site-api-adapter

スター9

フォーク1

更新日2026年7月8日 04:04

Conditional post-verification skill for turning already stable reverse-engineering findings into a reusable site API adapter: adapter.yaml, request/response schema, route classification, prompt-router rules, runbook, smoke tests, and service boundary documentation. Trigger only when the user explicitly asks for adapter标准化, adapter.yaml, schema/runbook/prompt-router, 接口化沉淀, or when website-314-api-delivery calls it after real API reproduction is verified. Do not trigger while endpoints, sign/token, challenge/WAF, or business acceptance are still being discovered.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

ソース

zy950618

zy950618/oh_my_reverse_skill

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Site API Adapter

Do NOT Trigger When

用户的接口还没逆向稳定，处于"找加密入口/补环境/WAF 保护分类"阶段（沉淀必须在能稳定复现之后） → 切到 reverse-js-crawler / imperva-waf-reese84
用户只要单次脚本/采集数据，不会复用，不需要 schema/runbook → 切到 reverse-js-crawler
用户要求"完整 FastAPI 接口测试交付"、314 接入请求或本地基础框架接入 → 切到 website-314-api-delivery（让它做总控，本 skill 是它的 references 输出之一）
用户做的不是 Web/H5 接口沉淀 → 不属于本仓库范围
用户问的是"skill 评分" → 切到 skills-evaluation-governance

Purpose

把单站点逆向结果升级为可复用、可回归、可交接的接口化单元。这个 Skill 关注沉淀和标准化，不负责深度还原某个 token。

Standard LOOP Adapter Boundary

This skill is a conditional_escalation: it only runs after endpoint, sign/token, challenge/WAF, and business acceptance questions are resolved or explicitly scoped as blocked. Adapter output must preserve pure API delivery constraints and must not treat browser-captured replay, copied cookies, or browser profiles as stable adapter inputs.

Workflow

输入归档和分类：
- 站点信息、页面入口、接口列表、参数依赖、认证/风控状态、样本响应。
- 标记 market、locale、currency、stage、protection、framework。
生成 adapter：
- adapter.yaml：站点、市场、入口、接口、路由、依赖、风控类型、限流策略。
- schema.json：请求/响应结构、必填字段、错误码、字段映射。
- runbook.md：如何验证、如何排查、如何扩展。
设计 prompt-router：
- 把用户请求分类为纯 HTTP、JS runtime、浏览器诊断、WAF 专项、FastAPI 接口测试交付、本地基础框架接入、不可自动化。
- 输出 JSON，不能只输出自然语言。
写 smoke tests：
- 至少覆盖一个成功路径、一个业务错误、一个保护/不可用路径。
- 记录稳定性循环的 exact code/message/count。
维护边界：
- adapter 只描述站点能力和调用规范。
- 加密实现放 crypto/runtime。
- 业务服务放 services。
- 反爬专项放 anti_bot。

Success Criteria

adapter 能表达接口、依赖、保护、路由、测试和失败边界。
prompt-router 能输出结构化分类，不靠自然语言猜测。
已区分 adapter 沉淀、JS 逆向、WAF 专项、FastAPI 接口测试交付和可选本地基础框架接入。
已把站点/市场差异写入站点经验库。
已有 smoke、negative、regression 或 boundary eval。

Tool Policy

开始实现前 Read ~/.claude/skills/karpathy-guidelines/SKILL.md,确认 4 条原则:Think Before Coding / Simplicity First / Surgical Changes / Goal-Driven Execution。这是基础层规范,所有执行类 skill 强制依赖。
遇到逆向运行时问题(断点/时间/cookie/TLS 指纹/风控恢复/接口变更)Read ~/.claude/skills/oh_my_reverse_skill/99-SKILLS治理/10-逆向运行时常见问题.md。
输出结论、扩范围或做并发前 Read ~/.claude/skills/oh_my_reverse_skill/99-SKILLS治理/11-AI事实证据规约.md / 12-反泛化与任务收敛规约.md / 13-并发指纹与会话隔离规约.md。
改端点/字段/状态/保护/实现/eval 前后 Read 14-知识图谱行程与关联规约.md / 15-AI变更风险与回归校验规约.md,并更新 knowledge-graph.md / impact-regression.md。

Boundaries

这是接口化沉淀 Skill，不是 token 深度还原 Skill。
不负责具体 WAF token 逆向；遇到 WAF 切到 imperva-waf-reese84。
不负责完整 FastAPI 接口测试交付或本地基础框架接入；遇到全流程交付切到 website-314-api-delivery。

Governance

If the user asks for FastAPI interface test delivery or implementation through a local base framework such as 314, do not stop at adapter design. Use website-314-api-delivery as the orchestrator, then produce adapter/schema/runbook as part of the delivery.

Version: 0.2.0
Status: scorecard baseline
Site memory: adapter decisions should update 站点经验库/<domain>/route-decisions.md and market-matrix.md.
Backtest: include adapter-from-notes, prompt-router, negative token-reverse, and regression classification evals.
CI: use Skill Bench or local backtest; quick_validate must pass before accepting changes.

References

references/adapter-schema.md: adapter 字段建议。
references/prompt-router.md: 分类输出规范。
references/governance.md: versioning, change log, Skill Bench, GitHub CI, quick_validate, and drift-test policy.

このリポジトリの他の Skills

同じリポジトリ

skills-evaluation-governance

zy950618/oh_my_reverse_skill

Use this skill to score, refine, backtest, and govern Codex/Claude skills: assess whether notes are installable skills, create evals, prepare Skill Bench structure, compare SKILL.md quality, define trigger/negative-trigger tests, track drift, maintain versions, record changes, and enforce admission gates for new Skills. Trigger when the user asks to rate skills, use Skill Bench, convert notes into usable skills, evaluate trigger accuracy, maintain a skills library, score a new Skill before accepting it, run backtests, or Chinese requests such as SKILLS评分, 技能评分, 可用SKILLS, 新增Skill准入, Skill Bench跑分, 回测, 漂移测试, 长期治理, 版本号, 变更记录, 触发词优化, 负例测试, or 技能库治理.

2026-07-129

web-h5-loop-engineering

zy950618/oh_my_reverse_skill

Orchestration entry for Web/H5 reverse-engineering work only when the user explicitly asks for LOOP, closed-loop handling, multi-agent/three-role verification, repeated validation, execution ledger, acceptance report, or when a prior attempt failed because evidence, repeat verification, cleanup, impact, or backend acceptance was incomplete. It coordinates executor, verifier, and governor roles with loop ledger, acceptance report, fixture freshness, and metrics. Do not trigger for ordinary one-pass crawler tasks, simple fixture freshness checks, or single-tool JS work; use reverse-js-crawler or the relevant support tool first.

2026-07-129

find-crypto-entry

zy950618/oh_my_reverse_skill

Internal/support tool for locating the JS source of one concrete encrypted request field, sign, x-sign, authKey, or token. Use directly only when the user explicitly asks for an atomic entry-location task such as "找加密入口", "签名怎么算", or "这个请求头字段哪里生成"; otherwise let reverse-js-crawler or website-314-api-delivery choose it. Do not trigger for generic crawler delivery, ordinary request inspection, challenge/WAF backend acceptance, or non-encrypted parameters.

2026-07-129

env-patch

zy950618/oh_my_reverse_skill

Internal/support tool for running a previously identified browser encryption module in Node.js with env_core.js, prototype/native-function shims, and minimal stubs. Use directly only when the user explicitly asks for 补环境, Node里跑, webpack模块提取, or when an entry skill has already located the module and needs browser-to-Node reproduction. Do not trigger for ordinary browser debugging, AST deobfuscation, generic Node.js code, crawler delivery, or unresolved API discovery.

2026-07-099

js-page-runtime-parity

zy950618/oh_my_reverse_skill

Extract page-level JavaScript runtime dependencies and verify Browser, Node, V8, and PageRuntime output parity for authorized targets or localhost labs without generating risk tokens or defeat behavior.

2026-07-099

authorized-target-adapter

zy950618/oh_my_reverse_skill

Adapt reverse-engineering workflows only for owned or explicitly authorized targets with scope, allowed hosts, rate limits, stop conditions, redaction, and business data assertions.

2026-07-089

name	site-api-adapter
standard_type	conditional_escalation
description	Conditional post-verification skill for turning already stable reverse-engineering findings into a reusable site API adapter: adapter.yaml, request/response schema, route classification, prompt-router rules, runbook, smoke tests, and service boundary documentation. Trigger only when the user explicitly asks for adapter标准化, adapter.yaml, schema/runbook/prompt-router, 接口化沉淀, or when website-314-api-delivery calls it after real API reproduction is verified. Do not trigger while endpoints, sign/token, challenge/WAF, or business acceptance are still being discovered.
platforms	["web","h5"]

Site API Adapter

Do NOT Trigger When

用户的接口还没逆向稳定，处于"找加密入口/补环境/WAF 保护分类"阶段（沉淀必须在能稳定复现之后） → 切到 reverse-js-crawler / imperva-waf-reese84
用户只要单次脚本/采集数据，不会复用，不需要 schema/runbook → 切到 reverse-js-crawler
用户要求"完整 FastAPI 接口测试交付"、314 接入请求或本地基础框架接入 → 切到 website-314-api-delivery（让它做总控，本 skill 是它的 references 输出之一）
用户做的不是 Web/H5 接口沉淀 → 不属于本仓库范围
用户问的是"skill 评分" → 切到 skills-evaluation-governance

Purpose

把单站点逆向结果升级为可复用、可回归、可交接的接口化单元。这个 Skill 关注沉淀和标准化，不负责深度还原某个 token。

Standard LOOP Adapter Boundary

Workflow

输入归档和分类：
- 站点信息、页面入口、接口列表、参数依赖、认证/风控状态、样本响应。
- 标记 market、locale、currency、stage、protection、framework。
生成 adapter：
- adapter.yaml：站点、市场、入口、接口、路由、依赖、风控类型、限流策略。
- schema.json：请求/响应结构、必填字段、错误码、字段映射。
- runbook.md：如何验证、如何排查、如何扩展。
设计 prompt-router：
- 把用户请求分类为纯 HTTP、JS runtime、浏览器诊断、WAF 专项、FastAPI 接口测试交付、本地基础框架接入、不可自动化。
- 输出 JSON，不能只输出自然语言。
写 smoke tests：
- 至少覆盖一个成功路径、一个业务错误、一个保护/不可用路径。
- 记录稳定性循环的 exact code/message/count。
维护边界：
- adapter 只描述站点能力和调用规范。
- 加密实现放 crypto/runtime。
- 业务服务放 services。
- 反爬专项放 anti_bot。

Success Criteria

adapter 能表达接口、依赖、保护、路由、测试和失败边界。
prompt-router 能输出结构化分类，不靠自然语言猜测。
已区分 adapter 沉淀、JS 逆向、WAF 专项、FastAPI 接口测试交付和可选本地基础框架接入。
已把站点/市场差异写入站点经验库。
已有 smoke、negative、regression 或 boundary eval。

Tool Policy

开始实现前 Read ~/.claude/skills/karpathy-guidelines/SKILL.md,确认 4 条原则:Think Before Coding / Simplicity First / Surgical Changes / Goal-Driven Execution。这是基础层规范,所有执行类 skill 强制依赖。
遇到逆向运行时问题(断点/时间/cookie/TLS 指纹/风控恢复/接口变更)Read ~/.claude/skills/oh_my_reverse_skill/99-SKILLS治理/10-逆向运行时常见问题.md。
输出结论、扩范围或做并发前 Read ~/.claude/skills/oh_my_reverse_skill/99-SKILLS治理/11-AI事实证据规约.md / 12-反泛化与任务收敛规约.md / 13-并发指纹与会话隔离规约.md。
改端点/字段/状态/保护/实现/eval 前后 Read 14-知识图谱行程与关联规约.md / 15-AI变更风险与回归校验规约.md,并更新 knowledge-graph.md / impact-regression.md。

Boundaries

这是接口化沉淀 Skill，不是 token 深度还原 Skill。
不负责具体 WAF token 逆向；遇到 WAF 切到 imperva-waf-reese84。
不负责完整 FastAPI 接口测试交付或本地基础框架接入；遇到全流程交付切到 website-314-api-delivery。

Governance

Version: 0.2.0
Status: scorecard baseline
Site memory: adapter decisions should update 站点经验库/<domain>/route-decisions.md and market-matrix.md.
Backtest: include adapter-from-notes, prompt-router, negative token-reverse, and regression classification evals.
CI: use Skill Bench or local backtest; quick_validate must pass before accepting changes.

References

references/adapter-schema.md: adapter 字段建议。
references/prompt-router.md: 分类输出规范。
references/governance.md: versioning, change log, Skill Bench, GitHub CI, quick_validate, and drift-test policy.