CCPM Project Management
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
用户说“修复这个可复现 bug”或要求根据失败报告修代码时使用。执行红灯测试、根因定位、最小修复、独立审查和回归;尚未确认的问题先用 cm-test,新功能和架构重设计转交 cm-prd。
$ npx skills add kingxiaozhe/cm-workflow --skill cm-fix -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kingxiaozhe/cm-workflow cm-fix --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/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cm-fix .claude/skills/cm-fix && 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 "cm-fix" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/cm-fix into .claude/skills/cm-fix/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cm-fix", 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/kingxiaozhe/cm-workflow/tree/main/skills/cm-fixType 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 kingxiaozhe/cm-workflow --skill cm-fix -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kingxiaozhe/cm-workflow cm-fix --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cm-fix .agents/skills/cm-fix && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cm-fix" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/cm-fix into .agents/skills/cm-fix/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cm-fix", 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 kingxiaozhe/cm-workflow --skill cm-fix -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kingxiaozhe/cm-workflow cm-fix --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cm-fix .cursor/skills/cm-fix && 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 "cm-fix" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/cm-fix into .cursor/skills/cm-fix/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cm-fix", 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/kingxiaozhe/cm-workflow.git --path skills/cm-fix--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 kingxiaozhe/cm-workflow --skill cm-fix -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kingxiaozhe/cm-workflow cm-fix --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cm-fix .gemini/skills/cm-fix && 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 "cm-fix" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/cm-fix into .gemini/skills/cm-fix/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cm-fix", 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 kingxiaozhe/cm-workflow cm-fixInstalls 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 kingxiaozhe/cm-workflow --skill cm-fix -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cm-fix .github/skills/cm-fix && 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 "cm-fix" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/cm-fix into .github/skills/cm-fix/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cm-fix", 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 kingxiaozhe/cm-workflow --skill cm-fix -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kingxiaozhe/cm-workflow cm-fix --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cm-fix .opencode/skills/cm-fix && 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 "cm-fix" agent skill from https://github.com/kingxiaozhe/cm-workflow/tree/main/skills/cm-fix into .opencode/skills/cm-fix/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cm-fix", 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.
cm-fix用户说“修复这个可复现 bug”或要求根据失败报告修代码时使用。执行红灯测试、根因定位、最小修复、独立审查和回归;尚未确认的问题先用 cm-test,新功能和架构重设计转交 cm-prd。
Cm Fix is an agent skill from kingxiaozhe/cm-workflow. 用户说“修复这个可复现 bug”或要求根据失败报告修代码时使用。执行红灯测试、根因定位、最小修复、独立审查和回归;尚未确认的问题先用 cm-test,新功能和架构重设计转交 cm-prd。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/cross-boundary-debugging.md`, `references/js-host.md` and `references/test-extension.md`).
It sits in Product & Project Management, covering PRD writing. The repository describes itself as: Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors. The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 82d43f0. 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:
python3nodeFrom 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.
Cm Fix loads about 2.5k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 25 tokens; SKILL.md has 584 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 kingxiaozhe/cm-workflow at commit 82d43f0, republished under its MIT licence (© kingxiaozhe). 584 words, ~2,531 tokens.
.claude/skills/cm-fix/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.执行前读取 ../../runtime/project-context.md、../../runtime/orchestration.md、
../../runtime/review.md、../../runtime/model-efficiency.md 与
../../runtime/logging.md。Codex 入口为 $cm-fix;Claude Code 跨平台入口为
/cm-fix,macOS/Linux 另有历史别名 /cm:fix。
每个缺陷开始/恢复时按 ../../runtime/project-learning.md 重读项目根 AGENTS.md,
筛选相关教训辅助复现与定位;同一合同约束收尾写回,不以旧经验代替本次证据。
用户明确要求外部专家,或为本次修复开启 AUTO 时,仍必须先完成第 1 步本地复现,
再按 ../../runtime/external-expert.md 执行 ../external-expert/SKILL.md 的任务
路由。代码、修复、测试和审查保持 LOCAL;只有竞争根因或高风险事实查证可路由到
CONSULT/VERIFY。外部假设必须回到本地证伪;咨询记录不能代替 2.5 或第 5 步独立
审查。
用法:$cm-fix {specs路径} {代码项目路径} 缺陷描述(现象/报错/截图均可)
在读取项目内容、解析角色、写 run_start、运行复现命令或创建档案前,先确认本轮包含非空缺陷
描述,但不要把描述正文拼进 shell;随后执行:
node "{CM_WORKFLOW_ROOT}/scripts/cm-fix-entry.mjs" \
--skill-dir "{CM_WORKFLOW_ROOT}/skills/cm-fix" --project "{CODE_PROJECT}" \
[--specs "{SPECS_DIR}"] --defect-present没有 specs 的裸项目省略 --specs。缺少描述时不传 --defect-present,入口返回
blocked / defect_required 后只向用户补要描述。只有 ready / reproduce 才进入下方既有闭环;
它不提前声称缺陷可复现、不可复现或属于设计问题,只声明复现失败仍走 observation、确认设计
问题仍转 $cm-prd --change。返回的角色、日志和 Learning 均为 pending,执行/写入权限为 false;
入口不运行命令、不调用 provider/browser/外部专家、不创建日志/测试/档案,也不替代七步流程。
准入通过后,具备当前会话双向进程通道、分离的 specs/代码根、命令式复现与测试配置时,
读取 references/js-host.md,使用既有 cm-fix-host.mjs 执行;Codex/Claude 共用同一 owner。
下文七步仍是业务要求,但 JS 分支的日志、交接、Review 发布及完成全部交给 owner,
不得再手工执行对应写入步骤。只读准入的 ready 不是执行、外发或完成许可。
JS 步骤留在 unknown 时先检查原调用和磁盘现场。只有本地复现、诊断、测试、修复、回归、
复盘及走查等列在 JS 宿主手册 的步骤,
才可在确认后用 abandon_step 说明原因并重做;普通 advance/run 不会自行放弃。
独立审查、Learning 写回及交接文件仍按各自恢复或人工检查路径处理,不走此出口。
裸项目、无自动测试/纯视觉替代、父 N6 运行衔接等尚未接通 JS 的场景,要明确报告缺口; 不得宣称已完成 JS 迁移。只有用户明确选择既有非 JS 流程且尚未创建 JS 运行时,才执行 下文手工流程;JS 已启动后遇到阻断,不得切换旁路、换身份或双写状态。
以下手工流程中,两个路径校验通过后调用统一写入器记录 run_start;暂停/续跑沿用同一
.cm-run.json,本次缺陷闭环或观测闭环退出时写 run_done。不得直接拼 JSON。
从代码项目根解析 coder、tester、reviewer(命令、参数和日志字段见
runtime/workflow-routing.md)。coder 只作为最小修复的请求路由元数据,tester
负责防护网/回归,reviewer 只描述独立审查候选通道;declared-adapter 必须记录为
未观测适配器,不能伪造调用或绕过本地执行与独立审查。resolver 返回非零或配置错误
时立即 BLOCKED,不得复现、修改或写入缺陷档案;配置不存在时保持当前默认行为。
managed-adapter 按 runtime/model-efficiency.md 返回文本建议并自动记录真实 usage;
复现、修复落盘、测试和独立审查仍由本地流程执行。
角色调用按 runtime/model-efficiency.md 只传当前缺陷的复现证据、根因范围、修复
diff、回归结果和对应规则;不重复投喂整仓、完整历史日志或其他缺陷上下文。失败输出
保留首个可行动错误与证据路径,防护网、独立审查和回归要求不因精简而变化。
修 bug 专用的轻量闭环——不走 N1–N8 全链(那是 feature 流程),也不许脱离工作流裸改(裸改没防护网没审查,修一个坏三个)。
多缺陷输入:先对全部缺陷做第 1-2 步(复现+定位),按根因聚类——同根缺陷合并为一次修复(多个失败测试、一次改动、档案互链),修复顺序按严重度排,不按输入顺序。不聚类的代价:三个现象一个根因跑三个闭环,且第一个修复落地后,后两个的复现步骤可能已失效(第 1 步卡死)。
转交进场(消费上游落盘物,不改上游流程):缺陷描述可附上游档案引用——$cm-test 的只读测试报告、$cm-refactor 档案的未修缺陷清单、N6 业务走查报告的偏差项、观测闭环的半份档案(按 slug 在 fixes/ 检索)。带引用进场的缺陷,第 1 步采信上游已有证据(位置/现象/日志原文),仍须实际复现一次核实,但不从零摸排。
$cm-ai 全局规则在本流程内同等生效:灾难级与节点显式卡点暂停、多方案自主决策留痕、状态落盘(node 写 FIX)、运行日志照记、独立审查按 runtime/review.md 执行。
修改代码前预检 fresh 独立审查通道;无可用通道时暂停修复,已有改动保持待审。
当前支持 Codex 子代理/隔离 CLI;未验证的 Claude-native 适配不能改名冒充 Codex。
跨边界证据(条件触发):缺陷涉及跨进程/跨服务、异步队列或流、路由目标、缓存/状态不一致或时序偶现时,读取 references/cross-boundary-debugging.md;它只补定位证据,不新增入口、状态或完成标准。普通可复现缺陷不补表,仍走以下七步。
观测中,列出已试场景,说明观测点为何这样埋,写清"等什么证据(哪个日志出现什么内容)"
③ 本次命令正常收口退出,不挂着等——运行日志记 run_done,detail 写「观测中:等{什么证据}」;状态文件 state 复位,不留悬挂的 running
④ 证据到手后再次运行 $cm-fix 附上证据,按 slug 定位 fixes/ 下的半份档案,从第 2 步定位续跑,档案续写、状态改 修复中,运行日志记 resume(detail 注证据摘要)
——"我改了点东西你再试试"依然被禁止../codebase-context/references/writeback.md 确定项目地图及本次文档范围;有地图先读相关链路与影响映射,项目指定架构文档同样适用任一客观条件命中才触发(简单缺陷零负担,判断依据同"门槛是客观项不是判断题"):波及面 ≥3 个模块 / 根因层与现象层不同层 / 观测闭环续跑的缺陷 / 拟走升级出口。
rediagnosis_required 可显式授权 rediagnose 一次,追加绑定原审查的新诊断,再由 fresh 独立上下文生成 cause-r2;第二次推翻停在 rediagnosis_review_limit_reached,不能自动第三次诊断或审查。原 task attempt、复现、cause-r1 和历史保持不变,详见 JS 控制文档。{SPECS_DIR}/.reviews/fix-{slug}-cause-r1.md——命名带 cause 是有意的:不落入第 5 步 fix-{slug}-r*.md 的匹配域,两个卡点各自独立,根因凭证不会误满足 diff 审查卡点references/test-extension.md 在第二轮登记扩充,修复回调仍不得改测试。$cm-refactor,不在修 bug 时动)decision 事件留痕design_change_required 后,有 redTest 就沿原测试编写/红测入口取得真实失败;意外通过或失败原因不符照常阻断。红测确认后进入 escalation_required,不跑基线、修复、回归或最终实现审查。升级立项,列出根因、影响范围、诊断方案、根因审查凭证、测试路径和红证据路径,建议用 $cm-prd --change 立项,以新方案使该测试变绿为验收。非视觉运行未配置 redTest 时直接进入升级归档,并明写没有失败测试及原因;视觉运行必须配置视觉 redTest(testFiles:[]),先走视觉红测核验真实修前载体再升级,不冒充自动红测。publish_dossier,再用获准的 finish 写 run_done / escalation / escalated 并关闭 owner;中断后在原运行重开收口,冲突则阻断。重开后的 escalated 是终态,completionEligible 始终为 false,不记 task_done 或修复完成指标;立项建议不自动创建变更项目。修后按 ../cm-test/references/unit-coverage.md 检查已授权修复范围的增量单测覆盖率,
核对正常/异常/边界及相邻场景并重跑,纳入下面的同一份 handoff;原失败测试红绿证据必须保留。
普通流程在审前补足授权测试;JS owner 若第一轮最终审查要求补测,按 references/test-extension.md 登记测试编写和实跑结果,
再走第二轮修复、回归与独立审查;不在 owner 外修改测试或重建原红灯、基线。
先按 ../codebase-context/references/writeback.md 完成地图评估与必要回写;无地图建本次局部地图,有地图只更新受影响章节。普通流程记 handoff evidence,JS 复用已绑定的 plan、修后文件与 Review;改动纳入摘要与独立审查,不能等第 7 步再写。
审查前按 ../../runtime/project-learning.md 复盘并完成必要的 AGENTS.md 增量写回,纳入本次审查 diff;无新增记入缺陷档案。微缺陷通道也必须复盘,新增 AGENTS.md 改动导致不再满足单文件门槛时走完整流程。
失败测试转绿 + 存量基线不退化后,按 runtime/review.md 审查本缺陷 diff(重点:根因是否真被修掉、有无只治症状、波及面有无遗漏)
防护网测试本身是审查对象(实测最大问题类:测试是戏台):红的原因是否=该缺陷、断言测的是根因还是症状、有无安慰剂/前提共谋;核对第 3 步落档的红证据——没有红过的记录,测试可信度按不成立处理
所有缺陷零豁免;独立通道不可用则待审,self-degraded 仅作诊断,不得成功收口;通道故障不算代码 finding/实现审查轮次,有效 finding 不能靠换人消除;≤2 轮上限同样生效
{slug} 先规范成跨平台安全的 ASCII kebab;令 REVIEW_FEATURE=fix-{slug}、
REVIEW_TASK=T-FIX-{slug}。主执行者按真实 diff 写
{SPECS_DIR}/.reviews/fix-{slug}-T-FIX-{slug}-a{attempt}-handoff.json,格式与
runtime/task-handoff.schema.json 相同。先按 handoff 的完整 changed_files 运行
cm-task-gate.py hash-implementation --project-root {CODE_PROJECT} --file ...,把返回的
implementation_sha256 写入 handoff,再真跑:
python3 {CM_WORKFLOW_ROOT}/scripts/cm-task-gate.py check-n4 \
--handoff {HANDOFF_PATH} --reviews-dir {SPECS_DIR}/.reviews \
--feature fix-{slug} --task T-FIX-{slug} --project-root {CODE_PROJECT}{SPECS_DIR}/.reviews/fix-{slug}-T-FIX-{slug}-r{attempt}.md,包含当前 handoff
文件名和 SHA。审查完成后必须真跑下列命令;只有当前 attempt 的
independent: true 且 verdict: approved 才能进入第 6 步:python3 {CM_WORKFLOW_ROOT}/scripts/cm-task-gate.py check-n5 \
--handoff {HANDOFF_PATH} --reviews-dir {SPECS_DIR}/.reviews \
--feature fix-{slug} --task T-FIX-{slug} --project-root {CODE_PROJECT}changes_requested 后修改代码必须生成 attempt 2 handoff 并复审;第 2 轮仍有阻断项
写 blocked 并停止。文件存在、旧凭证或 ls 输出都不构成批准。task_done;遵守回写合同的项目规则豁免,不把缺失地图静默跳过。task_done,按学习合同与第 5 步处理。{SPECS_DIR}/fixes/{YYYYMMDD}-{简短slug}.md——现象 / 复现步骤 / 复现尝试(逐条「场景 → 改了哪个维度 → 结果(复现/未复现/环境不支持)」;按描述一次命中只写一行)/ 根因 / 修法(含放弃的方案)/ 波及面与回归结果 / 测试文件路径;命中跨边界证据条件时追加“证据链与假设”(调用链、边证据、最后正常边、首个失败边、反证结果)。这是缺陷知识库,同类 bug 再犯先查这里fix,任务列写档案文件名,其余列同口径(轮次/拦截数/人工介入)policies.delivery:diff 不 stage/commit;branch/draft-mr 提交
fix: {一句话} (档案: fixes/xxx.md),审查摘要进 commit message(同 N4)task_start/review/task_done/run_done 照记,node 字段写 FIX门槛是客观项不是判断题——"感觉这个 bug 很小"不构成理由,四条全中才走,任一不中走完整七步:
快速通道可省:第 3 步防护网测试、第 6 步全量回归(用前后对照截图代替)。
不可省:独立审查(凭证照落)、地图评估(回写导致多文件则走完整流程)、缺陷档案(显式标注 快速通道)、METRICS 行(Feature 列写 fix-lite)。
快速通道的审查特化:独立审查是该通道的主要质量防线,第一职责是复核四个客观门槛;diff 任一项不符或波及面存疑即打回完整七步。
fix-lite 的占比进运行日志——快速通道被滥用(占比异常高/出现分支改动混入)时收紧门槛,数据说了算。
🔧 缺陷闭环: {slug}
根因: {一句话}
修法: {一句话} | 放弃方案: {有则一句话,无则省}
防护网: 新增 {测试文件}(红→绿) · 存量基线 {N} 项无退化
审查: 独立审查({channel}) {通过/N轮N条} | 回归: 波及面 {N} 项通过
档案: fixes/{文件名} METRICS 已记
学习: {AGENTS.md已写回并回读/已复盘,无新增}
业务地图: {已更新/已建局部地图/无需更新/项目规则豁免/待同步} {路径或原因}docs/fixes/,审查凭证落 docs/fixes/.reviews/(第 5 步卡点同样生效),METRICS 跳过© kingxiaozhe, MIT. 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 3 other files (references) in skills/cm-fix of kingxiaozhe/cm-workflow.
Open the folder on GitHubat commit 82d43f0
Cm Fix 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 |
|---|---|---|---|---|---|---|
| Cm Fix this skillkingxiaozhe/cm-workflow | 104 | — | ~2.5k | Automated safety check: Pass | MIT | |
| CCPM Project Managementautomazeio/ccpm | 8.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Ralph Tui Create Beadssubsy/ralph-tui | 2.5k | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Trellis Brainstormanjiemo/SunnyBeach | 178 | 7 repos | ~4k | Automated safety check: Pass | Apache-2.0 | |
| Ralph Tui Create Beads Rustsubsy/ralph-tui | 2.5k | 1 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Ralph Tui Create JSONsubsy/ralph-tui | 2.5k | 1 repos | ~2.6k | Automated safety check: Pass | MIT |
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
anjiemo/SunnyBeach
Guides collaborative requirements discovery before implementation.
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).
subsy/ralph-tui
Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.
jamesrochabrun/skills
Generate comprehensive Product Requirements Documents (PRDs) for product managers.
kingxiaozhe/cm-workflow
用户明确说“规格已确认,开始实现”或要求按已审批 CM specs 开发时使用。新任务默认由 JS workflow 驱动 N1-N8,完成开发、独立审查、QA 与文档同步;模糊点子、未审规格和单独一句“继续”不能触发编码批准。
kingxiaozhe/cm-workflow
用户说“检查工作流是否安装正确”“为什么找不到 cm 命令”时使用。默认查询 npm 稳定版,有新版自动升级已管理的 CM 安装,再检查插件、核心 Skills、兼容包装与模板引用;不测试或修改业务代码。
kingxiaozhe/cm-workflow
用户说“我有个点子”“帮我梳理产品”或需要先聊清目标时使用。通过逐题访谈整理为可交给 cm-prd 的 PRD;已有明确需求文档时改用 cm-prd,不写代码、不拆开发任务。
kingxiaozhe/cm-workflow
用户说“第一次接管这个项目”“分析仓库并生成项目规则”时使用。分析已有代码并生成 Codex AGENTS.md 与 CM/Claude 兼容规则;仅适用于非空存量项目,不创建脚手架、不承接普通代码修改。
kingxiaozhe/cm-workflow
微信小程序开发工程师 Skill,执行小程序开发任务,自动适配项目技术栈(原生小程序/Taro/uni-app 等),支持 Figma/Stitch 设计稿还原与云开发
kingxiaozhe/cm-workflow
用户说“把需求拆成可开发规格”“变更现有功能需求”或要求整理方案、任务和验收时使用。支持新项目、存量二开与需求变更;完成后停在人审规格,不直接编码。
Categories
用户说“修复这个可复现 bug”或要求根据失败报告修代码时使用。执行红灯测试、根因定位、最小修复、独立审查和回归;尚未确认的问题先用 cm-test,新功能和架构重设计转交 cm-prd。. Cm Fix is an agent skill from kingxiaozhe/cm-workflow.
Cm Fix fits situations like: tasks that involve PRD writing.
Run `npx skills add kingxiaozhe/cm-workflow --skill cm-fix -a claude-code`. Or copy the skill folder (skills/cm-fix in kingxiaozhe/cm-workflow) into .claude/skills/cm-fix in your project. Claude Code loads it when a task matches its description.
Run `npx skills add kingxiaozhe/cm-workflow --skill cm-fix -a codex`. Or copy the skill folder (skills/cm-fix in kingxiaozhe/cm-workflow) into .agents/skills/cm-fix 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 kingxiaozhe/cm-workflow --skill cm-fix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cm-fix, .gemini/skills/cm-fix, .github/skills/cm-fix and .opencode/skills/cm-fix in your project.
Going by SKILL.md and its folder, Cm Fix needs the command-line tools its instructions call (python3 and node).
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.
Cm Fix is published under the MIT 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 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.1k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Cm Fix: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
kingxiaozhe (a GitHub user) maintains it in kingxiaozhe/cm-workflow, which has 104 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 9, 2026.
Source: kingxiaozhe/cm-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.