@mingfuyun/star-allinone 0.1.9 → 0.2.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mingfuyun/star-allinone",
-  "version": "0.1.9",
+  "version": "0.2.0",
   "description": "星系运维前端能力包",
   "main": "dist/index.js",
   "bin": {

package/skills/README.md

@@ -71,6 +71,7 @@ custom-*   业务定制 skill，由业务项目维护
         ├── impact-analysis/
         ├── ai-review/
         ├── commit-current-changes/
+        ├── i-have-adhd/               # 同步为 shared-i-have-adhd；其他 shared skill 的用户输出格式
         └── publish-test/              # 流水线 ID 从 .star-allinone.json 读取
 ```
 

package/skills/shared/ai-review/SKILL.md

@@ -27,3 +27,7 @@ Do not require a project-local review-rules file. If `.agents/project/review-rul
 Lead with findings ordered `[P0]`–`[P3]`, with file and line. Separate blocking issues from recommendations. Do not report style preferences as bugs.
 
 If none, write `No issues found.` Always include validation performed and gaps. Do not modify files unless the user explicitly asks for fixes.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/api-mock/SKILL.md

@@ -21,3 +21,7 @@ If the service contract is missing, first follow `.agents/skills/shared-api-to-s
 ## Handoff
 
 For every endpoint, report HTTP method, path, scenario label, and one strict parseable JSON block. If files were written, list the paths and confirm they parse as JSON.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/api-to-service/SKILL.md

@@ -49,3 +49,7 @@ pnpm exec tsc --noEmit
 ```
 
 Parse changed JSON files. Search generated names, operationId, and exact API paths for omissions and collisions. Run `pnpm lint` for broad service changes. Cite the OpenAPI path, method, operationId, and schema names in the handoff.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/commit-current-changes/SKILL.md

@@ -64,3 +64,7 @@ A confirmed commit or push does not authorize the test pipeline. If the user lat
 - Never expose credentials from diffs; stop if secrets are present.
 - Never use destructive Git commands to clean the working tree.
 - If push is rejected, report the reason and do not rewrite history without separate authorization.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/design-to-page/SKILL.md

@@ -46,3 +46,7 @@ pnpm exec tsc --noEmit
 ```
 
 Run `pnpm lint` for broad or shared changes. Run the project's documented build command when routes, entry, or multiple pages change.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/i-have-adhd/SKILL.md

@@ -0,0 +1,142 @@
+---
+name: {{sharedSkillName}}
+description: 'Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".'
+disable-model-invocation: true
+license: MIT
+metadata:
+  tags: "ADHD, Output Style, Productivity, Formatting"
+  category: "productivity"
+---
+
+# i-have-adhd
+
+The reader has ADHD. Output is not just brief. It is shaped so an ADHD brain can act on it.
+
+## Persistence
+
+These rules apply to every response for the rest of the session, not only this one. They do not expire after a few turns and they do not lapse when the topic changes. If you are unsure whether they still apply, they do.
+
+Turn them off only when the reader says "stop adhd mode" or "normal mode". Confirm in one line, then return to your default style.
+
+## What ADHD changes about reading
+
+Five facts drive every rule below:
+
+1. Working memory is small. Anything not on screen is forgotten. Do not ask the reader to "keep in mind X."
+2. Knowing the answer is not doing the answer. The friction between "got it" and "done it" is where work dies.
+3. Starting is the hardest step. The first action must be obvious, small, and doable now.
+4. Time estimates feel uniform. "A bit of work" and "a few hours" register the same. Vague estimates fail.
+5. Dopamine is scarce. Visible progress matters. Buried wins do not register.
+
+## Rules
+
+### 1. Lead with the next action
+
+The first line is something the reader can do. Not context. Not a plan. The action.
+
+Bad: "Let's think about this. Your auth flow has a few moving pieces..."
+Good: "Run `npm install jsonwebtoken`, then edit `src/auth.ts:42`."
+
+If the answer is a command, path, or snippet, it goes first. Prose comes after, if at all.
+
+### 2. Number multi-step tasks
+
+If the work takes more than one step, write a numbered list. Each step is one bounded action. No step contains "and then" twice.
+
+Use the fewest steps that still work. Cut any step the reader does not need, and fold trivial steps into the one before. A short path finished beats a complete path abandoned.
+
+Bad: "First open the file, find the function, swap it out, then run the tests."
+
+Good:
+```
+1. Open `src/auth.ts`
+2. Replace `verifyToken` (lines 42 to 58) with the snippet below
+3. Run `npm test -- auth.spec.ts`
+```
+
+### 3. End with one concrete next action
+
+If anything is left open, name ONE thing the reader can do in under two minutes. Even "open the file" counts.
+
+Bad: "Hope that helps. Let me know if you want to dig deeper."
+Good: "Next: run `npm test` and paste the first failing line."
+
+### 4. Suppress tangents
+
+If a second issue exists, finish the first, then offer the second as a separate question.
+
+Bad: "Here's the fix. By the way, your dependency is also stale, and your README is out of date, and..."
+Good: "Here's the fix. Separately: there is also a stale dependency. Want me to handle that next?"
+
+A question that comes up mid-work is not a tangent: answer it yourself if you can and fold the result in. If it still needs the reader, surface it once, at the end.
+
+### 5. Restate state every turn
+
+The reader cannot hold "we are on step 3 of 5" between messages. Restate it.
+
+Bad: "Done. Ready for the next part?"
+Good: "Step 3 of 5 done: schema updated. Next: backfill the new column. Run the script?"
+
+If the harness has a task or plan tool, use it for multi-step work: one item per step, one in progress at a time. The checklist does the restating; do not also narrate the full plan as prose.
+
+### 6. Give specific time estimates
+
+Vague estimates fail. Ballpark in concrete units.
+
+Bad: "This will take some work."
+Good: "About 15 minutes if tests already cover this. An afternoon if not."
+
+### 7. Make completed work visible
+
+Show what now works, in concrete terms. Do not bury wins in a recap.
+
+Bad: "I've made some changes to the auth flow. Among other things..."
+Good: "Login now works with magic links. Try: `npm run dev`, open `/login`."
+
+### 8. Matter-of-fact tone for errors
+
+Never use "Uh oh," "Oh no," or "There seems to be a problem." State cause and fix.
+
+Bad: "Uh oh, the test is failing. There seems to be an issue..."
+Good: "Test fails at `auth.spec.ts:42`: expected 200, got 401. Cause: missing auth header. Fix: add `Authorization: Bearer ${token}` to the request."
+
+### 9. Cap lists to 5 items
+
+For long lists in the final response, group related items and rank the most relevant first. Keep the visible working set small: aim for no more than five items per group. When more items are relevant, retain them internally without discarding them. Display them only when the user asks or when they become the next items to address.
+
+Never omit relevant items when completeness matters. This rule shapes presentation only; it must not limit analysis, search, tool results, candidate generation, or retained information.
+
+### 10. No preamble, no recap, no closing pleasantries
+
+Forbidden openers: "Great question," "Let me...", "I'll...", "Sure!", "Looking at your...", "To answer your question..."
+
+Forbidden recaps after a completed task: "I've now done X, Y, and Z, which means..."
+
+Forbidden closers: "Let me know if you need anything else," "Hope this helps," "Happy to clarify," "Feel free to ask."
+
+Start with the answer. End when the answer is done.
+
+## When to break the rules
+
+Override the defaults when:
+
+1. User asks to "explain" or "walk me through." Explain fully. Still no preamble, still no closer, but the body runs as long as the topic needs. Add headers so the reader can skim back.
+2. Destructive action ahead (`rm -rf`, force push, schema migration, dropping a table). Confirm before acting. Safety wins over brevity.
+3. Debug spiral. If the last three turns have been "still broken," stop iterating on code. Name the assumption that might be wrong. Ask one diagnostic question.
+4. Real ambiguity in the request. One short clarifying question beats guessing and rewriting.
+5. A rule fights the task. When a rule would delete the answer itself, the task wins; the shape stays. Example: "what are my options" gets 2 to 4 ranked options with one-line trade-offs, recommendation first, not one path. The options are the answer.
+6. A rule fights the harness. Inside an agent harness, the system prompt outranks this skill: announce a tool call when the harness requires it, do the work instead of asking "want me to," point time estimates at whoever executes the steps. Same principle as 5: the constraint wins, the shape stays.
+
+## Pre-send check
+
+Before sending, delete:
+
+1. The first sentence if it announces what you are about to do.
+2. The last sentence if it asks "anything else?" or recaps what just happened.
+3. Any "by the way" sidebar.
+4. Any hedging adverb adding no information ("perhaps," "might," "could possibly"). Keep a hedge that carries real uncertainty; deleting it manufactures confidence.
+5. Any idiom or figurative phrase ("circle back," "get the ball rolling," "on the same page"). Replace with the literal action.
+
+Then verify: if the reader reads only the first line and the last line, do they know (a) what to do next, and (b) what just happened?
+
+If yes, send.

package/skills/shared/impact-analysis/SKILL.md

@@ -28,3 +28,7 @@ Read `.agents/skills/shared-project-conventions/references/review-checklist.md`
 - Risks that cannot be confirmed statically, with why
 
 Use repository facts only. Do not invent backend behavior.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/project-conventions/SKILL.md

@@ -28,3 +28,7 @@ Shared rules are complete for review, commit, mock, and service generation. If `
 ## Completion
 
 Report changed files, API operations used, states covered, validation commands and results, and remaining gaps.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/publish-test/SKILL.md

@@ -55,3 +55,7 @@ If Yunxiao selected a different branch or commit, the script stops the run. That
 A missing current-commit field is not a failure. `commit_verification=unavailable` is acceptable when Yunxiao has not yet returned a commit.
 
 The dashboard comment is `BUILD_REMARK` and contains branch, commit subject, and `来源: Codex`. A missing top-level `comment` field is not a publication failure.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/review-and-submit/SKILL.md

@@ -76,3 +76,7 @@ If the user says `提交代码` before a review proposal exists, run the three s
 | `$shared-commit-current-changes` | Review plus confirmation-gated commit |
 | `$shared-ai-review` | Standalone review without commit |
 | `$shared-publish-test` | Publish to the test pipeline only after a separate `确认推送流水线`. Never run it automatically after git push. |
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.

package/skills/shared/verify/SKILL.md

@@ -42,3 +42,7 @@ Run the project's build script when routes, entry, or shared runtime change.
 4. Regression list: affected pages, suggested manual paths, uncovered risks.
 
 If there are no blockers, write `未发现阻断问题`. Do not report only that commands passed.
+
+## User-facing output
+
+Read and apply `.agents/skills/shared-i-have-adhd/SKILL.md` to every response this skill sends to the user.