ecc-recipes

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ECC Recipes

ECC 方案集

One entry point for "which group of ECC slash-commands runs my workflow, in what order, and when do I stop." Also browses every command-group recipe family.
Fills the gap between two existing skills:
  • ecc-guide
    — lists commands and where to read docs, but as a flat catalog.
  • prompt-optimizer
    — matches a task to components, but outputs a single prompt, not a multi-command group with run-order and stop condition.
This skill adds: family grouping + run-order + stop condition.
这是一个入口,用于查询“哪组ECC斜杠命令可运行我的工作流、执行顺序是什么以及何时停止”,同时也可浏览所有命令组方案家族。
填补了现有两个技能之间的空白:
  • ecc-guide
    — 列出命令及其文档位置,但仅为扁平化目录。
  • prompt-optimizer
    — 将任务与组件匹配,但仅输出单个提示词,而非带有执行顺序和停止条件的多命令组。
本技能新增了:家族分组 + 执行顺序 + 停止条件

When to Activate

激活时机

  • "Which command group do I run for <workflow>?"
  • "What's the command sequence to build an MVP / fix a defect / refactor?"
  • "Show me all ECC command-group recipes" (catalog mode)
  • "How many workflow pipelines does ECC have?"
  • User invokes
    /ecc-recipes
    with or without a description.
  • “执行<工作流>需要哪个命令组?”
  • “构建MVP、修复缺陷或重构的命令序列是什么?”
  • “展示所有ECC命令组方案”(目录模式)
  • “ECC有多少个工作流流水线?”
  • 用户调用
    /ecc-recipes
    ,无论是否附带描述。

Do Not Use When

请勿使用的场景

  • User wants the task done now — route to the actual command, don't describe it.
  • User wants deep docs for ONE command — use
    ecc-guide
    .
  • User wants a draft prompt rewritten — use
    prompt-optimizer
    .
  • 用户希望立即完成任务 — 引导至实际命令,无需描述。
  • 用户需要单个命令的详细文档 — 使用
    ecc-guide
  • 用户需要重写草稿提示词 — 使用
    prompt-optimizer

Core Principle

核心原则

Answer from current files, not memory. The command set changes; never hardcode counts or member lists. Read the live
commands/
directory each run, then classify into families.
从当前文件获取答案,而非依赖记忆。 命令集会发生变化;切勿硬编码命令数量或成员列表。每次运行时读取实时的
commands/
目录,再将命令分类至各个家族。

Live reads

实时读取

Resolve the commands directory (first that exists), then list names:
bash
for D in \
  "$HOME"/.claude/plugins/marketplaces/ecc/commands \
  "$HOME"/.claude/plugins/cache/ecc/ecc/*/commands \
  ./commands \
  ./.claude/commands \
  "$HOME"/.claude/commands; do
  [ -d "$D" ] && CMD_DIR="$D" && break
done
[ -z "${CMD_DIR:-}" ] && { echo "No ECC commands directory found."; return 1; }
find "$CMD_DIR" -maxdepth 1 -name '*.md' -exec basename {} .md \; | sort
Optionally read
manifests/install-*.json
if present for richer grouping. Use the smallest set of reads needed.
解析命令目录(优先存在的目录),然后列出命令名称:
bash
for D in \
  "$HOME"/.claude/plugins/marketplaces/ecc/commands \
  "$HOME"/.claude/plugins/cache/ecc/ecc/*/commands \
  ./commands \
  ./.claude/commands \
  "$HOME"/.claude/commands; do
  [ -d "$D" ] && CMD_DIR="$D" && break
done
[ -z "${CMD_DIR:-}" ] && { echo "No ECC commands directory found."; return 1; }
find "$CMD_DIR" -maxdepth 1 -name '*.md' -exec basename {} .md \; | sort
若存在
manifests/install-*.json
文件,可选择性读取以实现更丰富的分组。仅读取必要的最少文件。

Family Classification (by prefix)

家族分类(按前缀)

Group command names by leading prefix; map known singletons by hand. Families are derived live — the table below is the classification rule, not a frozen list.
Family prefixRecipe meaningTypical run-order
orch-*
gated Research, Plan, TDD, Review, Commit per task typepick one orch-* by task kind; it runs its own internal phases
multi-*
multi-model workflow
multi-plan
then
multi-execute
then review (or
multi-workflow
end-to-end)
prp-*
PRD to plan to implement to PR pipeline
prp-prd
then
prp-plan
then
prp-implement
then
prp-commit
then
prp-pr
epic-*
large multi-unit epic, parallel
epic-decompose
then
epic-claim
then
epic-validate
then
epic-review
then
epic-unblock
then
epic-sync
then
epic-publish
loop-*
managed autonomous loop and monitor
loop-start <pattern>
then watch with
loop-status
gan-*
generator and evaluator loop
gan-build
(code) or
gan-design
(UI); self-looping
*-build
/
*-review
/
*-test
per-language CI triad
<lang>-test
(TDD) then
<lang>-build
(fix) then
<lang>-review
hookify-*
behavior-hook management
hookify
then
hookify-list
then
hookify-configure
learn
/
instinct-*
/
evolve
/
promote
/
prune
continuous-learning
learn
then
instinct-status
then
evolve
then
promote
singletons
santa-loop
,
plan
,
plan-prd
,
pr
,
code-review
,
checkpoint
, etc.
standalone or glue between groups
Any command not matching a prefix rule → list it under singletons with its one-line description.
按开头前缀对命令名称进行分组;手动映射已知的单例命令。家族是实时生成的 — 下表是分类规则,而非固定列表。
家族前缀方案含义典型执行顺序
orch-*
针对不同任务类型的受控研究、规划、TDD、评审、提交流程根据任务类型选择一个
orch-*
命令;它会自行运行内部阶段
multi-*
多模型工作流先执行
multi-plan
,再执行
multi-execute
,然后进行评审(或使用
multi-workflow
完成端到端流程)
prp-*
从PRD到规划、实现再到PR的流水线先执行
prp-prd
,再执行
prp-plan
,接着
prp-implement
,然后
prp-commit
,最后
prp-pr
epic-*
大型多单元史诗任务,支持并行先执行
epic-decompose
,再执行
epic-claim
,接着
epic-validate
,然后
epic-review
,之后
epic-unblock
,再
epic-sync
,最后
epic-publish
loop-*
受控自主循环与监控执行
loop-start <pattern>
,然后通过
loop-status
监控
gan-*
生成器与评估器循环执行
gan-build
(代码)或
gan-design
(UI);自动循环运行
*-build
/
*-review
/
*-test
各语言CI三元组先执行
<lang>-test
(TDD),再执行
<lang>-build
(修复),然后
<lang>-review
hookify-*
行为钩子管理先执行
hookify
,再执行
hookify-list
,然后
hookify-configure
learn
/
instinct-*
/
evolve
/
promote
/
prune
持续学习流程先执行
learn
,再执行
instinct-status
,接着
evolve
,然后
promote
单例命令
santa-loop
,
plan
,
plan-prd
,
pr
,
code-review
,
checkpoint
独立运行或作为组间衔接工具
任何不符合前缀规则的命令 → 归类至单例命令下,并附上其一行描述。

How It Works

工作原理

1. Live-read command names from CMD_DIR.
2. Classify into families by prefix and a singleton map.
3. If a workflow description was given -> MATCH MODE.
   If none -> CATALOG MODE.
4. Advisory only: print the plan. Never run the matched commands.
1. 从CMD_DIR实时读取命令名称。
2. 根据前缀和单例映射将命令分类至各个家族。
3. 若提供了工作流描述 → 匹配模式。
   若未提供 → 目录模式。
4. 仅提供建议:输出计划。切勿运行匹配的命令。

Catalog mode (no description)

目录模式(无描述)

Output the family table: each family, member count, members, one-line meaning, typical run-order. End with the total command count and a prompt to describe a workflow for a matched recipe.
输出家族表格:包含每个家族、成员数量、成员列表、一行描述的含义以及典型执行顺序。最后显示命令总数,并提示用户描述一个工作流以获取匹配的方案。

Match mode (description given)

匹配模式(提供描述)

  1. Restate the workflow in one sentence.
  2. Pick the best 1-2 families; say WHY in one line each.
  3. Run-order block — exact command sequence for the matched family.
  4. Stop condition — always explicit (max-runs, completion-signal, review-passes, or single-shot). For autonomous loops, warn about subscription burn and recommend a backstop bound.
  5. Where to read — the
    commands/<name>.md
    path plus
    /ecc-guide <name>
    .
  1. 用一句话重述工作流。
  2. 选择最匹配的1-2个家族;每个家族用一句话说明理由。
  3. 执行顺序块 — 匹配家族的精确命令序列。
  4. 停止条件 — 必须明确(最大运行次数、完成信号、评审通过或单次执行)。对于自主循环,需警告订阅消耗问题,并建议设置兜底限制。
  5. 文档位置
    commands/<name>.md
    路径,以及
    /ecc-guide <name>
    命令。

Output Template (match mode)

输出模板(匹配模式)

Workflow: <one-sentence restatement>

Best fit: <family> — <why>
(Alt: <family> — <why>)

Run-order:
  /<cmd1>   # job
  /<cmd2>   # job
  /<cmd3>   # job
  STOP when: <condition>
  WARNING (autonomous loops only): an unbounded loop burns subscription/credits —
  add a max-iteration or max-cost backstop alongside the completion signal.

Read full docs:
  commands/<cmd1>.md   (or: /ecc-guide <cmd1>)
工作流:<一句话重述>

最佳匹配:<家族> — <理由>
(备选:<家族> — <理由>)

执行顺序:
  /<cmd1>   # 任务
  /<cmd2>   # 任务
  /<cmd3>   # 任务
  停止条件:<条件>
  警告(仅自主循环):无限制循环会消耗订阅/额度 —
  需在完成信号之外添加最大迭代次数或最大成本兜底限制。

查看完整文档:
  commands/<cmd1>.md  (或:/ecc-guide <cmd1>)

Examples

示例

Catalog:
/ecc-recipes
→ prints the family table and total count.
Match:
/ecc-recipes plan a whole app upfront then auto-build with adversarial review until done
→ Best fit:
loop-*
(autonomous) wrapping
gan-*
or
santa-loop
(adversarial). Run-order:
plan-prd
then
loop-start rfc-dag --mode safe
then monitor
loop-status
; STOP when all units pass review N consecutive times (add a max-iteration backstop to bound burn).
Match:
/ecc-recipes fix a bug in my Go service
→ Best fit:
orch-fix-defect
(reproduce, fix, review, commit). Alt:
go-test
then
go-build
then
go-review
. STOP: regression test green and review pass.
目录模式:
/ecc-recipes
→ 输出家族表格和命令总数。
匹配模式:
/ecc-recipes plan a whole app upfront then auto-build with adversarial review until done
→ 最佳匹配:
loop-*
(自主型),封装
gan-*
santa-loop
(对抗式评审)。执行顺序:先执行
plan-prd
,再执行
loop-start rfc-dag --mode safe
,然后通过
loop-status
监控;停止条件:所有单元连续N次通过评审(需添加最大迭代次数兜底限制以避免过度消耗)。
匹配模式:
/ecc-recipes fix a bug in my Go service
→ 最佳匹配:
orch-fix-defect
(重现、修复、评审、提交)。备选:
go-test
go-build
go-review
。停止条件:回归测试通过且评审通过。

Non-Goals

非目标

  • Not an executor — advisory only.
  • Not per-command deep docs — that's
    ecc-guide
    .
  • Not prompt rewriting — that's
    prompt-optimizer
    .
  • Never hardcode command counts or member lists — always live-read.
  • 非执行器 — 仅提供建议。
  • 非单命令详细文档 — 该功能由
    ecc-guide
    提供。
  • 非提示词重写 — 该功能由
    prompt-optimizer
    提供。
  • 切勿硬编码命令数量或成员列表 — 始终实时读取。