create-yss-spec 3.5.3 → 3.5.4

package/template/.agents/skills/using-git-worktrees/references/git-fallback.md

@@ -0,0 +1,46 @@
+# 手工 Git worktree 创建
+
+仅在入口所列条件命中时读取本文件。Markdown 链接相对本文件；行内 references/assets/schemas 路径相对 Skill 根目录。Git、依赖安装和测试命令从当前仓库或选定的工作树根目录执行。
+
+### 1b. Git Worktree Fallback
+
+**Only use this if Step 1a does not apply** — you have no native worktree tool available. Create a worktree manually using git.
+
+#### Directory Selection
+
+Follow this priority order. Explicit user preference always beats observed filesystem state.
+
+1. **Check your instructions for a declared worktree directory preference.** If the user has already specified one, use it without asking.
+
+2. **Check for an existing project-local worktree directory:**
+   ```bash
+   ls -d .worktrees 2>/dev/null     # Preferred (hidden)
+   ls -d worktrees 2>/dev/null      # Alternative
+   ```
+   If found, use it. If both exist, `.worktrees` wins.
+
+3. **If there is no other guidance available**, default to `.worktrees/` at the project root.
+
+#### Safety Verification (project-local directories only)
+
+**MUST verify directory is ignored before creating worktree:**
+
+```bash
+git check-ignore -q .worktrees 2>/dev/null || git check-ignore -q worktrees 2>/dev/null
+```
+
+**If NOT ignored:** Add the chosen directory to .gitignore within the authorized setup scope, verify it is ignored, then proceed. Leave that edit uncommitted unless Git commit authorization already covers it.
+
+**Why critical:** Prevents accidentally committing worktree contents to repository.
+
+#### Create the Worktree
+
+```bash
+# Determine path based on chosen location
+path="$LOCATION/$BRANCH_NAME"
+
+git worktree add "$path" -b "$BRANCH_NAME"
+cd "$path"
+```
+
+**Isolation failure:** If worktree creation is blocked, report the actual error and preserve the current checkout. Use another already authorized isolated location when available; ask only if proceeding would change the requested isolation boundary. Do not silently begin implementation in the original checkout.

package/template/.agents/skills/using-git-worktrees/references/setup-and-baseline.md

@@ -0,0 +1,45 @@
+# 项目准备与基线验证
+
+仅在入口所列条件命中时读取本文件。Markdown 链接相对本文件；行内 references/assets/schemas 路径相对 Skill 根目录。Git、依赖安装和测试命令从当前仓库或选定的工作树根目录执行。
+
+## Step 2: Project Setup
+
+Auto-detect and run appropriate setup:
+
+```bash
+# Node.js: inspect packageManager, lockfile and project instructions first.
+# In a pnpm project, use the recorded version and frozen lockfile:
+# pnpm install --frozen-lockfile
+# Use npm/yarn only when the repository actually declares them.
+
+# Rust
+if [ -f Cargo.toml ]; then cargo build; fi
+
+# Python
+if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+if [ -f pyproject.toml ]; then poetry install; fi
+
+# Go
+if [ -f go.mod ]; then go mod download; fi
+```
+
+## Step 3: Verify Clean Baseline
+
+Run tests to ensure workspace starts clean:
+
+```bash
+# Use project-appropriate command
+pnpm test / cargo test / pytest / go test ./... # select the declared project runner
+```
+
+**If tests fail:** Record the existing failure and investigate within the authorized scope. Ask only if a new decision or access is needed; do not label the baseline clean.
+
+**If tests pass:** Report ready.
+
+### Report
+
+```
+Worktree ready at <full-path>
+Tests passing (<N> tests, 0 failures)
+Ready to implement <feature-name>
+```

package/template/.agents/skills/using-git-worktrees/references/troubleshooting.md

@@ -0,0 +1,47 @@
+# 工作树常见错误
+
+仅在入口所列条件命中时读取本文件。Markdown 链接相对本文件；行内 references/assets/schemas 路径相对 Skill 根目录。Git、依赖安装和测试命令从当前仓库或选定的工作树根目录执行。
+
+## Quick Reference
+
+| Situation | Action |
+|-----------|--------|
+| Already in linked worktree | Skip creation (Step 0) |
+| In a submodule | Treat as normal repo (Step 0 guard) |
+| Native worktree tool available | Use it (Step 1a) |
+| No native tool | Git worktree fallback (Step 1b) |
+| `.worktrees/` exists | Use it (verify ignored) |
+| `worktrees/` exists | Use it (verify ignored) |
+| Both exist | Use `.worktrees/` |
+| Neither exists | Check instruction file, then default `.worktrees/` |
+| Directory not ignored | Add to .gitignore; commit only when authorized |
+| Permission error on create | Report failure; preserve the requested isolation boundary |
+| Tests fail during baseline | Record failures; continue authorized diagnosis |
+| No package.json/Cargo.toml | Skip dependency install |
+
+## Common Mistakes
+
+### Fighting the harness
+
+- **Problem:** Using `git worktree add` when the platform already provides isolation
+- **Fix:** Step 0 detects existing isolation. Step 1a defers to native tools.
+
+### Skipping detection
+
+- **Problem:** Creating a nested worktree inside an existing one
+- **Fix:** Always run Step 0 before creating anything
+
+### Skipping ignore verification
+
+- **Problem:** Worktree contents get tracked, pollute git status
+- **Fix:** Always use `git check-ignore` before creating project-local worktree
+
+### Assuming directory location
+
+- **Problem:** Creates inconsistency, violates project conventions
+- **Fix:** Follow priority: explicit instructions > existing project-local directory > default
+
+### Proceeding with failing tests
+
+- **Problem:** Can't distinguish new bugs from pre-existing issues
+- **Fix:** Distinguish baseline failures from new defects; ask only for a missing decision

package/template/.agents/skills/wayfinder/SKILL.md

@@ -26,81 +26,17 @@ The map is an **index**, not a store. It lists the decisions made and points at
 
 **Where the map, its child tickets, blocking, and frontier queries physically live is tracker-specific.** The issue tracker should have been provided to you. If not, tell the user to run `/setup-matt-pocock-skills`. Consult the tracker doc's "Wayfinding operations" section for how _this_ repo expresses them. If no tracker has been provided, default to the local-markdown tracker.
 
-### The map body
+### Map and ticket format
 
-The whole map at low resolution, loaded once per session. Open tickets are **not** listed — they are open child issues, found by query.
-
-```markdown
-## Destination
-
-<what reaching the end of this map looks like — the spec, decision, or change this effort is finding its way to. One or two lines; every session orients to it before choosing a ticket.>
-
-## Notes
-
-<domain; skills every session should consult; standing preferences for this effort>
-
-## Decisions so far
-
-<!-- the index — one line per closed ticket: enough to judge relevance, then zoom the link for the detail the ticket holds -->
-
-- [<closed ticket title>](link) — <one-line gist of the answer>
-
-## Not yet specified
-
-<!-- see "Fog of war": in-scope fog you can't ticket yet; graduates as the frontier advances -->
-
-## Out of scope
-
-<!-- see "Out of scope": work ruled beyond the destination; closed, never graduates -->
-```
-
-### Tickets
-
-Each ticket is a **child issue** of the map; the tracker's issue id is its identity. Its body is the question, bounded by a coherent decision and the current runtime/context capacity:
-
-```markdown
-## Question
-
-<the decision or investigation this ticket resolves>
-```
-
-Each ticket carries a `wayfinder:<type>` label — one of `research`, `prototype`, `grilling`, `task` (see [Ticket Types](#ticket-types)).
-
-A session **claims** a ticket by assigning it to the dev driving the map, **first**, before any work, so concurrent sessions skip it. That assignee _is_ the claim: an open, unassigned ticket is unclaimed.
-
-Blocking uses the tracker's **native** dependency relationship — essential because it renders the frontier _visually_ in the tracker's own UI, so the human sees what's takeable without opening the map. Only a tracker that lacks native blocking falls back to a body convention. A ticket is **unblocked** when every ticket blocking it is closed; the **frontier** is the open, unblocked, unclaimed children — the edge of the known.
-
-The answer isn't part of the body — it's recorded on resolution (see [Work through the map](#work-through-the-map)). Assets created while resolving a ticket are linked from the issue, not pasted in.
+创建或更新地图 / Ticket 时读取 [资产结构](references/map-format.md)。地图只索引决定，详情留在 Ticket；先认领再处理，以原生依赖表示阻塞。
 
 ## Ticket Types
 
-Every ticket is either **HITL** — human in the loop, worked _with_ a human who speaks for themselves — or **AFK**, driven by the agent alone. A HITL ticket only resolves through that live exchange; the agent never stands in for the human's side of it (a grilling agent that answers its own questions has broken this).
-
-- **Research** (AFK): Reading documentation, third-party APIs, or local resources like knowledge bases to surface a fact a decision waits on. Resolved by a `/yss-research` **subagent** (`/research` is a deprecated alias). Use when knowledge outside the current working directory is required.
-- **Prototype** (HITL): Raise the fidelity of the discussion by making a cheap, rough, concrete artifact to react to — an outline, a rough take, a stub, or UI/logic code via the /prototype skill. Links the prototype as an asset. Use when "how should it look" or "how should it behave" is the key question.
-- **Grilling** (HITL): Conversation. The default case. Always invoke the /grilling and /domain-modeling skills.
-- **Task** (HITL or AFK): Manual work that must happen before a _decision_ can be made — nothing to decide, prototype, or research, but the discussion is blocked until it's done. Signing up for a service so its API can be judged, provisioning access, moving data so its shape can be seen. This is the one type that _does_ rather than decides — and it earns its place by unblocking a decision, not by delivering the destination. The agent drives it alone where it can (AFK); otherwise it hands the human a precise checklist (HITL). Resolved when the work is done; the answer records what was done and any resulting facts (credentials location, new URLs, row counts) later tickets depend on.
-
-## Fog of war
-
-The map is _deliberately_ incomplete: don't chart what you can't yet see. Beyond the live tickets lies the **fog of war** — the dim view of decisions and investigations you can tell are coming but can't yet pin down, because they hang on questions still open. Resolving a ticket clears the fog ahead of it, graduating whatever's now specifiable into fresh tickets — one at a time, until the way to the destination is clear and no tickets remain.
-
-The map's **Not yet specified** section is where that dim view is written down: the suspected question, the area to revisit later. It's the undiscovered frontier _toward_ the destination — everything here is in scope, just not sharp enough to ticket. Write as loosely or as fully as the view allows; it doubles as a signpost for collaborators reading where the effort is headed.
-
-**Fog or ticket?** The test is whether you can state the question precisely now — _not_ whether you can answer it now.
+选择或处理 Ticket 类型时，读取 [类型与参与方式](references/ticket-types.md)。Research 为 AFK；Prototype / Grilling 为 HITL，真实用户回复不能由 Agent 代答；Task 只为解除决定阻塞。
 
-- **Ticket when** the question is already sharp — even if it's blocked and you can't act on it yet.
-- **Not yet specified when** you can't yet phrase it that sharply. Don't pre-slice the fog into ticket-sized pieces: it's coarser than a ticket, and one patch may graduate into several tickets, or none, once the frontier reaches it.
+## Scope and frontier
 
-**Not yet specified** excludes what's already decided (Decisions so far), what's already a live ticket, and what's out of scope (the next section).
-
-## Out of scope
-
-Fog only ever gathers _toward_ the destination. The destination fixes the scope, so work beyond it is **out of scope** — it isn't fog, and it doesn't belong in **Not yet specified**. It gets its own **Out of scope** section on the map: work you've consciously ruled out of _this_ effort. Scope, not sharpness, lands it here.
-
-Out-of-scope work never graduates — the frontier stops at the destination — so it returns only if the destination is redrawn, and then as a fresh effort, not a resumption.
-
-Ruling something out of scope is a scoping act, not a step on the route. When a ticket that already exists turns out to sit past the destination — mis-scoped in while charting, or exposed by a resolution — **close it** (a closed ticket is unambiguously off the frontier) and leave one line in the **Out of scope** section: the gist plus why it's out of scope, linking the closed ticket. It stays out of **Decisions so far**, which records the route actually walked — a scope boundary isn't a step on it.
+划分未知范围、生成新 Ticket 或剔除越界工作时，读取 [范围与决策前沿](references/scope-and-frontier.md)。能明确提问的工作可成票；范围外工作不作为待细化事项。
 
 ## Invocation
 
@@ -108,23 +44,8 @@ Two modes. Keep each decision traceable and stop at a real dependency, decision
 
 ### Chart the map
 
-User invokes with a loose idea.
-
-1. **Name the destination.** Run a `/grilling` and `/domain-modeling` session to pin down what this map is finding its way to — the spec, decision, or change. The destination fixes the scope, so it's settled first.
-2. **Map the frontier.** Grill again, **breadth-first** this time: fan out across the whole space rather than deep on any one thread, surfacing the open decisions and the first steps takeable now. **If this surfaces no fog** — the way to the destination is already clear, the whole journey small enough for one session — you don't need a map. Stop and ask the user how they'd like to proceed.
-3. **Create the map** (label `wayfinder:map`): Destination and Notes filled in, Decisions-so-far empty, the fog sketched into **Not yet specified**.
-4. **Create the tickets you can specify now** as child issues of the map — then wire blocking edges in a **second pass** (issues need ids before they can reference each other). Wiring sorts them into the frontier and the blocked; everything you can't yet specify stays in the fog — the **Not yet specified** section.
-5. **Fire the research subagents.** For each `research` ticket you just created, spin up a `/yss-research` subagent to resolve it in parallel, capturing its findings on a throwaway `research/<name>` branch with a context pointer from the ticket. `/research` remains only as a deprecated compatibility alias.
-6. Stop — charting is one session's work; it hand-resolves nothing.
+用户给出模糊想法、尚无地图时，读取 [建立地图](references/chart-map.md)。先确认目标和范围，再创建可明确提问的 Ticket；建立地图不代替执行。
 
 ### Work through the map
 
-User invokes with a map (URL or number). A ticket is **optional** — without one, you pick the next decision, not the user.
-
-1. Load the **map** — the low-res view, not every ticket body.
-2. Choose the ticket. If the user named one, use it. Otherwise take the first frontier ticket in order. **Claim it**: assign it to yourself before any work.
-3. Resolve it — **zoom as needed**: fetch the full body of any related or closed ticket on demand; invoke the skills the `## Notes` block names. If in doubt, use `/grilling` and `/domain-modeling`.
-4. Record the resolution: post the answer as a **resolution comment**, **close** the issue, and **append a context pointer** to the map's Decisions-so-far.
-5. Add newly-surfaced tickets (create-then-wire); graduate any fog the answer has made specifiable, clearing each graduated patch from **Not yet specified** so it lives only as its new ticket. If the answer reveals a ticket — this one or another — sits beyond the destination, **rule it out of scope** rather than resolving it on the route. If the decision invalidates other parts of the map, update or delete those tickets.
-
-The user may run unblocked tickets in parallel, so expect other sessions to be editing the tracker concurrently.
+用户给出已有地图时，读取 [推进地图](references/work-map.md)。先加载地图再认领一个未阻塞的决定，相关 Ticket 详情按需读取；完成后记录决定并更新前沿。

package/template/.agents/skills/wayfinder/references/chart-map.md

@@ -0,0 +1,14 @@
+# 建立决策地图
+
+仅在入口所列条件命中时读取本文件。Markdown 链接相对本文件；行内 references/assets/schemas 路径相对 Skill 根目录。仓库脚本与 pnpm 命令从当前登记的项目根目录执行。
+
+### Chart the map
+
+User invokes with a loose idea.
+
+1. **Name the destination.** Run a `/grilling` and `/domain-modeling` session to pin down what this map is finding its way to — the spec, decision, or change. The destination fixes the scope, so it's settled first.
+2. **Map the frontier.** Grill again, **breadth-first** this time: fan out across the whole space rather than deep on any one thread, surfacing the open decisions and the first steps takeable now. **If this surfaces no fog** — the way to the destination is already clear, the whole journey small enough for one session — you don't need a map. Stop and ask the user how they'd like to proceed.
+3. **Create the map** (label `wayfinder:map`): Destination and Notes filled in, Decisions-so-far empty, the fog sketched into **Not yet specified**.
+4. **Create the tickets you can specify now** as child issues of the map — then wire blocking edges in a **second pass** (issues need ids before they can reference each other). Wiring sorts them into the frontier and the blocked; everything you can't yet specify stays in the fog — the **Not yet specified** section.
+5. **Fire the research subagents.** For each `research` ticket you just created, spin up a `/yss-research` subagent to resolve it in parallel, capturing its findings on a throwaway `research/<name>` branch with a context pointer from the ticket. `/research` remains only as a deprecated compatibility alias.
+6. Stop — charting is one session's work; it hand-resolves nothing.

package/template/.agents/skills/wayfinder/references/map-format.md

@@ -0,0 +1,49 @@
+# 决策地图与 Ticket 结构
+
+仅在入口所列条件命中时读取本文件。Markdown 链接相对本文件；行内 references/assets/schemas 路径相对 Skill 根目录。仓库脚本与 pnpm 命令从当前登记的项目根目录执行。
+
+### The map body
+
+The whole map at low resolution, loaded once per session. Open tickets are **not** listed — they are open child issues, found by query.
+
+```markdown
+## Destination
+
+<what reaching the end of this map looks like — the spec, decision, or change this effort is finding its way to. One or two lines; every session orients to it before choosing a ticket.>
+
+## Notes
+
+<domain; skills every session should consult; standing preferences for this effort>
+
+## Decisions so far
+
+<!-- the index — one line per closed ticket: enough to judge relevance, then zoom the link for the detail the ticket holds -->
+
+- [<closed ticket title>](../link) — <one-line gist of the answer>
+
+## Not yet specified
+
+<!-- see "Fog of war": in-scope fog you can't ticket yet; graduates as the frontier advances -->
+
+## Out of scope
+
+<!-- see "Out of scope": work ruled beyond the destination; closed, never graduates -->
+```
+
+### Tickets
+
+Each ticket is a **child issue** of the map; the tracker's issue id is its identity. Its body is the question, bounded by a coherent decision and the current runtime/context capacity:
+
+```markdown
+## Question
+
+<the decision or investigation this ticket resolves>
+```
+
+Each ticket carries a `wayfinder:<type>` label — one of `research`, `prototype`, `grilling`, `task` (see [Ticket Types](ticket-types.md#ticket-types)).
+
+A session **claims** a ticket by assigning it to the dev driving the map, **first**, before any work, so concurrent sessions skip it. That assignee _is_ the claim: an open, unassigned ticket is unclaimed.
+
+Blocking uses the tracker's **native** dependency relationship — essential because it renders the frontier _visually_ in the tracker's own UI, so the human sees what's takeable without opening the map. Only a tracker that lacks native blocking falls back to a body convention. A ticket is **unblocked** when every ticket blocking it is closed; the **frontier** is the open, unblocked, unclaimed children — the edge of the known.
+
+The answer isn't part of the body — it's recorded on resolution (see [Work through the map](work-map.md#work-through-the-map)). Assets created while resolving a ticket are linked from the issue, not pasted in.

package/template/.agents/skills/wayfinder/references/scope-and-frontier.md

@@ -0,0 +1,24 @@
+# 范围与决策前沿
+
+仅在入口所列条件命中时读取本文件。Markdown 链接相对本文件；行内 references/assets/schemas 路径相对 Skill 根目录。仓库脚本与 pnpm 命令从当前登记的项目根目录执行。
+
+## Fog of war
+
+The map is _deliberately_ incomplete: don't chart what you can't yet see. Beyond the live tickets lies the **fog of war** — the dim view of decisions and investigations you can tell are coming but can't yet pin down, because they hang on questions still open. Resolving a ticket clears the fog ahead of it, graduating whatever's now specifiable into fresh tickets — one at a time, until the way to the destination is clear and no tickets remain.
+
+The map's **Not yet specified** section is where that dim view is written down: the suspected question, the area to revisit later. It's the undiscovered frontier _toward_ the destination — everything here is in scope, just not sharp enough to ticket. Write as loosely or as fully as the view allows; it doubles as a signpost for collaborators reading where the effort is headed.
+
+**Fog or ticket?** The test is whether you can state the question precisely now — _not_ whether you can answer it now.
+
+- **Ticket when** the question is already sharp — even if it's blocked and you can't act on it yet.
+- **Not yet specified when** you can't yet phrase it that sharply. Don't pre-slice the fog into ticket-sized pieces: it's coarser than a ticket, and one patch may graduate into several tickets, or none, once the frontier reaches it.
+
+**Not yet specified** excludes what's already decided (Decisions so far), what's already a live ticket, and what's out of scope (the next section).
+
+## Out of scope
+
+Fog only ever gathers _toward_ the destination. The destination fixes the scope, so work beyond it is **out of scope** — it isn't fog, and it doesn't belong in **Not yet specified**. It gets its own **Out of scope** section on the map: work you've consciously ruled out of _this_ effort. Scope, not sharpness, lands it here.
+
+Out-of-scope work never graduates — the frontier stops at the destination — so it returns only if the destination is redrawn, and then as a fresh effort, not a resumption.
+
+Ruling something out of scope is a scoping act, not a step on the route. When a ticket that already exists turns out to sit past the destination — mis-scoped in while charting, or exposed by a resolution — **close it** (a closed ticket is unambiguously off the frontier) and leave one line in the **Out of scope** section: the gist plus why it's out of scope, linking the closed ticket. It stays out of **Decisions so far**, which records the route actually walked — a scope boundary isn't a step on it.

package/template/.agents/skills/wayfinder/references/ticket-types.md

@@ -0,0 +1,12 @@
+# 决策 Ticket 类型
+
+仅在入口所列条件命中时读取本文件。Markdown 链接相对本文件；行内 references/assets/schemas 路径相对 Skill 根目录。仓库脚本与 pnpm 命令从当前登记的项目根目录执行。
+
+## Ticket Types
+
+Every ticket is either **HITL** — human in the loop, worked _with_ a human who speaks for themselves — or **AFK**, driven by the agent alone. A HITL ticket only resolves through that live exchange; the agent never stands in for the human's side of it (a grilling agent that answers its own questions has broken this).
+
+- **Research** (AFK): Reading documentation, third-party APIs, or local resources like knowledge bases to surface a fact a decision waits on. Resolved by a `/yss-research` **subagent** (`/research` is a deprecated alias). Use when knowledge outside the current working directory is required.
+- **Prototype** (HITL): Raise the fidelity of the discussion by making a cheap, rough, concrete artifact to react to — an outline, a rough take, a stub, or UI/logic code via the /prototype skill. Links the prototype as an asset. Use when "how should it look" or "how should it behave" is the key question.
+- **Grilling** (HITL): Conversation. The default case. Always invoke the /grilling and /domain-modeling skills.
+- **Task** (HITL or AFK): Manual work that must happen before a _decision_ can be made — nothing to decide, prototype, or research, but the discussion is blocked until it's done. Signing up for a service so its API can be judged, provisioning access, moving data so its shape can be seen. This is the one type that _does_ rather than decides — and it earns its place by unblocking a decision, not by delivering the destination. The agent drives it alone where it can (AFK); otherwise it hands the human a precise checklist (HITL). Resolved when the work is done; the answer records what was done and any resulting facts (credentials location, new URLs, row counts) later tickets depend on.

package/template/.agents/skills/wayfinder/references/work-map.md

@@ -0,0 +1,15 @@
+# 推进决策地图
+
+仅在入口所列条件命中时读取本文件。Markdown 链接相对本文件；行内 references/assets/schemas 路径相对 Skill 根目录。仓库脚本与 pnpm 命令从当前登记的项目根目录执行。
+
+### Work through the map
+
+User invokes with a map (URL or number). A ticket is **optional** — without one, you pick the next decision, not the user.
+
+1. Load the **map** — the low-res view, not every ticket body.
+2. Choose the ticket. If the user named one, use it. Otherwise take the first frontier ticket in order. **Claim it**: assign it to yourself before any work.
+3. Resolve it — **zoom as needed**: fetch the full body of any related or closed ticket on demand; invoke the skills the `## Notes` block names. If in doubt, use `/grilling` and `/domain-modeling`.
+4. Record the resolution: post the answer as a **resolution comment**, **close** the issue, and **append a context pointer** to the map's Decisions-so-far.
+5. Add newly-surfaced tickets (create-then-wire); graduate any fog the answer has made specifiable, clearing each graduated patch from **Not yet specified** so it lives only as its new ticket. If the answer reveals a ticket — this one or another — sits beyond the destination, **rule it out of scope** rather than resolving it on the route. If the decision invalidates other parts of the map, update or delete those tickets.
+
+The user may run unblocked tickets in parallel, so expect other sessions to be editing the tracker concurrently.

package/template/.agents/skills/writing-for-agents/SKILL-MECHANICS.md

@@ -1,22 +1,31 @@
 # Skill mechanics
 
-The skill-specific branch of [`writing-for-agents`](SKILL.md): what changes when the document is a skill — frontmatter, the invocation choice, and router skills. Everything else about writing it is the universal reference in `SKILL.md`.
+Read this reference when designing a skill's invocation policy or shared dependencies. The host repository owns authorization and lifecycle rules; runtime metadata expresses only the capabilities that the installed host actually supports.
 
-## Invocation
+## Keep the decisions separate
 
-Two choices, trading the two loads:
+- **Discovery** makes an entry available through a catalog, description or explicit command. Keep the required `name` and `description` even when automatic selection is disabled.
+- **Automatic selection** lets the model choose a relevant entry. A precise description helps selection; it does not grant permission to run commands or change files.
+- **Explicit invocation** follows the host's supported user entry. Do not assume that a natural-language mention and a slash command behave identically on every host.
+- **Reading dependencies** loads an authorized reference or shared contract. Disabling automatic selection does not by itself make that file unreadable.
+- **Executing actions** still requires the repository's current scope, prerequisites and user authorization. Reading a commit contract does not authorize a commit.
 
-- A **model-invoked** skill keeps a `description`, so the agent can fire it autonomously — and other skills can reach it. You can still type its name: model-invocation always _includes_ user reach; a description only ever adds agent discovery, never removes the human's. The description is the skill's top-level context pointer, forced to stay loaded at all times — permanent context load in exchange for discoverability. A model-invoked skill whose content is all reference is also one home for shared reference: another skill can invoke it, so reference needed by several skills lives in one place. Mechanics: omit `disable-model-invocation`, and write a model-facing description carrying the trigger branches (the pointer-writing rules in `SKILL.md` apply in full).
-- A **user-invoked** skill strips the description from the agent's reach: only the human typing its name can invoke it, and no other skill can. Zero context load, but it spends cognitive load — you are the index that must remember it exists. Mechanics: set `disable-model-invocation: true`; the `description` becomes human-facing — a one-line summary, trigger lists stripped.
+## Express policy for the target host
 
-Pick model-invocation only when the agent must reach the skill on its own, or another skill must. If it only ever fires by hand, make it user-invoked and pay no context load.
+`description`, `disable-model-invocation` and `agents/openai.yaml` are not interchangeable controls. The frontmatter field is interpreted by hosts that support it; Codex has its own `policy.allow_implicit_invocation` metadata. A generated projection proves that files were distributed, not that another host enforces the same policy.
 
-Shared reference that two user-invoked skills both need can live in neither — with no descriptions, neither can fire the other. Push it to a plain file outside the skill system: external reference any skill can point at.
+For YSS registry and metadata consistency, use [the maintained authoring contract](../maintaining-skills/references/authoring.md). Preserve existing interface and dependency metadata. Verify the actual installed host's catalog and invocation behavior; record unsupported or unknown capabilities instead of treating an ignored field as enforcement.
 
-## Splitting by invocation
+Do not claim that a description is always loaded, that explicit-only skills have zero context cost, or that a policy field is a filesystem sandbox. Measure observable reads and runtime usage for the task being optimized, and leave absent telemetry unknown.
 
-The invocation cut of splitting (the sequence cut lives in `SKILL.md`): split off a model-invoked skill when you have a distinct leading word that should trigger it on its own — a trigger word you actually use in your prompts — or another skill must reach it. You pay context load for the new always-loaded description, so that independent reach has to be worth it.
+## Share references without adding unintended entry points
 
-## Router skills
+An authorized public skill may read an internal contract by its registered path while that internal skill remains excluded from independent automatic selection. The YSS commit skills use this pattern with `git-commit-core`. Retain the public caller's action-authorization boundary and the dependency's ownership and distribution rules.
 
-When user-invoked skills multiply past what you can remember, that piled-up cognitive load is cured by a **router skill**: one user-invoked skill that names the others and when to reach for each, so the human has one skill to remember instead of many. It can only hint, never fire them: user-invoked skills have no description, so nothing but the human can reach them.
+Put shared material in a plain reference file or an internal skill according to its ownership and consumers. Neither location requires a new automatic workflow. Preserve the dependency closure, and do not publish a second copy that can drift independently.
+
+## Split and route by responsibility
+
+Create a separate discoverable skill when it has a distinct task, trigger and useful outcome. Move conditional detail into references when it serves the same task. Avoid mechanical splits based on leading words, length or assumptions about permanent context load.
+
+A router can explain which entry or reference applies. It must preserve host-specific explicit-invocation requirements and the repository's approval boundaries; routing alone cannot grant execution authority. Check a natural-language positive, a nearby non-trigger, explicit invocation and any affected dependency or authorization boundary.

package/template/.agents/skills/yedit-table-usage/SKILL.md

@@ -39,178 +39,11 @@ description: "配置或修复 YSS UI YEditTable 的行内编辑、候选联动
 - 自适应高度使用 `useTableHeight(tableAreaRef, options)` 并绑定 `:height="tableHeight"`；直接父容器必须可计算且设置 `min-height: 0`。若表格内容会反向撑开观察容器，改用稳定 `boundaryRef`；弹层展开后高度仍不准时才调用 `nextTick(recalculateHeight)`。
 - API 失败由 `mutator.ts` 统一提示并 reject。Hook 中不写 `success === false` 分支，不在 `else/catch` 重复 `message.error`；清理状态放在 `finally`。
 
-## 标准代码骨架
-
-```typescript
-import type { YEditTableColumn, YTableActionConfig } from '@yss-ui/components';
-
-/** 扩展属性行。 */
-export interface ExtRow {
-  id?: string;
-  _rowKey: string;
-  extName?: string;
-  extValues?: string[];
-  memo?: string;
-}
-
-/** 可编辑表格列。 */
-export const EDIT_COLUMNS: YEditTableColumn[] = [
-  {
-    field: 'extName',
-    title: '扩展属性',
-    minWidth: 220,
-    component: 'form-item-select',
-    props: { placeholder: '请选择扩展属性' },
-    customRule: (value, _row, _field, all) => {
-      if (!value) return { errMsg: '扩展属性不能为空' };
-      if (all.filter(item => item.extName === value).length > 1) return { errMsg: '扩展属性不能重复' };
-      return {};
-    },
-  },
-  {
-    field: 'extValues',
-    title: '扩展值',
-    minWidth: 240,
-    component: 'form-item-select',
-    props: { multiple: true, placeholder: '请选择扩展值' },
-    customRule: value =>
-      Array.isArray(value) && value.some(item => String(item).length > 100)
-        ? { errMsg: '单个扩展值最多 100 个字符' }
-        : {},
-  },
-  {
-    field: 'memo',
-    title: '备注',
-    minWidth: 240,
-    component: 'form-item-input',
-    props: { placeholder: '请输入备注' },
-    customRule: value => (String(value ?? '').length > 200 ? { errMsg: '最多 200 个字符' } : {}),
-  },
-  { type: 'action', title: '操作', width: 100, fixed: 'right' },
-];
-
-/** 表格字典数据；实际项目可由 Hook 响应式提供。 */
-export const EDIT_OPTIONS_MAP = {
-  extName: [
-    { label: '类型', value: 'type' },
-    { label: '级别', value: 'level' },
-  ],
-  extValues: [
-    { label: '默认', value: 'default' },
-    { label: '扩展', value: 'extended' },
-  ],
-};
-
-/** 创建前端新行。 */
-export const createEmptyRow = (): ExtRow => ({
-  _rowKey: `temp-${Date.now()}-${Math.random().toString(36).slice(2)}`,
-  extValues: [],
-});
-
-/** 创建带删除确认的操作配置。 */
-export const createActionConfig = (onDelete: (row: ExtRow) => void): YTableActionConfig => ({
-  buttons: [
-    {
-      value: 'delete',
-      label: '删除',
-      type: 'link',
-      isConfirm: true,
-      confirmProps: { title: '是否确认删除此条数据？', okText: '确定', cancelText: '取消' },
-      click: ({ row }) => onDelete(row),
-    },
-  ],
-});
-```
-
-```vue
-<script setup lang="ts">
-import { computed, ref } from 'vue';
-import { YEditTable } from '@yss-ui/components';
-import { createActionConfig, createEmptyRow, EDIT_COLUMNS, EDIT_OPTIONS_MAP, type ExtRow } from './constant';
-
-/** 组件模式。0-新增，1-编辑，2-查看。 */
-interface Props {
-  mode: 0 | 1 | 2;
-}
-
-const props = defineProps<Props>();
-const rows = ref<ExtRow[]>([]);
-const tableRef = ref<InstanceType<typeof YEditTable>>();
-const readonly = computed(() => props.mode === 2);
-const columns = computed(() => (readonly.value ? EDIT_COLUMNS.filter(column => column.type !== 'action') : EDIT_COLUMNS));
-const actionConfig = createActionConfig(row => {
-  rows.value = rows.value.filter(item => item._rowKey !== row._rowKey);
-});
-
-/** 处理组件 add 事件，显式更新 v-model:data。 */
-const handleAddRow = () => {
-  rows.value = [...rows.value, createEmptyRow()];
-};
-
-/** 校验全部编辑行。 */
-const validateRows = async (): Promise<boolean> => {
-  if (!tableRef.value) return false;
-  const { valid } = await tableRef.value.validate();
-  return valid;
-};
-</script>
-
-<template>
-  <YEditTable
-    ref="tableRef"
-    v-model:data="rows"
-    :columns="columns"
-    :action-config="actionConfig"
-    :options-map="EDIT_OPTIONS_MAP"
-    :row-config="{ keyField: '_rowKey', useKey: true }"
-    :table-config="{ editConfig: { trigger: 'click', mode: 'row', autoClear: false } }"
-    :disabled="readonly"
-    :addable="!readonly"
-    add-btn-text="添加一行"
-    add-position="bottom"
-    @add="handleAddRow"
-  />
-</template>
-
-<style scoped lang="less">
-@import './style.less';
-</style>
-```
-
-## Select 值类型边界
-
-```typescript
-/** allowCreate 对应 tags 模式，字段按数组存储。 */
-interface CreatableRow {
-  tags?: string[];
-}
-
-const creatableColumn: YEditTableColumn = {
-  field: 'tags',
-  title: '标签',
-  component: 'form-item-select',
-  props: { allowCreate: true, placeholder: '请选择或输入标签' },
-};
-```
-
-## 表头筛选
-
-```typescript
-const textFilterColumn: YEditTableColumn = {
-  field: 'columnName',
-  title: '目标列名称',
-  component: 'form-item-input',
-  filterable: true,
-  filters: [{ data: '' }],
-  filterMethod: ({ option, cellValue }) =>
-    String(cellValue ?? '').toLowerCase().includes(String(option?.data ?? '').trim().toLowerCase()),
-  filterRender: { name: 'VxeInput', props: { clearable: true, placeholder: '请输入关键词' } },
-};
-```
-
-- 远程筛选监听 `@filter-change`，并设置 `filterMethod: () => true` 禁用本地二次筛选。
-- 切换数据源或新增行后，可调用 `tableRef.value?.getTableInstance()?.clearFilter()`。
-- 只在面板高度定制时使用 `#<field>-filter`；修改 `option.data` 后调用 `updateFilterOptionStatus(option, !!option.data)` 同步状态。
+## 按需示例
+
+首次组织可编辑明细行、查看态或提交校验时，读取 [完整组合示例](references/editable-table-example.md)。
+
+需要可创建 Select 或表头筛选时，读取 [Select 与筛选示例](references/select-and-filter-examples.md)；行级候选与表头筛选仍是不同职责。
 
 ## 交付检查清单