opencode-skills-collection 4.1.2 → 4.1.4

package/bundled-skills/cline-pilot/references/cold-start.md

@@ -0,0 +1,58 @@
+# 冷启动初始化手册（新工程）
+
+## 前置核：全局默认 Memory Bank 提示词（必须先于任何 memory bank 开启确认到位）
+检查 → 引导 → 降级，三步：
+
+**第一步检查（跨 OS 通用，首选）**：CLI 与 VSCode 插件共用 `~/.cline/data`（Windows 为 `%USERPROFILE%\.cline\data`），一处配置两端生效。一行判定：
+```bash
+# macOS / Linux
+python3 -c "import json;d=json.load(open('$HOME/.cline/data/globalState.json'));print(d.get('globalClineRulesToggles'))"
+# Windows (PowerShell)
+python -c "import os,json;d=json.load(open(os.path.expanduser('~/.cline/data/globalState.json')));print(d.get('globalClineRulesToggles'))"
+```
+值为 `{".../memory-bank.md": true}` 即已配置（key 是各 OS 的实际绝对路径）；再 `head`/`Get-Content` 该文件确认是 memory-bank 提示词。命中且内容完整 → 直达分支二/三。
+
+**全局规则目录的默认落点（按 OS 对照）**：
+| OS | 插件默认全局 Rules 目录 | 旧式全局文件（legacy，仍兼容） | HOME 变量 |
+|----|--------------------------|--------------------------------|-----------|
+| macOS / Linux | `~/Documents/Cline/Rules/` | `~/.clinerules` | `$HOME` |
+| Windows | `%USERPROFILE%\Documents\Cline\Rules\` | `%USERPROFILE%\.clinerules` | `%USERPROFILE%` |
+
+检测顺序：先查注册表（上）；未命中再 `ls` 上述两个落点有无 memory-bank 提示词文件（有文件但 toggle 未开 = 配了没勾，引导用户打开）；都没有 = 未配置 → 第二步引导。
+
+2. **引导**（未配置时）：推荐用户配到**全局**（跨工程生效）——Cline 设置→自定义指令/Rules，粘贴 `assets/global-memory-bank-prompt.md` 全文（面向英文用户/工程给 `global-memory-bank-prompt.en.md`）；文件落点对应上表 OS 行；给用户明确操作说明后再继续
+3. **降级**（用户暂不配）：**注入模式**——把所选语言版提示词全文直接写进本次任务 prompt 的上下文，**然后再发 `active memory bank`**（顺序固定：先提示词、后激活）
+
+- 提示词全文 = `assets/global-memory-bank-prompt.md`（中文）/ `global-memory-bank-prompt.en.md`（英文），逐字模板勿改语义
+- 来源：用户博客 https://gongdear.com/articles/2026/09/04/1788492620184.html 最后部分“自定义指令（完整版）”
+
+## 分支 A：全新工程（连代码都没有）
+代码事实为零 → **规则内容只能来自用户**，按 Cline 最佳实践逐维度问齐后让 Cline 落盘。**不要替用户编任何一条**。
+
+### 逐维度询问清单（一次一块，别一次性全抛）
+1. **projectbrief**：这个项目是什么、给谁用、范围多大、目标是什么（一句话 + 3-5 个要点就够，别问八股）
+2. **productContext**：解决什么问题、现在怎么解决的、期望怎么工作
+3. **techContext**：技术栈选型、运行环境、部署边界、已知技术约束
+4. **systemPatterns**：计划采用的架构模式、分层约定、关键中间件（用户没想好就标“待定”）
+5. **开发偏好**：语言规范、命名、错误处理、测试要求、分支策略、提交信息格式
+6. **activeContext / progress**：当前起点是什么、第一步打算做什么（通常 = 脚手架初始化）
+
+### 交给 Cline 的任务书要点
+- 先写全局提示词核（前置硬前提）
+- 再建工程级 `.clinerules` + `memory-bank/`（六文件），**内容逐条来自上面的用户回答**，用户没答的标“待确认”，禁止填充想象中的规范
+- 只建规则/记忆文件，不产业务代码；一次性汇报后止步
+
+## 分支 B：存量代码工程
+代码事实存在 → **规则以扫描代码为基准**，用户背景信息只做补全。
+
+### 交给 Cline 的任务书要点
+- 先写全局提示词核（前置硬前提）
+- 全量扫描现有代码：架构/模块划分/技术栈/既有命名与错误处理/测试现状/构建与分支约定
+- 依据代码事实落 `.clinerules` + `memory-bank/` 六文件；用户提供的偏好（背景、习惯、约束）覆盖同冲突项时以用户为准
+- 代码里看不出来且用户没说的 → 标“待确认”
+- 只改规则/记忆文件，**禁止顺手重构业务代码**；一次性汇报后止步
+
+## 两分支共同收尾
+1. 我按验收清单核对：六文件存在且非空、内容可溯（用户话或代码行）、无业务代码改动
+2. 向用户汇报：建了什么／每条依据是什么／哪些“待确认”
+3. **停下等用户审阅**（他会逐轮纠偏，要求 Cline 同步改 rules/memory）→ 确认后才进正常转达工作流

package/bundled-skills/cline-pilot/references/decision-log.example.md

@@ -0,0 +1,9 @@
+# Decision Log — habits & preferences learned per TAG CLASS 决策流水（按标签类记）
+
+> Log each user correction/decision with its TAG CLASS.
+> ≥2 consistent samples in one tag class → distill into the 标签偏好区 section of SKILL.md.
+> 同标签类 ≥2 个一致样本 → 蒸馏进 SKILL.md 的标签偏好区。
+
+| Date 日期 | Tag class 标签类 | Scenario 场景 | My choice 我的选择 | User correction 用户纠正 | Reason 理由 |
+|------|--------|------|---------------|------------|---------|
+| — | — | — | — | — | — |

package/bundled-skills/cline-pilot/references/local-config.example.md

@@ -0,0 +1,26 @@
+# Local Config — YOUR MACHINE (private, not tracked)
+
+Copy this file to `local-config.md` and fill in YOUR values before first use.
+本文件为模板；复制为 `local-config.md` 后填入你自己的值。
+
+## Dev Environment 开发环境
+| Item 项目 | Value 值 |
+|----|-----|
+| conda env | e.g. `dev-env` |
+| Pre-launch | `source <your rc/env file> && conda activate <env>` |
+| Dirty-stack fix | `unset CONDA_PREFIX CONDA_PREFIX_1 CONDA_PROMPT_MODIFIER CONDA_SHLVL CONDA_DEFAULT_ENV` (if your agent session inherits broken CONDA state) |
+| Toolchain | e.g. `java` 21 / `mvn` 3.9+ / `node` |
+| Branch rules | e.g. main is push-protected; feature branches only |
+
+## Launch Template 启动模板
+```bash
+zsh -c '<unset CONDA_* if dirty>; source <env> && conda activate <env> && cd <project> && cline ...'
+```
+Self-check before launch: python points to target env / toolchain versions / `git branch --show-current` = task branch.
+
+## LLM Endpoint
+- base: `http://<your openai-compatible endpoint>/v1`, model: `<model-id>`
+- Probe before launch: `curl -s -H 'Authorization: Bearer <key>' <base>/models | head -c 200`
+
+## Scratch Workspace 临时工作区
+`<path>/worktree/` — worktrees / subagent dirs / temp builds MUST stay here; never scatter into `~`.

package/bundled-skills/cline-pilot/references/project-profiles.example.md

@@ -0,0 +1,10 @@
+# Project Profiles — intro + tags only, NO architecture 项目画像（仅简介+标签，不记架构）
+
+> Register a one-line intro + tags per project so learned preferences can be
+> applied by TAG CLASS. Architecture details live in the project's own memory
+> bank + clinerules, never here.
+> 按工程登记简介+标签，以便按“标签类”套用已学偏好。架构细节归工程自己的 memory bank，不放这里。
+
+| Project 工程 | Path 路径 | One-line intro 简介 | Side 端 | Lifecycle 生命周期 | Risk 风险面 |
+|------|------|----------|----|---------|--------|
+| — | — | — | backend/frontend 前后端 | long-term/short 长护/短期 | prod-data?/public API? 是否生产数据/对外接口 |

package/bundled-skills/cline-pilot/scripts/session_report.py

@@ -0,0 +1,151 @@
+#!/usr/bin/env python3
+"""session_report.py — Cline 会话活动摘要 + 工程进度硬证据。
+
+用法:
+  python3 session_report.py                # 最新会话 10 条 + 当前目录证据
+  python3 session_report.py 15             # 最近 15 条
+  python3 session_report.py /path/to/repo  # 指定工程目录（自动识别 sid 或路径）
+
+输出:
+  - 会话最近 N 条消息（role / text / tool / 结果摘要）
+  - 工程硬证据：分支、git status、最近 commit、最新测试报告首行（多栈：Maven surefire / JUnit-xml / pytest 等）
+    输出 / output: branch, git status, last commit, newest test-report lines (stack-agnostic)
+只读操作，不改任何文件。stdlib only。
+"""
+import glob
+import json
+import os
+import subprocess
+import sys
+
+
+SESSIONS_ROOT = os.path.join(os.path.expanduser("~"), ".cline", "data", "sessions")
+
+
+def latest_session_id():
+    if not os.path.isdir(SESSIONS_ROOT):
+        return None
+    entries = []
+    for e in os.listdir(SESSIONS_ROOT):
+        p = os.path.join(SESSIONS_ROOT, e)
+        if os.path.isdir(p):
+            entries.append((os.path.getmtime(p), e))
+    return max(entries)[1] if entries else None
+
+
+def load_session(sid):
+    p = os.path.join(SESSIONS_ROOT, sid, sid + ".messages.json")
+    if not os.path.exists(p):
+        return None, None
+    with open(p, encoding="utf-8") as f:
+        d = json.load(f)
+    return d.get("messages", []), d.get("updated_at")
+
+
+def summarize(msgs, n):
+    lines = []
+    for m in (msgs or [])[-n:]:
+        role = m.get("role", "?")
+        content = m.get("content")
+        if isinstance(content, str):
+            lines.append("[%s] %s" % (role, content[:160].strip()))
+            continue
+        for c in content or []:
+            t = c.get("type")
+            if t == "text":
+                lines.append("[%s|text] %s" % (role, (c.get("text") or "")[:160].strip()))
+            elif t in ("tool_use", "toolCall", "tool"):
+                name = c.get("name") or c.get("toolName") or ""
+                inp = c.get("input") or c.get("arguments") or {}
+                lines.append("[%s|tool:%s] %s" % (role, name, json.dumps(inp, ensure_ascii=False)[:150]))
+            elif t == "tool_result":
+                r = c.get("content") or c.get("output") or ""
+                r = r if isinstance(r, str) else json.dumps(r, ensure_ascii=False)
+                lines.append("[%s|result] %s" % (role, str(r)[:150]))
+            else:
+                lines.append("[%s|%s] %s" % (role, t, json.dumps(c, ensure_ascii=False)[:120]))
+    return lines
+
+
+def sh(cmd, cwd):
+    try:
+        r = subprocess.run(cmd, shell=True, cwd=cwd, capture_output=True, text=True, timeout=60)
+        out = r.stdout.strip()
+        return out if out else "(exit %d %s)" % (r.returncode, r.stderr.strip()[:60])
+    except Exception as e:
+        return "(error %s)" % e
+
+
+# 多栈测试报告候选（按优先级）/ multi-stack test-report candidate patterns
+REPORT_GLOBS = [
+    "**/target/surefire-reports/*.txt",   # Maven/JUnit
+    "**/junit-xml/TEST-*.xml",             # Node (vitest/jest jasmine2)
+    "**/build/test-results/test/*.xml",   # Kotlin/Gradle
+    "**/.pytest_cache/v/cache/lastfailed", # pytest
+    "**/coverage/*.html",                  # 覆盖率产物兜底
+]
+
+
+def repo_evidence(root):
+    if not os.path.exists(os.path.join(root, ".git")) and not os.path.isdir(os.path.join(root, ".git")):
+        try:
+            r = subprocess.run(["git", "rev-parse", "--show-toplevel"], cwd=root, capture_output=True, text=True, timeout=20)
+            if r.returncode != 0:
+                return ["(not a git repo: %s)" % root]
+            root = r.stdout.strip()
+        except Exception:
+            return ["(not a git repo: %s)" % root]
+    lines = [
+        "branch   : %s" % sh("git branch --show-current", root),
+        "status   : %s" % (sh("git status --short | head -15", root) or "(clean)"),
+        "commit   : %s" % sh("git log -1 --pretty='%h %s'", root),
+    ]
+    recent = []
+    for pat in REPORT_GLOBS:
+        hits = glob.glob(os.path.join(root, pat), recursive=True)
+        if hits:
+            recent.extend(hits)
+            break
+    recent = sorted(recent, key=lambda p: os.path.getmtime(p), reverse=True)[:6]
+    for f in recent:
+        try:
+            with open(f, encoding="utf-8", errors="replace") as fh:
+                first = fh.readline().strip()
+            lines.append("tests    : %s | %s" % (os.path.relpath(f, root), first[:140]))
+        except OSError:
+            pass
+    if not recent:
+        lines.append("tests    : (no test reports found / 未找到测试报告)")
+    return lines
+
+
+def main(argv):
+    n, repo, sid = 10, os.getcwd(), None
+    for a in argv:
+        if a.isdigit() and int(a) < 500:
+            n = max(1, int(a))
+        elif os.path.isdir(os.path.expanduser(a)):
+            repo = os.path.expanduser(a)
+        else:
+            sid = a
+    sid = sid or latest_session_id()
+    if not sid:
+        print("no cline sessions found under", SESSIONS_ROOT)
+        return 1
+    print("== session: %s ==" % sid)
+    msgs, updated = load_session(sid)
+    if msgs is None:
+        print("(messages.json not found)")
+        return 1
+    print("updated_at: %s | total messages: %d" % (updated, len(msgs)))
+    print("-- recent activity --")
+    for line in summarize(msgs, n):
+        print(line)
+    print("-- repo evidence: %s --" % repo)
+    for line in repo_evidence(repo):
+        print(line)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main(sys.argv[1:]))

package/bundled-skills/cross-chain-relayer-audit/SKILL.md

@@ -0,0 +1,136 @@
+---
+name: cross-chain-relayer-audit
+description: 'Cross-chain relayer bridge audit register: message hash verifications, replay protection nonces, validator quorum, and withdrawal proofs.'
+category: engineering
+risk: safe
+source: self
+source_type: self
+date_added: "2026-10-01"
+author: Ranjeet2063
+tags: [cross-chain, bridge, relayer, security, cryptography, web3, stellar]
+tools: []
+source_repo: Ranjeet2063/agentic-awesome-skills
+---
+
+# Cross-Chain Relayer Security Audit
+
+**What it is:** Audits cross-chain message passing protocols, cryptographic commitment trees, and validator quorum consensus for cross-chain relayers.
+
+## Overview
+
+Provides a standardized, auditable framework and data model for **Cross-Chain Relayer Security Audit** operations across distributed engineering and decentralized application systems.
+
+## When to Use This Skill
+
+- When formalizing architectural contracts, security invariants, or operational limits for Cross-Chain Relayer Security Audit.
+- When cross-functional review is required between protocol developers, smart contract auditors, and AI engineering agents.
+- When generating reproducible CSV, SQL DDL, JSON Schema, and Notion property registers for tracking compliance.
+
+## How It Works
+
+1. Define the parameters, thresholds, and identity bindings required for the target operational register.
+2. Select appropriate boundary enforcement values from validated enum select sets.
+3. Export standardized artifacts (CSV table, SQL DDL, JSON Schema) to integrate into validation CI pipelines.
+
+## Field Reference
+
+| # | Field Name | Type | SQL Type | JSON Schema Type | Notion Property Type | Example Value |
+|---|------------|------|----------|------------------|----------------------|---------------|
+| 1 | Relayer Audit ID | `id` | `SERIAL PRIMARY KEY` | `integer` | Text | `REL-001` |
+| 2 | Source Chain Domain | `text` | `VARCHAR(32)` | `string` | Text | `Ethereum Sepolia` |
+| 3 | Destination Chain Domain | `text` | `VARCHAR(32)` | `string` | Text | `Stellar Testnet` |
+| 4 | Message Hash Verification | `select` | `VARCHAR(32)` | `string` | Select | `Keccak256 Verified` |
+| 5 | Replay Protection Nonce Check | `select` | `VARCHAR(32)` | `string` | Select | `Enforced Strict Sequence` |
+| 6 | Validator Quorum Threshold | `text` | `VARCHAR(16)` | `string` | Text | `5-of-7 Quorum` |
+| 7 | Slashing Condition Active | `select` | `VARCHAR(16)` | `string` | Select | `Yes` |
+| 8 | Withdrawal Proof Standard | `select` | `VARCHAR(64)` | `string` | Select | `Merkle Patricia Trie Proof` |
+| 9 | Finality Confirmation Blocks | `number` | `INTEGER` | `number` | Number | `32` |
+| 10 | Bridge Security Posture | `select` | `VARCHAR(32)` | `string` | Select | `Verified Secure` |
+| 11 | Audit Stamp Date | `date` | `DATE` | `string, format: date` | Date | `2026-10-01` |
+
+## Select Options
+
+**Message Hash Verification**
+
+```
+Keccak256 Verified | SHA256 Verified | Invalid Hash
+```
+
+**Replay Protection Nonce Check**
+
+```
+Enforced Strict Sequence | Bitmask Window | Unchecked
+```
+
+**Slashing Condition Active**
+
+```
+Yes | No
+```
+
+**Withdrawal Proof Standard**
+
+```
+Merkle Patricia Trie Proof | ZK-SNARK Validity Proof | Light Client Header
+```
+
+**Bridge Security Posture**
+
+```
+Verified Secure | Under Audit | Vulnerable Finding
+```
+
+## Relations
+
+- `Audit Reference` -> links to the formal review documentation or test repository.
+- `Target Architecture` -> links to the deployed contract or autonomous agent runtime component.
+
+## Examples
+
+**Prompt**
+
+```
+How do I configure and track Cross-Chain Relayer Security Audit for our production environment?
+```
+
+**Recommended Next Step**
+
+> Generate the unified field schema, SQL DDL migration, and JSON validation schema to register into your system catalog.
+>
+> Workflow: Define criteria -> Run automated verification -> Record baseline -> Monitor invariants.
+
+## Best Practices
+
+- Enforce strict typing on numerical bounds and currency amounts; avoid unstructured free-text fields for critical states.
+- Re-run validation test suites on every state-altering commit or parameter change.
+- Keep example data synthetic and isolated from production cryptographic keys or private endpoints.
+
+## Limitations
+
+- Provides architectural specifications, data models, and verification schemas; does not execute direct transaction signing without authorized external tooling.
+- Requires network connectivity and valid RPC credentials when querying on-chain states.
+
+## Security & Safety Notes
+
+- All parameters declare `risk: safe`. No unauthorized state modification or privileged credential access is performed.
+- Use synthetic dummy keys and mock addresses in test suites and local verification scripts.
+
+## Common Pitfalls
+
+- **Problem:** Mismatched decimal precision between contract runtime and database register.
+  **Solution:** Always verify decimals using the explicit field mapping in this reference.
+- **Problem:** Missing authorization checks prior to state update.
+  **Solution:** Cross-validate against the Security Audit register before deployment.
+
+## Related Skills
+
+- @smart-contract-formal-verification - verifies state invariants mathematically.
+- @web3-rate-limiting-circuit-breaker - provides operational guardrails and threshold breakers.
+- @stellar-anchor-integration - covers SEP-10 and SEP-24 anchor compliance flows.
+
+## Reusable Prompt
+
+```
+I want to establish a verified Cross-Chain Relayer Security Audit register for our production protocol.
+Guide me through the required field parameters and output the corresponding SQL DDL and JSON Schema.
+```

package/bundled-skills/deep-research-framework/SKILL.md

@@ -0,0 +1,81 @@
+---
+name: deep-research-framework
+description: "Framework for deep research reports: define the question and tier sources first, cross-verify, then write conclusion-first reports with explicit uncertainty statements. Use when the user asks for a research report, topic investigation, or competitive analysis."
+category: research
+risk: safe
+source: https://github.com/alapha888/agent-skills-en
+source_repo: alapha888/agent-skills-en
+source_type: community
+date_added: "2026-10-01"
+author: alapha888
+tags: [research-reports, source-verification, analysis]
+tools: [claude, cursor, gemini, codex]
+license: MIT
+license_source: https://github.com/alapha888/agent-skills-en/blob/main/LICENSE
+---
+
+# Deep Research Report Framework
+
+Produce a report whose "conclusions are trustworthy, process is traceable, and the unknowns are explicitly marked." The quality floor of research is set by its sources, not its prose.
+
+## When to Use
+
+- Use when the user asks for a research report, topic investigation, or competitive analysis.
+- Use when sources need tiering and cross-verification before writing conclusions.
+
+## Workflow
+
+1. **Define the question**: write in one sentence what the report must answer. Add at most 3 sub-questions. Starting before the question is clear guarantees the research will sprawl.
+2. **Tier your sources** (tier before you search, so you don't believe whatever you find first):
+   - Primary: official docs, original papers, original filings, protocol/legal texts, measured data.
+   - Secondary: reputable press, industry reports, expert interviews.
+   - Tertiary: social-media posts, forum threads, aggregator sites — leads only, never evidence.
+3. **Cross-verify**: key conclusions need two or more independent sources. Two sources quoting the same origin don't count as independent. If no second source exists, downgrade the conclusion to "single-source claim" and mark it as such.
+4. **Writing structure** (conclusion first):
+   - Opening: 3–5 lines stating the core conclusions.
+   - Body: one section per sub-question, each in "conclusion → evidence → sources" order.
+   - Closing: uncertainty statement — "what wasn't found, what's speculation, under what conditions the conclusions change."
+5. **Timestamps**: date every key fact ("as of Sep 2026"). Undated information is treated as "possibly stale" by default.
+
+## Rules
+
+- Mark speculation as speculation. Use "may", "likely", "unverified" — never dress speculation up with "clearly" or "it is well known".
+- No tertiary source supports a core conclusion. A forum thread can point a direction, never serve as evidence.
+- Every number in the report has a source. A number without a source is deleted, not rewritten.
+- State "what you don't know" before "what you know" — honest uncertainty beats pretty certainty.
+
+## Minimal example (report outline template)
+
+```markdown
+# Research Report: <Topic> (example outline)
+
+**Core conclusions** (3–5 lines): …
+
+## 1. Sub-question one
+- Conclusion: …
+- Evidence: … (source: primary/secondary, as of …)
+- Evidence: … (second independent source)
+
+## 2. Sub-question two
+…
+
+## Uncertainty statement
+- Not found: …
+- Single-source claims: … (one source only, pending verification)
+- Invalidation conditions: if … changes, conclusion X in this report needs reassessment.
+```
+
+## Limitations
+
+- Source quality is the ceiling of the report. Declared "primary sources" cannot be verified for authenticity by this skill; it only enforces the tiering and cross-verification discipline.
+- Independent-source requirements are a judgment call. Two outlets quoting the same wire story or press release count as one origin, and the skill cannot detect shared-origin syndication automatically.
+- Web access is required for source-backed research. Without search or fetch tools the skill stops rather than writing a report from memory, or marks every external fact `[UNVERIFIED]` and warns on the cover.
+- Recency claims expire. A dated fact ("as of Sep 2026") is only valid until the underlying source changes; the skill does not re-verify older reports.
+
+## Anti-patterns
+
+- ❌ Single-source verdicts: one social-media post becomes "research shows".
+- ❌ Speculation as fact: "clearly" and "it is well known" are the most dangerous words in a research report.
+- ❌ Undated facts: 2023 data presented as the current state; the conclusion quietly expires.
+- ❌ Evidence pile with no conclusion: 20 sources listed, and the reader still can't tell what the author believes.
+- ❌ Hiding the unknowns: burying what wasn't found makes the report look omniscient and plants landmines.

package/bundled-skills/defi-yield-strategy-allocator/SKILL.md

@@ -0,0 +1,124 @@
+---
+name: defi-yield-strategy-allocator
+description: 'Multi-vault automated yield strategy allocation register: APY benchmarks, impermanent loss risk tiers, and rebalancing triggers.'
+category: engineering
+risk: safe
+source: self
+source_type: self
+date_added: "2026-10-01"
+author: Ranjeet2063
+tags: [defi, yield, soroban, vault, liquidity, finance, stellar]
+tools: []
+source_repo: Ranjeet2063/agentic-awesome-skills
+---
+
+# DeFi Yield Strategy Allocation Register
+
+**What it is:** Monitors capital efficiency, yield compounding schedules, and downside protection bounds across decentralized finance yield protocols.
+
+## Overview
+
+Provides a standardized, auditable framework and data model for **DeFi Yield Strategy Allocation Register** operations across distributed engineering and decentralized application systems.
+
+## When to Use This Skill
+
+- When formalizing architectural contracts, security invariants, or operational limits for DeFi Yield Strategy Allocation Register.
+- When cross-functional review is required between protocol developers, smart contract auditors, and AI engineering agents.
+- When generating reproducible CSV, SQL DDL, JSON Schema, and Notion property registers for tracking compliance.
+
+## How It Works
+
+1. Define the parameters, thresholds, and identity bindings required for the target operational register.
+2. Select appropriate boundary enforcement values from validated enum select sets.
+3. Export standardized artifacts (CSV table, SQL DDL, JSON Schema) to integrate into validation CI pipelines.
+
+## Field Reference
+
+| # | Field Name | Type | SQL Type | JSON Schema Type | Notion Property Type | Example Value |
+|---|------------|------|----------|------------------|----------------------|---------------|
+| 1 | Strategy Allocation ID | `id` | `SERIAL PRIMARY KEY` | `integer` | Text | `YLD-001` |
+| 2 | Target Protocol Strategy | `text` | `VARCHAR(64)` | `string` | Text | `Soroban AMM Liquidity Staking` |
+| 3 | Allocated Capital Principal | `currency` | `NUMERIC(24,7)` | `number` | Number | `100000.0000000` |
+| 4 | Base APY Yield % | `number` | `NUMERIC(6,2)` | `number` | Number | `14.25` |
+| 5 | Impermanent Loss Risk Score | `select` | `VARCHAR(32)` | `string` | Select | `Low (Stablecoin Pair)` |
+| 6 | Max Protocol Drawdown Cap % | `number` | `NUMERIC(5,2)` | `number` | Number | `5.00` |
+| 7 | Automated Harvest Frequency Hours | `number` | `INTEGER` | `number` | Number | `12` |
+| 8 | Emergency Unwind Trigger | `select` | `VARCHAR(64)` | `string` | Select | `Price Divergence > 3%` |
+| 9 | Capital Allocation Health | `select` | `VARCHAR(32)` | `string` | Select | `Optimum Yield` |
+| 10 | Portfolio Manager | `text` | `VARCHAR(64)` | `string` | Text | `Ranjeet2063` |
+| 11 | Last Rebalance Date | `date` | `DATE` | `string, format: date` | Date | `2026-10-01` |
+
+## Select Options
+
+**Impermanent Loss Risk Score**
+
+```
+Low (Stablecoin Pair) | Moderate (Correlated) | High (Volatile)
+```
+
+**Emergency Unwind Trigger**
+
+```
+Price Divergence > 3% | TVL Drain > 20% | Oracle Failure
+```
+
+**Capital Allocation Health**
+
+```
+Optimum Yield | Underperforming | Unwinding | Liquidated
+```
+
+## Relations
+
+- `Audit Reference` -> links to the formal review documentation or test repository.
+- `Target Architecture` -> links to the deployed contract or autonomous agent runtime component.
+
+## Examples
+
+**Prompt**
+
+```
+How do I configure and track DeFi Yield Strategy Allocation Register for our production environment?
+```
+
+**Recommended Next Step**
+
+> Generate the unified field schema, SQL DDL migration, and JSON validation schema to register into your system catalog.
+>
+> Workflow: Define criteria -> Run automated verification -> Record baseline -> Monitor invariants.
+
+## Best Practices
+
+- Enforce strict typing on numerical bounds and currency amounts; avoid unstructured free-text fields for critical states.
+- Re-run validation test suites on every state-altering commit or parameter change.
+- Keep example data synthetic and isolated from production cryptographic keys or private endpoints.
+
+## Limitations
+
+- Provides architectural specifications, data models, and verification schemas; does not execute direct transaction signing without authorized external tooling.
+- Requires network connectivity and valid RPC credentials when querying on-chain states.
+
+## Security & Safety Notes
+
+- All parameters declare `risk: safe`. No unauthorized state modification or privileged credential access is performed.
+- Use synthetic dummy keys and mock addresses in test suites and local verification scripts.
+
+## Common Pitfalls
+
+- **Problem:** Mismatched decimal precision between contract runtime and database register.
+  **Solution:** Always verify decimals using the explicit field mapping in this reference.
+- **Problem:** Missing authorization checks prior to state update.
+  **Solution:** Cross-validate against the Security Audit register before deployment.
+
+## Related Skills
+
+- @soroban-liquidity-pool - covers AMM invariant and LP-share modelling.
+- @web3-rate-limiting-circuit-breaker - provides operational guardrails and threshold breakers.
+- @soroban-oracle-data-feed-audit - covers oracle heartbeat and stale-price handling.
+
+## Reusable Prompt
+
+```
+I want to establish a verified DeFi Yield Strategy Allocation Register register for our production protocol.
+Guide me through the required field parameters and output the corresponding SQL DDL and JSON Schema.
+```