create-yss-spec 1.1.4 → 2.0.0

package/template/.agents/skills/writing-great-skills/GLOSSARY.md

@@ -0,0 +1,201 @@
+# Glossary — Building Great Skills
+
+The domain model for what makes a skill great. A skill exists to wrangle determinism out of a stochastic system; the root virtue is **Predictability**, and every term below is a lever on it. This is the disclosed reference for [`writing-great-skills`](SKILL.md).
+
+The terms are grouped by axis: **Invocation** (how a skill is reached), **Information Hierarchy** (how its content is arranged), **Steering** (how the agent's runtime behaviour is shaped), and **Pruning** (how it is kept lean). Each **failure mode** lives beside the lever that cures it, tagged _failure mode_.
+
+**Bold terms** in any definition are themselves defined in this glossary; find them by their heading.
+
+## Predictability
+
+The degree to which a skill makes the agent behave the same _way_ on every run — the same process, not the same output (a brainstorming skill should _predictably_ diverge; its tokens vary, its behaviour doesn't). The root virtue every other term serves — cost and maintainability are symptoms of it, not rivals.
+
+_Avoid_: consistency, reliability, robustness, output-determinism
+
+## Invocation
+
+How a skill is reached — and the two loads you pay for the choice.
+
+### Model-Invoked
+
+A skill that keeps its **description** field, so the agent can see it and fire it autonomously — and the human can still type its name, so model-invocation always _includes_ user reach. There is no model-only state: a description only ever _adds_ agent discovery, never removes the human's. Pays a permanent **context load** on every turn in exchange for that discoverability. Reachable by other skills, because the description that makes it agent-discoverable makes it invocable. 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. Pick model-invocation only when the agent must reach the skill on its own; if it never fires except by hand, drop the description and pay no context load.
+
+_Avoid_: ability, tool, capability
+
+### User-Invoked
+
+A skill with its **description** stripped — invisible to the agent and reachable only by the human typing its name (user-_only_, where **model-invoked** is user-_and-agent_). Trades agent-discoverability for zero **context load**. Because it has no description, nothing but the human can reach it: no other skill can fire it.
+
+_Avoid_: procedure, workflow, command
+
+### Description
+
+The skill's machine-readable trigger, and the one **context pointer** a **model-invoked** skill is forced to keep loaded at all times. Its mere presence _is_ the invocation axis: keep it and the skill is model-invoked (and reachable by other skills); delete it and the skill is **user-invoked**, reachable only by the human. The source of a model-invoked skill's **context load**.
+
+_Avoid_: frontmatter, summary
+
+### Context Pointer
+
+A reference held in the agent's context that names some out-of-context material and encodes the condition for reaching it. The **description** is the top-level context pointer (context window → skill); pointers to disclosed files are the same object one level down. Its wording, not the target, decides _when_ the agent reaches — and _how reliably_. A must-have target behind a weakly worded pointer is a variance bug: fix the wording first, and inline the material only if sharpening fails.
+
+_Avoid_: link, reference, import
+
+### Context Load
+
+The cost a **model-invoked** skill imposes on the agent's context window — its **description**, always loaded, spending both tokens and attention. What **user-invoked** skills escape by having no description, and the brake on splitting into more model-invoked skills.
+
+_Avoid_: token cost, context bloat
+
+### Cognitive Load
+
+The cost a **user-invoked** skill imposes on the human — what they must hold in their head: which skills exist and when to reach for each (the human is the index). What **model-invocation** removes by being agent-discoverable, and the brake on splitting into more user-invoked skills. Not a cost to minimise: it is the price of human agency, the reason some skills stay user-invoked. Spend it where human judgement matters; remove it where it does not.
+
+_Avoid_: human index, burden, overhead
+
+### Router Skill
+
+A **user-invoked** skill whose job is to point at your other user-invoked skills — naming each and when to reach for it — 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. The cure for **cognitive load** when user-invoked skills multiply.
+
+_Avoid_: dispatcher, menu, registry, index, router procedure
+
+### Granularity
+
+How finely you divide skills. Finer division spends one of the two loads: more **model-invoked** skills spend **context load** (more descriptions crowding the window and competing for attention); more **user-invoked** skills spend **cognitive load** (more for the human to remember and reach for). Two cuts guide the division. By **invocation**, split off a model-invoked skill where you have a distinct **leading word** to trigger it — a trigger word you actually use in your prompts. By **sequence**, split a run of **steps** where a step's **post-completion steps** need hiding, since isolating it in its own context clears what follows. Beware the reverse: merging sequences exposes each step's post-completion steps to what follows, inviting premature completion.
+
+_Avoid_: chunking, modularity
+
+## Information Hierarchy
+
+How a skill's content is arranged, and how far down the ladder each piece sits.
+
+### Information Hierarchy
+
+A skill's content ranked by how immediately the agent needs it — a single ladder, produced by two cuts: in-file or behind a pointer, and step or reference. The rungs:
+
+- **Steps** — in-file, primary
+- **Reference**, in-file — secondary
+- **Reference**, disclosed — behind a **context pointer**
+
+A skill with no **steps** uses just the bottom two rungs — often a legitimately flat peer-set (e.g. every rule of a review on one rung), which is a fine arrangement, not a smell. The hierarchy is independent of invocation: a skill can be model- or user-invoked whether it is all steps, all reference, or both. When a skill has steps, in-file reference that should be disclosed buries them and turns attending to them into a coin-flip — a variance lever, not just a legibility one. Keep the top of the ladder legible; push down it whatever you can.
+
+_Avoid_: structure, organization, layout
+
+### Steps
+
+The ordered actions the agent performs — when a skill has them, the primary tier of its content, and the part that earns its place in SKILL.md. Not every skill has steps: a skill can be all steps (`tdd`), all **reference** (a review), or both, independent of invocation. Every step ends on a **completion criterion**, clear or vague.
+
+_Avoid_: workflow, instructions, choreography
+
+### Reference
+
+Material the agent refers to on demand — definitions, facts, parameters, examples, conditional instructions. When a skill has **steps** it is secondary to them; when a skill has none it is the entire content; or it lives outside any skill entirely — see **External Reference**. Reached via **context pointers**, and the prime candidate for **progressive disclosure**.
+
+_Avoid_: supporting material, docs, background
+
+### External Reference
+
+**Reference** that lives outside the skill system — a plain file, no **description**, no **steps**, not invocable — that any skill can point at. The home for shared reference that needn't fire on its own, and the only shared home two **user-invoked** skills can use, since neither has a description and so neither can fire the other.
+
+_Avoid_: doc, resource, knowledge base
+
+### Progressive Disclosure
+
+Moving **reference** down the ladder — out of SKILL.md and behind a **context pointer** — so the top stays legible. Not primarily a token optimisation; it is how the **information hierarchy** is protected. Licensed by **branching**: disclose what only some branches need, inline what every path needs, and if a pointer fires unreliably on must-have material, sharpen its wording, and pull it back inline only if that fails.
+
+_Avoid_: lazy loading, chunking
+
+### Co-location
+
+Keeping the material an agent needs at once in one place — a concept's definition, rules, and caveats under a single heading, not scattered across the file — so reading one part brings its neighbours with it. The within-file companion to the **Information Hierarchy**: the hierarchy ranks _how far down_ a piece sits; co-location decides _what sits beside it_ once there. There is no formula for the right format of a body of **reference**; the test is that a skill should read like documentation written for the agent, and grouped material reads that way where scattered material does not. Distinct from **Duplication**: that repeats one meaning in two places, where scattering fragments a single meaning across many.
+
+_Avoid_: grouping, clustering, cohesion
+
+### Sprawl
+
+_Failure mode._ A skill that is simply too long — too many lines in SKILL.md — independent of whether they are stale or repeated. Even an all-live, all-unique skill can sprawl. It costs readability (the agent wades through more before it can act, and attention thins across the excess), maintainability (every extra line is one more to keep **relevant**), and tokens. The cure is the **information hierarchy**: push **reference** down behind **context pointers**, and split by **branch** or sequence so each path carries only what it needs. Distinct from **sediment** (length from stale accumulation) and **duplication** (length from repeated meaning) — sprawl is length itself, whatever its cause.
+
+_Avoid_: bloat, length, size, verbosity
+
+## Steering
+
+The levers that shape the agent's runtime behaviour toward **Predictability**.
+
+### Branch
+
+A distinct way a skill can be invoked — a case the skill handles — so different runs take different paths through it. A skill with many steps may carry many branches; a linear one has none.
+
+_Avoid_: path, case, fork
+
+### Leading Word
+
+A compact concept — also called a _Leitwort_ — already living in the model's pretraining, that the agent thinks with while running the skill. It encodes a behavioural principle in the fewest possible tokens by invoking priors the model already holds (e.g. _lesson_, _proximal zone of development_, _fog of war_, _tracer bullets_). Repeated as a token, never as a sentence, it accumulates a distributed definition across the skill and anchors a whole region of behaviour. Coining your own works if you define it clearly, but a made-up word recruits no priors — you pay in definition tokens what a pretrained word gives free. Reach for an existing word first.
+
+A leading word serves **predictability** twice. In the body it anchors **execution** — the agent reaches for the same behaviour every time the concept appears, and inside flat reference it focuses attention on a class of thing to look for, recruiting the right checks each run. In the **description** it anchors **invocation** — and not only within the skill: when the same word lives in your prompts, your docs, and your codebase, the agent links that shared language to the skill and fires it more reliably. Word a description with the leading words you actually use when you want the skill.
+
+_Avoid_: keyword, term, motif
+
+### Completion Criterion
+
+The condition that tells the agent a unit of work is done — the target it judges against. Two properties make it a lever, not just a quality. Its **clarity** (can the agent tell done from not-done?) resists **premature completion** — a vague bound ("understanding reached") lets the agent declare done and slip to the next step; this axis needs _steps_ to bite, since premature completion is a between-steps failure. Its **demand** (how much it requires) sets **legwork** — "every modified model accounted for" forces thorough work where "produce a change list" does not — and this axis is _not_ step-bound: it can bind a body of flat reference too, which is how a skill with no steps still carries an exhaustiveness bar ("every rule applied"). The strongest criteria are both checkable and exhaustive.
+
+_Avoid_: done condition, exit condition, stopping rule
+
+### Legwork
+
+The work an agent does behind the scenes within a single step — reading files, exploring the codebase, making changes, digging up what it needs rather than offloading to the user. It lives below the step structure: never written as its own step, latent in the wording, controlled by the agent rather than the skill. The within-step counterpart to **post-completion steps**' across-step pull. Raised by a **leading word** (_comprehensive_, _thorough_) or a **completion criterion** that demands the work be exhaustive — including the demand axis applied to flat reference, which is what drives a skill of flat reference to cover all its rungs. Goes thin either when that demand is missing or when **premature completion** cuts the step short.
+
+_Avoid_: scope, effort, diligence, coverage
+
+### Post-Completion Steps
+
+The **steps** that follow the current step. Visible, they pull the agent forward into **premature completion** — the more it sees, the stronger the tug; the defence is to hide them by splitting the sequence of steps into two.
+
+_Avoid_: horizon, fog of war, lookahead
+
+### Premature Completion
+
+_Failure mode._ Ending the current step before it is genuinely done, because the agent's attention slips to being done rather than to the work. A between-steps failure: it needs **steps** to occur — a skill with no steps that quits early isn't premature completion but thin **legwork** under an unmet demand. A tug-of-war between two forces: visible **post-completion steps** (the pull forward) and the **completion criterion**'s clarity (the resistance — a sharp, checkable bar holds; a vague one gives way). Fuzziness is the necessary condition: a sharp bound resists the pull no matter how many later steps are visible, so a step that never rushes needs no defending. Two levers hold a step that does, but reach for them in order: **sharpen the bound first** — it is local and cheap. Only when the criterion is irreducibly fuzzy _and_ you actually observe the rush do you **hide the later steps** — and hiding only works across a real context boundary (a user-invoked hand-off or a subagent dispatch; an inline model-invoked call leaves the later steps in context and clears nothing). One cause of thin legwork, but distinct from it: legwork can be thin even when a step runs to full completion.
+
+_Avoid_: premature closure, the rush, rushing, shortcutting
+
+### Negation
+
+_Failure mode._ Steering by prohibition — telling the agent what _not_ to do — which drags the forbidden behaviour into context and makes it _more_ available, not less. _Don't think of an elephant_, and the elephant is all there is; _never write verbose comments_, and verbosity is the pattern the agent has just read. The negation is a weak modifier the strongly-activated concept overruns, so the ban half-reads as an instruction to do the thing. Its **leading word** is the _elephant_: whatever a prohibition names into the frame. Cure: prompt the **positive** — describe the target behaviour ("write one-line comments") so the banned one is never spoken. A prohibition earns its place only as a hard guardrail on a behaviour you cannot phrase positively; even then, pair it with the positive target so attention lands on what to do.
+
+_Avoid_: ironic rebound, don't-prompting, the pink elephant
+
+## Pruning
+
+Keeping a skill lean — each remedy paired with the failure it cures.
+
+### Single Source of Truth
+
+The desired state where each meaning lives in exactly one authoritative place, so a change to the skill's behaviour is a change in one place. **Duplication** is its violation.
+
+_Avoid_: home, canonical location
+
+### Duplication
+
+_Failure mode._ The same meaning given more than one **single source of truth**. It costs maintenance (change one place, you must change the others), costs tokens, and inflates prominence — repeating a meaning weights it on the ladder past its real rank. The accidental inverse of a **leading word**, which raises attention on purpose by repeating a token, never the meaning.
+
+_Avoid_: repetition, redundancy
+
+### Relevance
+
+Whether a line still bears on what the skill does — the lens for what to keep. A line loses relevance either by never bearing on the task (mere exposition, or a **branch** that should be disclosed) or by going stale: drifting out of date as the behaviour or world it describes changes. Shorter skills are easier to keep relevant, because each line is cheaper to check. Distinct from **no-op**: relevance asks whether a line bears on the task, not whether it changes behaviour.
+
+_Avoid_: load-bearing, staleness, freshness
+
+### Sediment
+
+_Failure mode._ Layers of old content that settle in a skill and are never cleared, because adding feels safe and removing feels risky — so stale and irrelevant lines accumulate and you must core down through them to find what is still live. The default fate of any skill without a pruning discipline; the slow erosion of **relevance**, as opposed to **duplication**'s repeated meaning.
+
+_Avoid_: accretion, bloat, cruft, rot
+
+### No-Op
+
+_Failure mode._ An instruction that changes nothing because the model already does it by default — you pay load to tell the agent what it would do anyway. The test: does a line change behaviour versus the default? A line can be perfectly **relevant** and still be a no-op. The same priors that make a **leading word** free make a no-op worthless.
+
+A leading word is a _technique_; No-Op is a _verdict_ on a line — and they cross. A leading word too weak to beat the default is a no-op (_be thorough_ when the agent is already thorough-ish), and the fix is a stronger word that passes the verdict (_relentless_), not a different technique. So the No-Op test — does it change behaviour versus the default? — is also how you grade whether a leading word is earning its repetitions. This is model-relative, not reader-relative: two people disagreeing over whether a line is a no-op disagree about the default, and settle it by running the skill, not by debate.
+
+_Avoid_: redundant instruction, restating the obvious, belaboring

package/template/.agents/skills/writing-great-skills/SKILL.md

@@ -0,0 +1,83 @@
+---
+name: writing-great-skills
+description: Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
+disable-model-invocation: true
+---
+
+A skill exists to wrangle determinism out of a stochastic system. **Predictability** — the agent taking the same _process_ every run, not producing the same output — is the root virtue; every lever below serves it.
+
+**Bold terms** are defined in [`GLOSSARY.md`](GLOSSARY.md); look them up there for the full meaning.
+
+## Invocation
+
+Two choices, trading different costs:
+
+- 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 too). It contributes to **context load** — the description sits in the window every turn. Mechanics: omit `disable-model-invocation`, and write a model-facing description with rich trigger phrasing ("Use when the user wants…, mentions…").
+- A **user-invoked** skill strips the description from the agent's reach: only you, 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.
+
+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.
+
+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.
+
+## Writing the description
+
+A model-invoked **description** does two jobs — state what the skill is, and list the **branches** that should trigger it. Every word increases **context load**, so a description earns even harder pruning than the body:
+
+- **Front-load the skill's leading word** — the description is where it does its invocation work.
+- **One trigger per branch.** Synonyms that rename a single branch are **duplication** — "build features using TDD … asks for test-first development" is one branch written twice. Collapse them; keep only genuinely distinct branches.
+- **Cut identity that's already in the body.** Keep the description to triggers, plus any "when another skill needs…" reach clause.
+
+## Information hierarchy
+
+A skill is built from two content types — **steps** and **reference** — that mix freely: a skill can be all steps, all reference, or both. The core decision is which to use and where each sits on the **information hierarchy**, a ladder ranked by how immediately the agent needs the material:
+
+1. **In-skill step** — an ordered action in `SKILL.md`, the primary tier: what the agent does, in order. Each step ends on a **completion criterion**, the condition that tells the agent the work is done. Make it _checkable_ (can the agent tell done from not-done?) and, where it matters, _exhaustive_ ("every modified model accounted for", not "produce a change list") — a vague criterion invites **premature completion**.
+2. **In-skill reference** — a definition, rule, or fact in `SKILL.md`, consulted on demand. Often a legitimately flat peer-set (every rule of a review on one rung) — a fine arrangement, not a smell. _This skill is all reference._
+3. **External reference** — reference pushed out of `SKILL.md` into a separate file, reached by a **context pointer**, loaded only when the pointer fires. (Spans _disclosed_ reference — a sibling file like `GLOSSARY.md`, still part of the skill — through fully **external reference** that lives outside the skill system and any skill can point at.)
+
+A demanding completion criterion drives thorough **legwork** — the digging the agent does within the work — whether the skill has steps or not, since "every rule applied" binds flat reference just as "every step done" binds a sequence.
+
+Push too little down and the top bloats; push too much and you hide material the agent actually needs. That tension is the whole decision.
+
+**Progressive disclosure** is the move down the ladder — out of `SKILL.md` into a linked file — so the top stays legible. Mechanics: a linked `.md` file in the skill folder, named for what it holds (this skill discloses its full definitions to `GLOSSARY.md`). Some skills are used in more than one way, and each distinct way is a **branch** — different runs taking different paths through the skill. Branching is the cleanest disclosure test: inline what every branch needs, and push behind a pointer what only some branches reach. A **context pointer**'s _wording_, not its target, decides when and how reliably the agent reaches the material.
+
+Where the ladder decides _how far down_ a piece sits, **co-location** decides _what sits beside it_ once there: keep a concept's definition, rules, and caveats under one heading rather than scattered, so reading one part brings its neighbours with it.
+
+## When to split
+
+**Granularity** is how finely you divide skills, and each cut spends one of the two loads, so split only when the cut earns it. Two cuts:
+
+- **By invocation** — split off a **model-invoked** skill when you have a distinct **leading word** that should trigger it on its own, 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.
+- **By sequence** — split a run of **steps** when the steps still ahead (a step's **post-completion steps**) tempt the agent to rush the one in front of it (**premature completion**). Keeping them out of view encourages the agent to do more **legwork** on the current task.
+
+## Pruning
+
+Keep each meaning in a **single source of truth**: one authoritative place, so changing the behaviour is a one-place edit.
+
+Check every line for **relevance**: does it still bear on what the skill does?
+
+Then hunt **no-ops** sentence by sentence, not just line by line: run the no-op test on each sentence in isolation, and when one fails, delete the whole sentence rather than trim words from it. Be aggressive — most prose that fails should go, not be rewritten.
+
+## Leading words
+
+A **leading word** is a compact concept already living in the model's pretraining that the agent thinks with while running the skill (e.g. _lesson_, _fog of war_, _tracer bullets_). Repeated throughout the text (though not necessarily - a strong leading word might only be needed once), it accumulates a distributed definition and anchors a whole region of behaviour in the fewest tokens, by recruiting priors the model already holds.
+
+It serves predictability twice. In the body it anchors _execution_: the agent reaches for the same behaviour every time the word appears. In the description it anchors _invocation_: when the same word lives in your prompts, docs, and code, the agent links that shared language to the skill and fires it more reliably.
+
+Hunt for opportunities to refactor skills to use leading words. A triad spelled out at three sites (**duplication**), a description spending a sentence to gesture at one idea — each is a passage begging to **collapse** into a single token. Examples include:
+
+- "fast, deterministic, low-overhead" -> _tight_ — one quality restated across a phase — into a single pretrained word (a _tight_ loop).
+- "a loop you believe in" -> _red_ — converts a fuzzy gate into a binary observable state (the loop goes _red_ on the bug, or it doesn't).
+
+You win twice over: fewer tokens, _and_ a sharper hook for the agent to hang its thinking on. Assume every skill is carrying restatements that leading words retire — go find them.
+
+## Failure modes
+
+Use these to diagnose issues the user may be having with the skill.
+
+- **Premature completion** — ending a step before it's genuinely done, attention slipping to _being done_. Defence, in order: sharpen the completion criterion first (cheap, local); only if it is irreducibly fuzzy _and_ you observe the rush, hide the post-completion steps by splitting (the sequence cut).
+- **Duplication** — the same meaning in more than one place. Costs maintenance and tokens, and inflates a meaning's prominence on the ladder past its real rank.
+- **Sediment** — stale layers that settle because adding feels safe and removing feels risky. The default fate of any skill without a pruning discipline.
+- **Sprawl** — a skill simply too long, even when every line is live and unique. Hurts readability and maintainability and wastes tokens. The cure is the ladder: disclose **reference** behind pointers, and split by **branch** or sequence so each path carries only what it needs.
+- **No-op** — a line the model already obeys by default, so you pay load to say nothing. The test: does it change behaviour versus the default? A weak leading word (_be thorough_ when the agent is already thorough-ish) is a no-op; the fix is a stronger word (_relentless_), not a different technique.
+- **Negation** — steering by prohibition backfires: _don't think of an elephant_ names the elephant and makes it more available, not less. Prompt the **positive** — state the target behaviour so the banned one is never spoken; keep a prohibition only as a hard guardrail you can't phrase positively, and even then pair it with what to do instead.

package/template/.agents/skills/writing-great-skills/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Writing Great Skills"
+  short_description: "Principles for predictable skills"
+policy:
+  allow_implicit_invocation: false

package/template/.agents/skills/yss-cache/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: yss-cache
+description: 用于 YSS 缓存框架的接入、配置、代码修改和故障诊断。Use when tasks involve QueryCache、UpdateCache、ClearCache、TTL、SpEL key、事务提交后缓存操作、Redis/Caffeine/Hazelcast 后端切换、Redis Standalone/Sentinel/Cluster、Jedis 连接池、Redis fallback、JetCache、多级缓存、序列化兼容、缓存不命中或失效不一致。
+---
+
+# yss-cache
+
+处理 `yss-component-cache-parent` 及其消费项目的缓存任务。
+
+## 工作流
+
+1. 按 `yss-source-index/references/source-location.md` 定位真实源码。当前工作区有 `.codegraph/` 时先用 CodeGraph；否则读取 [source-index.md](references/source-index.md) 后用符号或 Maven 模块搜索。
+2. 识别使用模型：Spring Cache 单后端路由、Redis 故障降级，或 JetCache local + remote。不要混用三者的行为假设。
+3. 明确缓存名、key、TTL、更新/删除路径、跨节点一致性和序列化兼容要求。
+4. 先检查现有依赖、启动注解、配置和注解用法，再决定修改业务代码、配置还是组件。
+5. 修改后执行对应 reference 的验证；组件跨模块修改必须从父 reactor 构建，不要依赖本地旧 SNAPSHOT。
+
+## 不变量
+
+- 新增查询缓存时同时覆盖更新、删除和状态变更的失效路径。
+- key 必须稳定并显式包含租户、机构、账套等隔离维度；不要依赖 DTO 的不稳定序列化结果。
+- 不要把 Redis fallback 当作正常二级缓存。Caffeine fallback 存在节点间不一致窗口。
+- 不要声称纯 Redis 后端会广播本地缓存失效。只有确认 JetCache 配置了 local、remote 和 broadcast channel 后才能作此判断。
+- 不要在没有双读、版本前缀、灰度清理或迁移窗口时修改 serializer、key prefix 或 cache name。
+- 不明确一致性要求时，不默认启用本地缓存或 fallback。
+
+## 按场景读取
+
+- 模块、后端选择或多级缓存边界：[architecture.md](references/architecture.md)
+- 新增或修改缓存注解、SpEL、空 key、全量清理：[annotations.md](references/annotations.md)
+- 依赖、启动注解、TTL、Caffeine/Hazelcast、Bean backoff：[configuration.md](references/configuration.md)
+- Redis 单机、哨兵、集群、认证、SSL、超时、Jedis pool：[redis-topology.md](references/redis-topology.md)
+- Redis 故障、fallback、恢复清理和一致性：[redis-fallback.md](references/redis-fallback.md)
+- RedisTemplate/RedisCacheManager 数据格式或迁移：[serialization.md](references/serialization.md)
+- 缓存不生效、未失效、启动失败、Redis 异常：[troubleshooting.md](references/troubleshooting.md)
+- 完成修改后的组件与消费项目验收：[verification.md](references/verification.md)
+
+## 工具
+
+- `scripts/inspect-cache-usage.sh <project-root>`：只读扫描消费项目；发现阻断缺陷返回 1，输入或环境错误返回 2。
+- `scripts/verify-cache-component.sh [--source-root PATH] [--consumer-root PATH --consumer-module MODULE]`：验证组件、真实 Redis、Java 8 字节码及可选消费模块。
+- `scripts/check-skill-freshness.sh [source-root]`：比较技能契约与当前组件源码；发现漂移返回 1。
+
+当组件源码变化后，用 `yss-source-index` 刷新 [source-index.md](references/source-index.md)，再运行 freshness 检查。不要手工修改生成索引。

package/template/.agents/skills/yss-cache/agents/openai.yaml

@@ -0,0 +1,5 @@
+version: 1
+interface:
+  display_name: "YSS Cache"
+  short_description: "YSS 缓存注解、Redis 拓扑、降级与序列化诊断"
+  default_prompt: "Use $yss-cache to configure or diagnose YSS cache annotations, Redis topology, fallback, TTL, and serialization behavior."

package/template/.agents/skills/yss-cache/references/annotations.md

@@ -0,0 +1,39 @@
+# 注解契约
+
+## 映射
+
+- `@QueryCache` -> Spring `CacheableOperation`。
+- `@UpdateCache` -> Spring `CachePutOperation`。
+- `@ClearCache` -> Spring `CacheEvictOperation`。
+- `value` 与 `cacheNames` 是别名；非空 `cacheName` 会覆盖枚举 cache names。
+- 默认 resolver 是 `cacheComposeResolver`。
+- `key` 与 `keyGenerator` 互斥。
+
+## 参数语义
+
+- `condition`：调用前判断，false 时跳过缓存操作。
+- `unless`：结果产生后判断；Query/Update 支持。ClearCache 虽保留该字段，但当前解析器不映射它。
+- `sync`：QueryCache 映射到同步加载；UpdateCache 和 ClearCache 当前不映射该字段。
+- `allEntries=true`：明确清空整个 cache。
+- `beforeInvocation=true`：业务方法执行前清理；后续业务失败不会恢复旧缓存。
+
+## Key 与清理
+
+```java
+@QueryCache(cacheName = "valuation:plan", key = "#tenantId + ':' + #planId")
+public PlanDTO get(String tenantId, Long planId) { ... }
+
+@ClearCache(cacheName = "valuation:plan", key = "#tenantId + ':' + #planId")
+public void delete(String tenantId, Long planId) { ... }
+```
+
+- 未配置 key 时由 Spring KeyGenerator 生成；无参数方法会得到 `SimpleKey.EMPTY`。
+- 当前 YSS 拦截器将 `SimpleKey.EMPTY` 视为全量清理。需要单 key 清理时必须给出稳定 key。
+- 全量清理优先显式写 `allEntries=true`，不要依赖偶然 key 形态。
+- 集合参数先稳定排序；null、大小写和空白必须归一化。
+
+## AOP 与事务
+
+- 缓存方法必须通过 Spring 代理调用；同类 `this.method()` 自调用会绕过拦截。
+- private 方法不能作为代理入口；final 方法/类受代理方式限制。
+- `put`、`evict`、`clear` 在事务同步激活时延迟到 `afterCommit`；回滚不执行缓存变更。

package/template/.agents/skills/yss-cache/references/architecture.md

@@ -0,0 +1,25 @@
+# 架构与选择
+
+## 三种模型
+
+| 模型 | 行为 | 一致性边界 |
+|---|---|---|
+| Spring Cache 后端路由 | `yss.cache.active-type` 在 Redis、Caffeine、Hazelcast 中选择一个 Provider | 同一时刻是单后端，不是多级缓存 |
+| Redis fallback | Redis 故障时可临时改用另一个 Provider | 是故障降级；Caffeine 会产生节点间不一致窗口 |
+| JetCache | 独立扩展，可配置 local + remote | 只有实际配置 broadcast channel 才能认为本地失效会同步 |
+
+## 模块
+
+- `yss-component-spring-cache`：注解、解析器、拦截器、路由和公共属性。
+- `yss-component-redis-cache`：Jedis 连接、RedisTemplate、RedisCacheManager、健康检查和 fallback。
+- `yss-component-caffeine-cache`：节点本地缓存。
+- `yss-component-hazelcast-cache`：显式依赖的集群内存后端。
+- `yss-component-cache-starter`：默认聚合 Spring Cache、Redis 和 Caffeine。
+- `yss-component-jetcache`：与 Spring Cache 路由模型分开分析。
+
+## 选择规则
+
+- 跨节点共享且不接受节点本地旧值：使用纯 Redis。
+- 读多写少并允许短暂节点差异：可选择 Caffeine。
+- Redis 故障期间业务可用性高于缓存一致性：评估后启用 fallback。
+- 需要 local + remote：先确认 JetCache 的 local、remote、序列化和广播配置，不要只看依赖名称。

package/template/.agents/skills/yss-cache/references/configuration.md

@@ -0,0 +1,34 @@
+# 接入与配置
+
+## 推荐接入
+
+```xml
+<dependency>
+  <groupId>com.yss.cloud</groupId>
+  <artifactId>yss-component-cache-starter</artifactId>
+</dependency>
+```
+
+启动类使用 `@EnableYssCloudCache`。`@EnableYssCloudRedisCache` 仅为兼容保留并已废弃。
+
+## 公共属性
+
+```yaml
+yss:
+  cache:
+    active-type: redis       # redis | caffeine | hazelcast
+    default-ttl: 1h
+    redis:
+      fallback-enabled: false
+      fallback-type: caffeine
+      clear-fallback-on-recovery: true
+```
+
+- Redis 动态 cache 和 Caffeine 默认 TTL 使用 `yss.cache.default-ttl`。
+- `CacheKeyCode` 中声明的 TTL 覆盖默认 TTL。
+- Caffeine 的 `spring.cache.caffeine.spec` 可覆盖默认构建规格，修改前检查项目现有配置。
+- Hazelcast 不在 starter 生产依赖中；使用时显式引入模块并配置 `active-type=hazelcast`。
+
+## 自定义 Bean
+
+默认配置会对用户提供的 `RedisProperties`、`RedisConnectionFactory`、`JedisClientConfiguration`、pool config、RedisCacheManager、resolver、provider、serializer、RedisTemplate 和 RedisMappingContext 回退。排障时按类型和名称检查实际 Bean，不能假设框架默认 Bean 一定生效。

package/template/.agents/skills/yss-cache/references/redis-fallback.md

@@ -0,0 +1,23 @@
+# Redis 故障降级与恢复
+
+## 状态流
+
+```text
+Redis 健康 -> 命令或健康检查失败 -> 标记不健康 -> 跳过 Redis
+-> 可选 fallback -> 周期健康检查 -> Redis 可连接
+-> 清理脏 Redis cache 与本地 fallback cache -> 恢复 Redis
+```
+
+- fallback 默认关闭，默认目标是 Caffeine。
+- Redis 健康检查当前每 20 秒执行一次。
+- Redis 命令级连接故障也会立即报告不健康，不必等待下一轮检查。
+- 只读 fallback 不标记 Redis cache 为脏。
+- put、putIfAbsent、evict、clear、invalidate 和 valueLoader 产生的回退写入会标记为脏。
+- 恢复时先清理降级期间发生写操作的 Redis cache，再清理本地 fallback cache。
+- Redis 失效失败时继续保持不健康状态并在后续检查重试，不能提前切回旧 Redis 数据。
+
+## 一致性判断
+
+- Caffeine fallback 是每节点独立数据，不能保证跨节点读到相同值。
+- `clear-fallback-on-recovery=false` 会跳过恢复清理，可能重新暴露 Redis 旧值；除非业务明确接受，不要关闭。
+- 强一致、锁、幂等状态或余额类数据不应依赖缓存 fallback 保证正确性。

package/template/.agents/skills/yss-cache/references/redis-topology.md

@@ -0,0 +1,62 @@
+# Redis 拓扑
+
+框架使用 Spring Boot `spring.redis` 属性和 Jedis 客户端。
+
+## Standalone
+
+```yaml
+spring:
+  redis:
+    host: localhost
+    port: 6379
+    database: 10
+    username: ${REDIS_USERNAME:}
+    password: ${REDIS_PASSWORD:}
+    connect-timeout: 5s
+    timeout: 10s
+    client-type: jedis
+    jedis:
+      pool:
+        enabled: true
+        max-active: 16
+        max-idle: 8
+        min-idle: 2
+        max-wait: 2s
+```
+
+## Sentinel
+
+```yaml
+spring:
+  redis:
+    database: 10
+    username: ${REDIS_USERNAME:}
+    password: ${REDIS_PASSWORD:}
+    sentinel:
+      master: mymaster
+      nodes: host1:26379,host2:26379,host3:26379
+      username: ${SENTINEL_USERNAME:}
+      password: ${SENTINEL_PASSWORD:}
+```
+
+业务 Redis 认证与 Sentinel 自身认证相互独立。
+
+## Cluster
+
+```yaml
+spring:
+  redis:
+    database: 0
+    username: ${REDIS_USERNAME:}
+    password: ${REDIS_PASSWORD:}
+    cluster:
+      nodes: host1:6379,host2:6379,host3:6379
+      max-redirects: 5
+```
+
+## 强制约束
+
+- Sentinel 和 Cluster 不能同时配置，违反时启动失败。
+- Redis Cluster 只允许 DB 0，非零 `spring.redis.database` 会启动失败。
+- username/password、SSL、client-name、连接/读取超时和 Jedis pool 参数会传入连接配置。
+- 不要提供 Lettuce 专属调优参数；当前实现明确使用 Jedis。

package/template/.agents/skills/yss-cache/references/serialization.md

@@ -0,0 +1,17 @@
+# 序列化兼容
+
+当前存在两条不同数据路径：
+
+- 框架 `RedisTemplate` 使用 Jackson JSON serializer。
+- Spring `RedisCacheManager` 沿用默认 JDK value serialization。
+
+两者的数据不可假设互相可读。`RedisTemplate` 的历史泛型声明与通用 JSON 行为也不完全一致，修改前必须检查消费方注入类型和实际操作。
+
+以下变化都属于 Redis 数据协议变更：
+
+- 修改 value/hash serializer。
+- 修改 key serializer 或 cache prefix。
+- 重命名 cache name。
+- 改变 key 的字段、顺序、归一化或版本。
+
+实施协议迁移前至少选择一种策略：双读单写、双写、版本化前缀、灰度清理或停机迁移。必须验证旧值读取、新值写入、回滚和混合版本节点；禁止把“统一 serializer”当作无风险重构。

package/template/.agents/skills/yss-cache/references/source-index.md

@@ -0,0 +1,64 @@
+# yss-cache Source Index
+
+Generated: 2026-07-17T10:08:00+00:00
+Indexed source root: resolved at refresh time; set `YSS_SOURCE_ROOT` to reproduce or refresh.
+
+This file is generated by `yss-source-index/scripts/refresh-yss-skill-index.py`. Do not hand-edit generated sections.
+
+Paths below are source path hints captured at refresh time. If they do not exist in the current workspace, locate sources using `YSS_SOURCE_ROOT`, CodeGraph, package/class names, Maven artifact names, or repository search before assuming the source is unavailable.
+
+## Component Path Hints
+
+- `yss-microservice-components/yss-component-cache-parent` (existed when indexed)
+
+## Documentation Files
+
+- `yss-microservice-components/yss-component-cache-parent/readme.md`
+
+## Maven Modules
+
+- `yss-microservice-components/yss-component-cache-parent`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-cache-starter`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-caffeine-cache`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-hazelcast-cache`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-jetcache`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-redis-cache`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache`
+
+## Key Java Entry Points
+
+- `yss-microservice-components/yss-component-cache-parent/yss-component-caffeine-cache/src/main/java/com/yss/cloud/cache/caffeine/config/CacheCaffeineManagerConfig.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-caffeine-cache/src/main/java/com/yss/cloud/cache/caffeine/config/CacheCaffeineResolver.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-caffeine-cache/src/main/java/com/yss/cloud/cache/caffeine/config/CaffeineCacheBackendProvider.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-hazelcast-cache/src/main/java/com/yss/cloud/cache/hazelcast/config/CacheHazelcastManagerConfig.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-hazelcast-cache/src/main/java/com/yss/cloud/cache/hazelcast/config/HazelcastCacheBackendProvider.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-hazelcast-cache/src/main/java/com/yss/cloud/cache/hazelcast/config/YssCacheHazelcastProperties.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-jetcache/src/main/java/com/yss/cloud/cache/jetcache/CacheManagerCompose.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-redis-cache/src/main/java/com/yss/cloud/cache/redis/config/RedisCacheBackendProvider.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-redis-cache/src/main/java/com/yss/cloud/cache/redis/config/RedisConnFactoryConfig.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-redis-cache/src/main/java/com/yss/cloud/cache/redis/config/RedisTemplateConfig.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-redis-cache/src/main/java/com/yss/cloud/cache/redis/config/SafeRedisCache.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-redis-cache/src/main/java/com/yss/cloud/cache/redis/config/YssCacheRedisResolver.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-redis-cache/src/main/java/com/yss/cloud/cache/repository/BaseRedisRepository.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-redis-cache/src/main/java/com/yss/cloud/cache/repository/YssDatamiddle.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/ApplicationContextCacheHelper.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/CacheComposeResolver.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/CacheManagerCompose.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/CacheMemResolver.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/CacheRedisResolver.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/EnableYssCloudCache.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/EnableYssCloudRedisCache.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/YssCacheBackendProvider.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/YssCacheInterceptor.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/YssCacheProperties.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/annotation/ClearCache.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/annotation/QueryCache.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/annotation/UpdateCache.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/annotation/YssCacheAnnotationParser.java`
+- `yss-microservice-components/yss-component-cache-parent/yss-component-spring-cache/src/main/java/com/yss/cloud/cache/config/CacheOperationSourceConfiguration.java`
+
+## Recommended Next Reads
+
+- Start with the documentation files above when learning component usage.
+- Search the key Java entry points for annotations, auto configuration, properties, aspects, interceptors, handlers, and result objects before changing application code.
+- Prefer existing component extension points over rewriting framework logic in business modules.