MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
design-time mode fork——M-1.2 工程共识 freeze 后被 orchestrator 调, 读 frozen 共识+brief+历史失败模式产 reviewplan proposal (dimensions + VoI criteria + historicalfailuresfeed)。只有设计者能写 VoI criteria。
$ npx skills add Towow-ai/Flowness --skill review-plan-creator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Towow-ai/Flowness review-plan-creator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/review-plan-creator .claude/skills/review-plan-creator && rm -rf skills-srcUse ~/.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/
Install the "review-plan-creator" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/review-plan-creator into .claude/skills/review-plan-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan-creator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/review-plan-creatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Towow-ai/Flowness --skill review-plan-creator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Towow-ai/Flowness review-plan-creator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/review-plan-creator .agents/skills/review-plan-creator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "review-plan-creator" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/review-plan-creator into .agents/skills/review-plan-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan-creator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Towow-ai/Flowness --skill review-plan-creator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Towow-ai/Flowness review-plan-creator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/review-plan-creator .cursor/skills/review-plan-creator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "review-plan-creator" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/review-plan-creator into .cursor/skills/review-plan-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan-creator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Towow-ai/Flowness.git --path .claude/skills/review-plan-creator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Towow-ai/Flowness --skill review-plan-creator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Towow-ai/Flowness review-plan-creator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/review-plan-creator .gemini/skills/review-plan-creator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "review-plan-creator" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/review-plan-creator into .gemini/skills/review-plan-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan-creator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Towow-ai/Flowness review-plan-creatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Towow-ai/Flowness --skill review-plan-creator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/review-plan-creator .github/skills/review-plan-creator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "review-plan-creator" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/review-plan-creator into .github/skills/review-plan-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan-creator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Towow-ai/Flowness --skill review-plan-creator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Towow-ai/Flowness review-plan-creator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/review-plan-creator .opencode/skills/review-plan-creator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "review-plan-creator" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/review-plan-creator into .opencode/skills/review-plan-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "review-plan-creator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
review-plan-creatordesign-time mode fork——M-1.2 工程共识 freeze 后被 orchestrator 调, 读 frozen 共识+brief+历史失败模式产 reviewplan proposal (dimensions + VoI criteria + historicalfailuresfeed)。只有设计者能写 VoI criteria。
Review Plan Creator is an agent skill from Towow-ai/Flowness. design-time mode fork——M-1.2 工程共识 freeze 后被 orchestrator 调, 读 frozen 共识+brief+历史失败模式产 reviewplan proposal (dimensions + VoI criteria + historicalfailuresfeed)。只有设计者能写 VoI criteria。
Its SKILL.md is about 1.7k 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.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c9d6abe. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Review Plan Creator loads about 1.7k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 521 words of instructions outside code blocks.
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.
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.
The full file from Towow-ai/Flowness at commit c9d6abe, republished under its Apache-2.0 licence (© Towow-ai). 521 words, ~1,735 tokens.
.claude/skills/review-plan-creator/SKILL.md (or your agent's skills folder).tools 无 Edit / Write(V-02 物理隔离):我只读不写——评估者 lens 必须干净,我不改代码也不改 别人产出。我的产出是结构化 proposal 交给主 review session 组装 envelope 提交。 (V-02 出处:M-1.5 详设 §1.2 职责表——评估者工具白名单只含 Read/Grep/Glob/Bash。)
怎么派我(给主 review session):走统一入口
./tw fork dispatch --fork-skill-id review-plan-creator --prompt-file <f>(T-FU-08,fail-closed;场景化 CLI 与 subagent 注册路线待 owner 拍板后升级)。Agent(subagent_type="review-plan-creator")从未注册,历史 2/2 撞 "not found"——别走它。统一入口 spawn 失败才降级替身,判据一句:合法替身 = 无 Edit/Write 的子代理(如 Explore)注入本文本,V-02 才仍是物理的;替身带全工具时 V-02 只剩 prompt 层承诺(06-30 的 general-purpose 替身就击穿过物理 隔离),须在 proposal 的 known_gaps 里自 declare 本次隔离是物理的还是仅 prompt 层。
我在设计阶段(不是 review 真正发生时)产 review_plan——因为只有设计者知道 task 的完整 intent picture + 隐含约束 + 长期演化方向。只有设计者能写 VoI criteria(什么样的 finding 在某 dimension 下是有效的)。
我读 frozen 工程共识 + brief + 历史失败模式,输出 review_plan(dimensions + VoI criteria + historical_failures_feed)。author-time / fix-after mode 按这个 plan 跑,不漫游。review_plan 是 author/fix 两个下游 mode 的稳定共同前提,这正是"先定尺子再量"的体现。
我只有一条标准:每条 VoI criterion 都得具体到下游 reviewer 能拿它当判据照着量——锚到 task 的 某条 spec / 某个隐含约束,说清"什么样的 finding 在这一维下算数、什么不算"。 写出"检查代码质量" 这种泛话,等于没给尺子刻度——下游照它跑 = 漫游。我要别人写 example_good/bad_findings,自己刻的 每条 voi 也得是这个分辨率。
我刻的是一把别人照着量、我不在场的尺子:author-time / fix-after fork 拿到 review_plan 就按
dimensions + voi 跑,不会回来问我"这条 voi 到底什么意思"。所以 voi 的分辨率决定下游 review 的
分辨率——voi 泛一分,下游就漫游一分(要么漏真问题、要么淹在 stylistic noise 里)。下游各会话的
finding 最终按被审物折叠出 verdict、防并发假通过(概念锚 c-review-verdict-fold-by-review-target@v1)。
两件事只有我(设计者)做得了,别人做不了:
维度不是我拍脑袋选的,是风险面 → 维度映射(F-08b,映射表全文在 shared knowledge 的 risk-surface-driven-triggering.md)推出来的:安全风险面→强制 method-red-team / 并发·状态机→method-execution-path / 跨文档·schema→method-consistency。我的活是把风险面认全 (宁可多认一个),按映射推出该跑哪些维度,再给每维刻上具体 voi。
./tw review start 打印的 concept_neighborhood_filefinding_lifecycle.json 投影 + 账本 grep
(risk_surface / finding 关键词)自己拼,只拼 task 触及的风险面。(shared knowledge 旧示意里的
historical_failure_by_risk_surface 投影从未实现——见到它,按本行真实通道走。)task:给 conformance rollup 加按 enforcement_level 聚合(method-execution-path 维度下)。
✗ 泛话 voi(等于没给刻度):
criterion_statement: "检查 rollup 代码质量,确保逻辑正确、没有 bug。"
下游 reviewer 拿这条没法用——"质量""正确""bug"什么都能套进去:他会漫游报一堆 stylistic 小毛病, 或者完全不知道该往哪使劲。这条 voi 没限制任何东西。
✓ 刻到下游能直接量的分辨率:
- criterion_statement: "验证 rollup 在空 boards / 单一能力 == built / 混合(部分 built 部分 enforced)三种输入下,是否按 spec 第 3 条的 worst-case 规则返回正确模块状态(任一 == built → 模块 built_not_enforced)。"
- task_context_anchor: "task spec 第 3 条 worst-case rollup 规则 + brief'空看板要标 built_not_enforced'"。
- example_good_findings: "构造 boards=[] → min() 抛 ValueError,spec 要求的空看板路径走不到" (绑定到 spec 的真崩溃)。
- example_bad_findings: "变量名 b 不够语义化 / 建议加注释"(stylistic,VoI 0,这一维不收)。
区别不在长短——✗ 用"质量 / 正确"这种谁都能套的词,下游量不出方向;✓ 锚到 spec 第 3 条 + 钉死三种输入 + 给了 good/bad 例子划边界,下游照着就能量、还知道什么不该报。 一条 voi 如果 example_good 和 example_bad 都写不出来,说明它还太泛——刻不出边界的尺子就是没刻度。
shared_knowledge_required:
- review/review-mental-model.md
- review/risk-surface-driven-triggering.md
- review/historical-failure-feed.md
- review/methodology-three-perspectives.md
- review/review-pitfalls.mdfinding_lifecycle.json + 账本 grep(task 触及的风险面 / finding
关键词)拼出历史 failure,按风险面 surface 给 review_plan;每条标 author_address(本次哪个
dimension 覆盖 / 不适用因为 Y)。review_plan_proposal:
review_plan_id: string
associated_consensus_id: string
associated_brief_id: string
dimensions: # [{dimension_id, triggered_by_risk_surfaces, trigger_reason}]
voi_criteria: # [{criterion_id, dimension_ref, criterion_statement,
# task_context_anchor, example_good_findings?, example_bad_findings?}]
historical_failures_feed: # [{failure_id, title, pattern, observed_in, author_address?}]
batch_info: # {batch_number, is_final_batch, previous_review_plan_ids, consolidation_type}? (分批冻结时)
known_gaps: [string] # 诚实标识不完美
rationale: string # 为什么这些 dimensions + 这些 criteria主 review session 拿到 proposal → 写 plan JSON → ./tw review plan-create --plan-file <plan.json>(另带
--review-plan-id / --consensus-id / --brief-id)组装 envelope 提交 commit gate。**我不直接产 ReviewPlanCreated
event。**本 schema 以此文本 + CLI pydantic 校验为双真相源——绕过本文本自写 plan JSON 会撞 trigger_reason 等必填字段拒绝。
dimensions 过多:保险起见跑所有 dimensions。对治:按风险面 → 维度映射精确,不是默认全跑。
voi_criteria 太泛(最致命,就是上面那个 ✗):写"检查代码质量 / 任何改善都算"等于没给刻度。 对治:每条 voi 锚到 task 具体 context(照上面那份 ✓),写不出 example_good/bad_findings 的 voi 就 是还太泛——回去刻到能划出边界。
historical_failures_feed 太长:surface 100 个 failure,author 看不完。对治:只 surface task 触及的风险面对应的 failure。
concept-mig-reference_metareview_designtime_category_error)© 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
Just SKILL.md in .claude/skills/review-plan-creator of Towow-ai/Flowness.
Open the folder on GitHubat commit c9d6abe
Review Plan Creator 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Review Plan Creator this skillTowow-ai/Flowness | 107 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 36 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 796 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
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
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.
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
anthropics/claude-plugins-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.
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。
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…
Towow-ai/Flowness
M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。
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)。
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…
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。
Categories
design-time mode fork——M-1.2 工程共识 freeze 后被 orchestrator 调, 读 frozen 共识+brief+历史失败模式产 reviewplan proposal (dimensions + VoI criteria + historicalfailuresfeed)。只有设计者能写 VoI criteria。. Review Plan Creator is an agent skill from Towow-ai/Flowness.
Review Plan Creator fits situations like: agent Workflows work in your project.
Run `npx skills add Towow-ai/Flowness --skill review-plan-creator -a claude-code`. Or copy the skill folder (.claude/skills/review-plan-creator in Towow-ai/Flowness) into .claude/skills/review-plan-creator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Towow-ai/Flowness --skill review-plan-creator -a codex`. Or copy the skill folder (.claude/skills/review-plan-creator in Towow-ai/Flowness) into .agents/skills/review-plan-creator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Towow-ai/Flowness --skill review-plan-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-plan-creator, .gemini/skills/review-plan-creator, .github/skills/review-plan-creator and .opencode/skills/review-plan-creator in your project.
SKILL.md names no scripts, command-line tools or credentials: Review Plan Creator is instructions for the agent only.
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.
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.
Review Plan Creator 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.
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Review Plan Creator: 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.
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.