@wenaixi/dsh-ponytail 5.1.0 → 5.3.0

package/skills/ponytail-debt/SKILL.md

@@ -1,31 +1,44 @@
 ---
 name: ponytail-debt
 description: >
-  把代码库中所有 `ponytail:` 注释收割为债务台账，让 ponytail 有意留下的捷径和延期不会悄悄烂成「以后再说就是永远不做」。触发词：ponytail debt / /ponytail-debt / ponytail 延期了什么 / 列出捷径 / ponytail 台账 / 标记了什么待做。一次性报告，不改代码。
+  Harvest every `ponytail:` comment in the codebase into a debt ledger, so the
+  deliberate shortcuts and deferrals ponytail leaves behind get tracked instead
+  of rotting into "later means never". Use when the user says "ponytail debt",
+  "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail
+  ledger", or "what did we mark to do later". One-shot report, changes nothing.
 ---
 
-ponytail 有意留下的每个捷径都会用 `ponytail:` 注释标出天花板和升级路径。本技能把它们收割为一张台账，让延期不会悄悄变成永久。
+Every deliberate ponytail shortcut is marked with a `ponytail:` comment naming
+its ceiling and upgrade path. This collects them into one ledger so a deferral
+can't quietly become permanent.
 
-## 扫描
+## Scan
 
-在仓库中 grep 注释标记，跳过 `node_modules`、`.git` 和构建产物：
+Grep the repo for comment markers, skipping `node_modules`, `.git`, and build
+output:
 
-`grep -rnE '(#|//) ?ponytail:' .`  （若技术栈有其他注释前缀，请一并加入）
+`grep -rnE '(#|//) ?ponytail:' .`  (add other comment prefixes if your stack uses them)
 
-每个命中即为台账的一行，注释前缀可避免把正文中偶然提及约定的内容误收入台账。
+Each hit is one ledger row. The comment prefix keeps prose that merely mentions
+the convention out of the ledger.
 
-## 输出
+## Output
 
-每行一个标记，按文件分组：
+One row per marker, grouped by file:
 
-`<文件>:<行号>，<简化了什么>。天花板：<注释中提到的限制>。升级：<何时回头处理的触发条件>。`
+`<file>:<line>, <what was simplified>. ceiling: <the limit named>. upgrade: <the trigger to revisit>.`
 
-约定为 `ponytail: <天花板>，<升级路径>`，因此天花板和触发条件直接从注释中提取。想给每行加负责人？再跑 `git blame -L<行号>,<行号>`。
+The convention is `ponytail: <ceiling>, <upgrade path>`, so pull the ceiling
+and the trigger straight from the comment. Want an owner per row too? add
+`git blame -L<line>,<line>`.
 
-风险标记：任何未写明升级路径或触发条件的 `ponytail:` 注释打上 `no-trigger` 标签，这些是最容易悄悄腐烂的。
+Flag the rot risk: any `ponytail:` comment that names no upgrade path or
+trigger gets a `no-trigger` tag, those are the ones that silently rot.
 
-结尾汇总 `<N> 个标记，<M> 个无触发条件。` 若无命中：`无 ponytail: 债务，台账干净。`
+End with `<N> markers, <M> with no trigger.` Nothing found: `No ponytail: debt. Clean ledger.`
 
-## 边界
+## Boundaries
 
-只读、只报告，不改任何东西。如需落盘，询问后可将台账写入文件（例如 `PONYTAIL-DEBT.md`）。一次性报告。「stop ponytail-debt / 正常模式」可退出。
+Reads and reports only, changes nothing. To persist it, ask and it writes the
+ledger to a file (e.g. `PONYTAIL-DEBT.md`). One-shot. "stop ponytail-debt" or
+"normal mode" to revert.

package/skills/ponytail-gain/SKILL.md

@@ -1,37 +1,50 @@
 ---
 name: ponytail-gain
 description: >
-  以精简看板展示 ponytail 的实测收益：更少代码、更低成本、更快速度，数据来自 benchmark 中位数。一次性展示，非持久模式，也非本仓实时统计。触发词：/ponytail-gain / ponytail gain / ponytail 能省多少 / 展示 ponytail 收益 / ponytail 看板。
+  Show ponytail's measured impact as a compact scoreboard: less code, less
+  cost, more speed, from the benchmark medians. One-shot display, not a
+  persistent mode, and not a per-repo number. Trigger: /ponytail-gain,
+  "ponytail gain", "what does ponytail save", "show ponytail impact",
+  "ponytail scoreboard".
 ---
 
-# Ponytail Gain · 收益看板
+# Ponytail Gain
 
-被调用时展示此看板。一次性展示：不要切换模式、写 flag 文件或做任何持久化。
+Display this scoreboard when invoked. One-shot: do NOT change mode, write flag
+files, or persist anything.
 
-数据为已发布的 benchmark 中位数（5 个日常任务：邮箱校验、防抖、CSV 求和、倒计时、限流器；3 个模型：Haiku、Sonnet、Opus），是实测值而非基于当前仓库计算。来源：`benchmarks/` 与 README。
+The figures are the published benchmark medians (5 everyday tasks: email
+validator, debounce, CSV sum, countdown timer, rate limiter; three models:
+Haiku, Sonnet, Opus). They are measured, not computed from the current repo.
+Source: `assets/benchmark-3model.svg` and `assets/benchmark-agentic.svg`.
 
-## 看板
+## Scoreboard
 
-用纯 ASCII 条形图渲染，条形长度表示实测区间，标签给出精确数值：
+Render plain ASCII bars. The bar length shows the measured range; the label
+carries the exact figure:
 
 ```
-  ponytail gain                     benchmark 中位数 · 5 任务 · 3 模型
+  ponytail gain                     benchmark median · 5 tasks · 3 models
 
-  代码行数    无技能  ████████████████████  100%
-              ponytail  ██▌·················    6–20%   ▼ 80–94%
-  成本        无技能  ████████████████████  100%
-              ponytail  █████▌··············   23–53%  ▼ 47–77%
-  速度        ponytail  ▸ 3–6× 更快
+  Lines of code   no-skill  ████████████████████  100%
+                  ponytail  ██▌·················    6–20%   ▼ 80–94%
+  Cost            no-skill  ████████████████████  100%
+                  ponytail  █████▌··············   23–53%  ▼ 47–77%
+  Speed           ponytail  ▸ 3–6× faster
 
-  本仓：  /ponytail-debt （已延期的捷径）
-          /ponytail-audit（仍可删的地方）
+  This repo:  /ponytail-debt  (shortcuts you deferred)
+              /ponytail-audit (what's still cuttable)
 ```
 
-## 诚实边界
+## Honesty boundary
 
-这些是 benchmark 中位数，不是本仓数据。永远不要打印针对本仓的节省数字（例如「本仓节省了 X 行/Token」）：没写的版本从未存在，因此在真实仓库中没有可对比的基线。唯一真实的本仓数字来自 `/ponytail-debt`（已计数的台账），本卡片也会指向那里，而不是凭空捏造。
+These are benchmark medians, not this repo. NEVER print a per-repo savings
+number ("you saved X lines/tokens here"): the unbuilt version was never
+written, so there is no real baseline to subtract from in a live repo. The
+only real per-repo figures come from `/ponytail-debt` (a counted ledger), and
+this card points there instead of inventing one.
 
-## 边界
+## Boundaries
 
-一次性展示，不改任何东西，不切换模式。
-「stop ponytail / 正常模式」可退出。
+One-shot display. Edits nothing, changes no mode.
+"stop ponytail" or "normal mode": revert.

package/skills/ponytail-help/SKILL.md

@@ -1,58 +1,87 @@
 ---
 name: ponytail-help
 description: >
-  ponytail 全量模式、技能与命令的速查卡，一次性展示，非持久模式。触发词：/ponytail-help / ponytail help / ponytail 有哪些命令 / 怎么用 ponytail。
+  Quick-reference card for all ponytail modes, skills, and commands.
+  One-shot display, not a persistent mode. Trigger: /ponytail-help,
+  "ponytail help", "what ponytail commands", "how do I use ponytail".
 ---
 
-# Ponytail Help · 速查卡
+# Ponytail Help
 
-被调用时展示此速查卡。一次性展示，不要切换模式、写 flag 文件或做任何持久化。
+Display this reference card when invoked. One-shot, do NOT change mode,
+write flag files, or persist anything.
 
-## 等级
+## Levels
 
-| 等级 | 触发 | 变化 |
-|-------|---------|------|
-| **Lite** | `/ponytail lite` | 按要求构建，但在同一行里点出更懒的替代方案。 |
-| **Full** | `/ponytail` | 强制走梯子：YAGNI → 标准库 → 原生 → 一行 → 最小实现。默认。 |
-| **Ultra** | `/ponytail ultra` | YAGNI 极端派，先删后加，在构建前先挑战需求本身。 |
+| Level | Trigger | What change |
+|-------|---------|-------------|
+| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |
+| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |
+| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |
 
-等级会保持到被修改或会话结束。
+Level sticks until changed or session end.
 
-## 技能
+## Skills
 
-| 技能 | 触发 | 作用 |
-|-------|---------|------|
-| **ponytail** | `/ponytail` | 懒人模式本体，用最简可用的解法。 |
-| **ponytail-review** | `/ponytail-review` | 过度设计评审：`L42: yagni: 工厂只有一个产品，直接内联。` |
-| **ponytail-audit** | `/ponytail-audit` | 全仓过度设计审计：按可删行数排序的清单。 |
-| **ponytail-debt** | `/ponytail-debt` | 收割 `ponytail:` 捷径注释，生成待办台账。 |
-| **ponytail-gain** | `/ponytail-gain` | 实测收益看板：更少代码、更低成本、更快速度。 |
-| **ponytail-help** | `/ponytail-help` | 本卡片。 |
+| Skill | Trigger | What it does |
+|-------|---------|--------------|
+| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |
+| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |
+| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |
+| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |
+| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |
+| **ponytail-help** | `/ponytail-help` | This card. |
 
+Codex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code
+and OpenCode use the slash-command forms above (OpenCode ships all six as
+slash commands).
 
-## 退出
+## Deactivate
 
-说「stop ponytail / 正常模式」即可退出，随时用 `/ponytail` 恢复。
-`/ponytail off` 同样可用。
+Say "stop ponytail" or "normal mode". Resume anytime with `/ponytail`.
+`/ponytail off` also works.
 
-## 配置默认等级
+## Configure Default Mode
 
-默认等级为 `full`，每会话自动激活。修改方式：
+Default mode = `full`, auto-active every session. Change it:
 
-**环境变量**（优先级最高）：
+**Environment variable** (highest priority):
 ```bash
 export PONYTAIL_DEFAULT_MODE=ultra
 ```
 
-**配置文件**（`$DSH_HOME/ponytail/config.json`，默认 `~/.dsh/ponytail/config.json`）：
-```json
-{ "defaultMode": "lite" }
+**Profile patch** (`profiles/<name>/cordis.patch.yml`):
+
+`dsh plugin add` does NOT write this file. After installing, add a top-level
+entry by hand or the config card will not render:
+
+```yaml
+- id: ponytail
+  name: "@wenaixi/dsh-ponytail"
+  config:
+    defaultMode: lite  # off|lite|full|ultra
 ```
 
-设为 `"off"` 可关闭会话启动时的自动激活，需要时再用 `/ponytail` 手动开启。
+Then restart the host (patch entries compose at startup, not on reload).
+The plugin config card writes the patch for you once it renders;
+`/ponytail default <mode>` does the same from a prompt. Set `"off"` to
+disable auto-activation on session start, activate manually with `/ponytail`
+when wanted.
+
+Resolution: env var > profile patch > built-in `full`. The card shows all three
+sources and which one wins, so a level that "looks" set but is shadowed is
+visible instead of silently ignored.
+
+## Update
+
+```bash
+dsh plugin --profile <name> add @wenaixi/dsh-ponytail
+```
 
-优先级：环境变量 > 配置文件 > `full`。
+Restart the host after updating: a plugin entry's artifact fingerprint is
+computed at process start and frozen, so a page refresh alone keeps serving
+the previous build. A fresh install only needs a refresh.
 
-## 更多
+## More
 
-完整文档与示例：https://github.com/DietrichGebert/ponytail
+Full docs + examples: https://github.com/DietrichGebert/ponytail

package/skills/ponytail-review/SKILL.md

@@ -1,45 +1,57 @@
 ---
 name: ponytail-review
 description: >
-  专挑过度设计的代码评审，只找能删的东西：重复造的标准库、没必要的依赖、臆想的抽象、闲置的灵活性。每条发现一行写完：位置、该删什么、用什么替代。触发词：过度设计评审 / 能删什么 / 是否过度设计 / 简化评审 / ponytail-review / /ponytail-review。配合面向正确性的评审使用，本技能只猎复杂度。
+  Code review focused exclusively on over-engineering. Finds what to delete:
+  reinvented standard library, unneeded dependencies, speculative abstractions,
+  dead flexibility. One line per finding: location, what to cut, what replaces
+  it. Use when the user says "review for over-engineering", "what can we
+  delete", "is this over-engineered", "simplify review", or invokes
+  /ponytail-review. Complements correctness-focused review, this one only
+  hunts complexity.
 ---
 
-只评审 diff 中的不必要复杂度，每条发现一行写完：位置、该删什么、用什么替代。diff 的最好结局是变短。
+Review diffs for unnecessary complexity. One line per finding: location, what
+to cut, what replaces it. The diff's best outcome is getting shorter.
 
-## 格式
+## Format
 
-`L<行号>: <标签> <该删什么>。<替代方案>。` 多文件 diff 用 `<文件>:L<行号>: ...`。
+`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for
+multi-file diffs.
 
-标签：
+Tags:
 
-- `delete:` 死代码、未使用的灵活性、臆想功能。替代：无。
-- `stdlib:` 标准库已有的东西被手写了一遍，写出函数名。
-- `native:` 依赖或代码在做平台已有的事，写出平台特性名。
-- `yagni:` 只有一个实现的抽象、没人改的配置、只有一个调用方的分层。
-- `shrink:` 同样逻辑，更少行数，给出更短写法。
+- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.
+- `stdlib:` hand-rolled thing the standard library ships. Name the function.
+- `native:` dependency or code doing what the platform already does. Name the feature.
+- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.
+- `shrink:` same logic, fewer lines. Show the shorter form.
 
-## 示例
+## Examples
 
-❌ 「这个 EmailValidator 类是不是有点复杂，要不要考虑现阶段是否真的需要这么多校验规则？」
+❌ "This EmailValidator class might be more complex than necessary, have you
+considered whether all these validation rules are needed at this stage?"
 
-✅ `L12-38: stdlib: 27 行的校验类。邮箱里有 "@" 就算 1 行，真正的校验是发确认邮件。`
+✅ `L12-38: stdlib: 27-line validator class. "@" in email, 1 line, real validation is the confirmation mail.`
 
-✅ `L4: native: 为了一次格式化就引入 moment.js。用 Intl.DateTimeFormat，0 依赖。`
+✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`
 
-✅ `repo.py:L88: yagni: 只有一个实现的 AbstractRepository。先内联，等第二个实现出现再说。`
+✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`
 
-✅ `L52-71: delete: 在幂等的本地调用外包了一层重试。删掉即可。`
+✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`
 
-✅ `L30-44: shrink: 手写循环拼 dict。用 dict(zip(keys, values))，1 行。`
+✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`
 
-## 评分
+## Scoring
 
-最后只留一个关心的指标：`net: -<N> 行可删。`
+End with the only metric that matters: `net: -<N> lines possible.`
 
-若无可删之处，直接说 `已足够精简，直接发版。` 并结束。
+If there is nothing to cut, say `Lean already. Ship.` and stop.
 
-## 边界
+## Boundaries
 
-范围：只看过度设计和复杂度。正确性 bug、安全漏洞、性能问题明确不在范围内，请走常规评审通道。单个冒烟测试或基于 `assert` 的自检是 ponytail 的最低要求，不算臃肿，永远不要标为可删。
-只列发现，不直接改代码。
-「stop ponytail-review / 正常模式」可切回啰嗦的评审风格。
+Scope: over-engineering and complexity only. Correctness bugs, security holes,
+and performance are explicitly out of scope. Route them to a normal review
+pass, not this one. A single smoke test or `assert`-based
+self-check is the ponytail minimum, not bloat, never flag it for deletion.
+Does not apply the fixes, only lists them.
+"stop ponytail-review" or "normal mode": revert to verbose review style.