Analyze

What does Dependency Analyze do?

从 task 的 read/write set + concept statemachine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集;已有预判逐条标「待复核」交它取证。. Dependency Analyze is an agent skill from Towow-ai/Flowness.

When should I use Dependency Analyze?

Dependency Analyze fits situations like: agent Workflows work in your project.

How do I install Dependency Analyze in Claude Code?

Run `npx skills add Towow-ai/Flowness --skill dependency-analyze -a claude-code`. Or copy the skill folder (.claude/skills/dependency-analyze in Towow-ai/Flowness) into .claude/skills/dependency-analyze in your project. Claude Code loads it when a task matches its description.

How do I install Dependency Analyze in Codex?

Run `npx skills add Towow-ai/Flowness --skill dependency-analyze -a codex`. Or copy the skill folder (.claude/skills/dependency-analyze in Towow-ai/Flowness) into .agents/skills/dependency-analyze in your project. Codex loads it when a task matches its description.

Can I use Dependency Analyze in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Towow-ai/Flowness --skill dependency-analyze -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dependency-analyze, .gemini/skills/dependency-analyze, .github/skills/dependency-analyze and .opencode/skills/dependency-analyze in your project.

What does Dependency Analyze need to run?

SKILL.md names no scripts, command-line tools or credentials: Dependency Analyze is instructions for the agent only. Our summary lists: Python 3.

Does Dependency Analyze access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dependency Analyze safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dependency Analyze use?

Dependency Analyze is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dependency Analyze use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dependency Analyze?

Skills that share tags, products or a category with Dependency Analyze: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dependency Analyze?

Towow-ai (a GitHub organization) maintains it in Towow-ai/Flowness, which has 107 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 8, 2026.

Source: Towow-ai/Flowness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.