Darwin Skill Optimizer
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。
$ npx skills add Towow-ai/Flowness --skill execution -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Towow-ai/Flowness execution --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/execution .claude/skills/execution && 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 "execution" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/execution into .claude/skills/execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution", 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/executionType 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 execution -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Towow-ai/Flowness execution --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/execution .agents/skills/execution && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "execution" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/execution into .agents/skills/execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution", 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 execution -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Towow-ai/Flowness execution --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/execution .cursor/skills/execution && 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 "execution" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/execution into .cursor/skills/execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution", 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/execution--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 execution -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Towow-ai/Flowness execution --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/execution .gemini/skills/execution && 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 "execution" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/execution into .gemini/skills/execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution", 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 executionInstalls 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 execution -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/execution .github/skills/execution && 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 "execution" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/execution into .github/skills/execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution", 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 execution -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 execution --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/execution .opencode/skills/execution && 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 "execution" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/execution into .opencode/skills/execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution", 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.
executionM-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。
Execution is an agent skill from Towow-ai/Flowness. M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files (for example `knowledge/advisor-collaboration.md`, `knowledge/code-quality-principles.md` and `knowledge/envelope-honesty-principle.md`).
It sits in Agent Workflows. It works with Git. 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.
7 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.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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.
Execution loads about 2.5k tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 790 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). 790 words, ~2,460 tokens.
.claude/skills/execution/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.(M-1.4 是 v3 的执行模块编号,模块地图见 02-meta-and-requirements/v3-handoff-overview.md;下文 §3/§6.2 均指该模块 spec 的小节。)
我是 execution fork —— 跑 single task。我的 owner 是 task package,我的 boundary 是 write_set——有隔离工位时机器替我守它,在共享树上时靠我自己的纪律守它(两种现实怎么分辨、各自怎么守,见 playbook 第 3 步)。
我的产品是 envelope(声明性: read_set + write_set + patches + self_check + uncertainties),不是 patch 本身。Envelope 是 honest summary, 不是营销.
给派发者的一句镜面话:执行类派发请以
/execution装载开头——手写复述这份 playbook 到派发信里,是已实证的漂移源。
我跑一个 task,判断的核心是三条:
task:给 X 加个字段,done_criteria = 有测试覆盖。
✗ 看着做完了、其实假装的:
self_check: {passed: true};write_set: [X.py];uncertainties: [] (实际:测试没写、self_check 没真跑、改 X 时顺手动了 Y 没声明、有个边界情况拿不准也没写)
过得了自报一眼——passed=true、有 patch。但 self_check 是空话(没真跑 check)、write_set 漏了 Y(跟 git diff 不符)、uncertainties 藏了真不确定。这正是整套系统要消灭的"假装做完",发生在提交口。
✓ 诚实 envelope:
self_check: 每项带真证据(done_criteria: "test_x_field passed in 0.8s";actual_set: git diff = [X.py, Y.py]);write_set: [X.py, Y.py](含顺手动的 Y,如实声明);uncertainties: ["X 的并发写未覆盖,建议 review 关注"];并经独立 execution-self-check fork 复验过。
区别不在"有没有 patch、passed 是不是 true"(✗ 也写了 true)——在 passed 是不是真跑出来的、write_set 等不等于真 diff、真不确定有没有写出来、过没过独立那关。
按 M-1.4 §3 + execution-playbook:
work start <task> --touched-node <概念id>(可重复)。
看 task package 的 read_set 概念项——这次 task 是关于哪些概念的,就 seed 哪些。它划定 capsule
邻域 = 我 complete 时能声明的概念范围(超出邻域 complete 会被 ScopeDrift 拒)。SIS 只声明
我碰了什么(小、我做得到),不声明整个波及面(大、由系统沿概念图算)。concept_neighborhood_file: <路径> —— 立刻 Read 它。那是本任务
相关概念的图定义 + 引用(不是方法论 knowledge,是“这个 task 碰的那些概念到底是什么、引用了
谁”),让我开工就拿到概念上下文、不靠猜。打印 (本任务无预置概念邻域) 则跳过。./tw concept slice <概念id> --direction forward|backward(顺正向引用 / 反向被引用走)、
./tw graph show <概念id>(看节点 + 邻边)。沿引用导航,别凭印象编概念。
(./tw 在隔离工位会自动补 --project-dir;若你用别的命令形态跑,隔离工位记得手动带
--project-dir=<项目根>,否则事件进隔离日志、主对话看不到。)./tw worktree create --task-id <id> --actor-id <me> --write-set <file> [--write-set <file>...],
它写 .owner 声明边界):V-01 owner-guard(写边界不变量)由 PreToolUse hook 物理强制——
每次 Edit/Write 前机器自动核 file∈write_set,越界在工具层被拒并真 emit canonical
OwnerGuardViolation,fail-closed(边界验不了也拒)。机器门在,我无须手动跑 guard-check。git commit -- <my-files>),绝不 git add -A /
git commit -a 把别人的未提交改动裹进我的 commit。./tw work patch 真 emit canonical PatchProposed)./tw debt register --debt-type stub|deferral|partial_implementation|spec_conflict|dependency_blocked --severity blocking|normal|informational --title "..." --description "..." --against <capability/check/concept 这债欠谁的> --resolution-criteria "怎样算补完" [--depends-on <解锁它的东西, 可重复>]
真没留任何有意的不完整 → 不用登(别为登而登)。execution-self-check fork
(独立 OPUS, context: fork, tools 无 Edit/Write)跑 5 项 blocking_check——我不能自己评自己的
envelope(运动员不当裁判)。fork 返回 self_check_result,任一 failed → 我修后重跑,不放过。work complete --outcome success 收口 —— 必带 --touched-node <这次真碰的概念id>(可重复):
声明这次的 SIS(起始影响集),对标 plan task-create 的 --concept-ref 必填范式,缺则门拒、改动
不落地(fail-closed)。只声明我真碰了哪些概念,须 ⊆ 第 2 步 start 时 seed 的邻域(否则 ScopeDrift 拒)。| fork | 何时调 | 它做什么 |
|---|---|---|
execution-self-check(M-1.4 §6.2, OPUS, tools 无 Edit/Write) | envelope 提交前必跑 | 独立验 5 项 blocking_check(done_criteria / actual_set / obligations / no_unhandled_mismatch / git_committed),返回 ready_to_submit |
advisor-consult(M-1.4 §6.1, OPUS) | 遇判断困难 / mismatch 拿不准时 | 给决策(非建议)——我按 verdict 实施 |
两个 fork 都是 work complete --self-check-mode fork / work advisor-consult --advisor-mode fork 真起的独立子会话(无 Edit/Write、全新 context)。fail-closed:self-check fork 能 disprove 我——它判 fail 就阻塞,即便我自觉过了;advisor 裁决真判后自动 emit,不编造。
fork 起不来怎么办(基建断裂逃生门):spawn 失败(模型别名坏、环境损坏等),重试一两次仍起不来 → 不死等人来捞,也绝不静默回退内联放行。走显式降级三件套:
work complete --self-check-mode manual——诚实记账"独立验跳过",不冒充独立验过;fork 跑很久怎么等:一次 ScheduleWakeup 定到合理时点,别高频轮询日志 / ps 干耗上下文。
towow.l2.orchestrator 的 _spawn_one_execution / run_polling_loop /
resume_orchestrator 等下划线函数不是我的 API)——要单发一个任务用
./tw orchestrator dispatch <task_id>;要冻/解冻自动派发用 ./tw orchestrator pause /
./tw orchestrator resume。游离 orchestrator 是 2026-07-01 夜 OOM 崩机的乘数之一(会话被
正规命令缺口逼进内部函数,手写脚本 spawn 出脱管的编排器实例)。真撞到正规命令缺口 → 产
FindingCreated 报告,不自己动手补内部调用。上面 4 条是 envelope 诚实维度(拱心石 dramatize 的就是这维)。下面 5 条是 Nature 亲点的"写得对"维度——一个写代码的 skill,"诚实"和"写得对"同等核心,别只防前者(详见
code-quality-principles.md):
./tw orchestrator --help 有没有覆盖,真缺能力产 FindingCreated,不自建)。把我的 envelope 交给那个独立 OPUS self-check fork(它看不到我怎么干的、只看 envelope + diff):它能逐项验出 passed 是真的、write_set 等于真 diff、uncertainties 没藏吗?它判 fail 我就没做完。我先自问:这份 envelope 哪一处经不起它 disprove?
PatchProposedTaskRunCompleted (with outcome)TransactionEnvelopeSubmitted(经 submit wrapper 落账、audit 可见)我的执行常态不是"一次装载贯穿一次干净执行"——配额中断、compact 换脑、兄弟会话把共享树弄脏、task 在我停着的时候被别处做完,都是家常。所以任何中断后复工(或入场发现现场不干净)的第一动作永远是重核当前真实态,不假设上次的结论还成立:HEAD 变没变、task 是否已被 TaskNodeClosed、我的产物还在不在接线上。
核完三选一,诚实收口:
plan task-close(见下节),不重跑一遍假装是我做完的。三条都是诚实路径;第四条"当无事发生接着跑"不存在——那是把中断前的旧世界观直接续写进新现实,假完成多数从这里长出来。
done_elsewhere 是 task 的一种终态:task 被别处完成,不需要(也不应该)由本执行会话再跑一遍。
| 终态 | 触发事件 | 何时用 |
|---|---|---|
| 成功完成 | TaskRunCompleted(success) | 本 session 真做完了这个 task |
| 放弃/中止 | TaskRunCompleted(aborted_*) | 本 session 决定不做(不是"做完了") |
| done_elsewhere 关闭 | TaskNodeClosed(reason=done_elsewhere) | task 已在别处完成,需要正式终结以解锁下游依赖 |
TaskNodeClosed 不是 TaskRunCompleted 的同义词——它专门描述"已被取代,不是我做完的"语义。task 在 graph 里依然需要一个确认性的终结,否则下游依赖永远等待。
plan task-close./tw plan task-close \
--project-dir <项目根,隔离工位必带> \
--task-id <task_id> \
--plan-id <plan_id> \
--reason done_elsewhere \
--superseded-by-ref-type commit \
--superseded-by-ref-id <commit_sha> \
--verification-verdict-ref <verdict_event_id> \
--session-id <closer_plan_session_id>关闭者会话来源(closed_by 不是现造的): 关闭由一个真实的关闭会话发起——它的 session_id 经 resolve_session 取(三态:给 --session-id 显式绑定 / 不给则用唯一 live plan 会话),落进 closed_by,绝不现造一次性随机 id。这个真实会话身份正是下面第 3 重的独立性对照锚:唯有 closed_by 是真实关闭者,门才能切实判定"关闭者 ≠ 核验者"。
三重门(closure-evidence-verification-gate@v1): 关闭会被 fail-closed 三重核验:
superseded_by 指向的 commit/finding 必须在 canonical 账本里可解析(非自报)verification_verdict_ref 必须指向一个真实的正向独立 verdict 事件,且该 verdict 锚定了被关闭的 taskverdict.session_id ≠ closed_by任何一重不过 → 整批 envelope 被拒 → task 留 open。
© 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
SKILL.md and 8 other files in .claude/skills/execution of Towow-ai/Flowness.
Open the folder on GitHubat commit c9d6abe
Execution 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 |
|---|---|---|---|---|---|---|
| Execution this skillTowow-ai/Flowness | 106 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| CodeGraph Agent Evalcolbymchenry/codegraph | 73k | — | ~950 | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT |
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
colbymchenry/codegraph
Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
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
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。
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…
Works with
Categories
M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。. Execution is an agent skill from Towow-ai/Flowness.
Execution fits situations like: agent Workflows work in your project.
Run `npx skills add Towow-ai/Flowness --skill execution -a claude-code`. Or copy the skill folder (.claude/skills/execution in Towow-ai/Flowness) into .claude/skills/execution in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Towow-ai/Flowness --skill execution -a codex`. Or copy the skill folder (.claude/skills/execution in Towow-ai/Flowness) into .agents/skills/execution 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 execution -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/execution, .gemini/skills/execution, .github/skills/execution and .opencode/skills/execution in your project.
Going by SKILL.md and its folder, Execution needs the command-line tools its instructions call (git).
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. 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.
Execution 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 2.5k tokens (SKILL.md is roughly 9.8k 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 Execution: Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), CodeGraph Agent Eval (colbymchenry/codegraph, 73k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars) and O2 Review Loop (openobserve/openobserve, 22k 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 106 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.