skill-domain-self-optimizer

skill-domain-self-optimizer is a skill for Claude Code, Codex from TashanGKD/tashan-cursor-skills. It costs 140 tokens per session (2,315 once invoked), scanned A, original, MIT.

A gap-driven improvement workflow for one area of an AI agent system. It uses health reports and scenario records to propose new skills, edits, or missing trigger paths.

In plain words
What is it for?
Use it to fix documented gaps in a selected domain, such as missing skills, unclear triggers, or mismatched inputs and outputs.
Why use it?
It turns observed failures into specific repair actions instead of producing a general list of problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to fix documented gaps in a selected domain, such as missing skills, unclear triggers, or mismatched inputs and outputs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tashangkd/tashan-cursor-skills/skill-domain-self-optimizer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add TashanGKD/tashan-cursor-skills --skill skill-domain-self-optimizer
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-domain-self-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-domain-self-optimizer/github.svg)](https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-domain-self-optimizer)
Your own site
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-domain-self-optimizer"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-domain-self-optimizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-domain-self-optimizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-domain-self-optimizer"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-domain-self-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00140 $0.02315
Opus 5 $0.00070 $0.01157
Sonnet 5 $0.00028 $0.00463
Haiku 4.5 $0.00014 $0.00231

Measured 9d ago against content hash b049543e83cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skill-domain-self-optimizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/skill-domain-self-optimizer/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

域自我优化(skill-domain-self-optimizer)

关系类型:depends-on(依赖域健康报告 + 沙盘文件 + DOMAIN-REGISTRY) 强绑定 Rule:R2 NO_FABRICATION / R6 ARTIFACT_FIRST / R13 RULE_BEATS_STYLE


核心设计原则

Gap → 行动 原则:每个 Gap 必须对应一个具体可执行的行动建议(不能只说「缺什么」,必须说「用什么Skill填补、或新建什么Skill」)。

证据优先 原则:建议必须基于沙盘中已记录的具体 Gap,不能凭推断扩展到沙盘未覆盖的问题。


激活后立即执行

Step 1  确认处理范围
        询问(如果用户未指定):
        「请指定要优化的域:
          (1) 产品开发  (2) 认知结构  (3) 公司运营  (4) 内容宣传  (5) Skill体系  (6) 全部」
        
        若是由 skill-closure-verifier-meta 调用,直接使用传入的域名称。

Step 2  读取输入数据(R3 READ_FIRST)
        并行读取:
        - _内部总控/skill-system-design/domain-health-[域名]-*.md(域健康报告,取最新)
        - _内部总控/skill-system-design/sandboxes/[域名]/*.md(该域所有沙盘)
        - _内部总控/skill-system-design/DOMAIN-REGISTRY.md(节点图)
        - _内部总控/skill-system-design/NODE-IO-CONTRACTS.md(I/O契约)
        
        若健康报告不存在:
        → 先调用 skill-domain-health-check 生成健康报告,再继续
        
        若沙盘数量 < 3:
        → 在报告中注明「沙盘样本不足,建议扩充后重新运行」
        → 但仍基于现有数据给出建议,不阻断

Step 3  Gap 分类与模式识别
        汇总所有 Gap 来源(健康报告 + 沙盘 Gap 发现表格):
        
        按类型分类:
        - 【类型A】缺节点:对应Skill文件不存在
        - 【类型B】缺触发条件:节点间的触发边缺失或不明确
        - 【类型C】I/O不匹配:节点的输出与下游节点的输入要求不对应
        - 【类型D】文档不自洽:域内核心文档之间内容矛盾
        - 【类型E】边界盲区:入口节点未覆盖的触发词/场景
        
        识别模式:
        → 同一节点被多个沙盘标注 Gap?→ 该节点是高优先修复点
        → 同一边(触发条件)被多个沙盘标注断裂?→ 该链路是系统性缺陷

Step 4  生成行动建议
        对每类 Gap,生成对应的行动方案:
        
        【类型A处理:缺节点】
        → 直接建议:「新建 Skill [skill-name],对应节点 [节点ID]」
        → 输出 Skill 产品定义草稿(2-3句话描述功能、触发词、I/O)
        → 标注:「建议通过 skill-designer(Level [N])正式设计」
        
        【类型B处理:缺触发条件】
        → 定位缺失的触发边(哪个节点完成后应触发哪个下游节点)
        → 建议:「修改 [上游Skill].SKILL.md:在 [步骤N] 末尾增加触发下游的明确步骤」
        → 给出具体的修改建议文字(如:「在 Step X 末尾增加:触发条件满足时,建议用户执行 [下游节点]」)
        
        【类型C处理:I/O不匹配】
        → 定位不匹配点:上游输出的格式/路径 ≠ 下游需要的格式/路径
        → 建议:「修改 [Skill].SKILL.md:明确输出格式/路径」或「修改 NODE-IO-CONTRACTS 更正描述」
        
        【类型D处理:文档不自洽】
        → 建议触发 doc-consolidator 或 cognitive-consistency-check(域相关)
        
        【类型E处理:边界盲区】
        → 建议:「更新 [Skill].SKILL.md 的 description 触发词部分,增加 [场景描述]」

Step 5  优先级排序
        按以下规则排序行动建议:
        
        P0(立即执行):
        - 缺节点且是关键传播路径上的节点
        - 多个沙盘均标注的相同 Gap
        
        P1(近期执行):
        - 缺触发条件(影响闭环完整性)
        - I/O不匹配(影响数据流正确性)
        
        P2(计划执行):
        - 边界盲区覆盖(扩展而非修复)
        - 文档自洽问题(可在下次复盘时处理)

Step 6  输出域优化建议报告(R6:必须写文件)
        写入:_内部总控/skill-system-design/domain-optimizer-[域名]-YYYYMMDD.md
        
        格式(见下方「报告格式」)
        
        同时在对话中输出摘要(已识别 N 个Gap,生成 M 条行动建议)

Step 7  路由执行建议
        P0 行动建议:
        → 询问用户:「是否现在立即处理 P0 项?」
        → 若同意:路由到对应 Skill(skill-designer / skill-rule-修改规范)
        
        P1/P2 行动建议:
        → 建议追加到 PENDING-SKILLS.md(如果是新建Skill)
        → 或告知用户「下次运行 skill-rule-修改规范 时处理」

Read the full file on GitHub · 198 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 198 lines · 140 tokens per session scan A b049543e83cc

Subscribe to this mod's changes

skill-domain-self-optimizer is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 140 tokens to every session and 2,315 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

android-feature

Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…

orbitalsonic/AndroidPilot · 72 tokens

template-helpers

Catalog of the reusable building blocks shipped with this Android template — BaseActivity/BaseFragment, the helpers/ extension files (navigation, lifecycle, toast, snackbar, dialogs, images, permissions, theme, locale, settings intents, date, delay), common/ (Firebase, network, observers), and…

orbitalsonic/AndroidPilot · 92 tokens

android-new-project

Workflow for turning a fresh copy of this Android template into a new app — renaming the package/namespace/applicationId, branding (icons, splash, palette, fonts), Firebase setup, signing config, stripping unused sample screens, and verifying the foundation. Use when the user says they are starting a new app…

orbitalsonic/AndroidPilot · 83 tokens

android-preflight

Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…

orbitalsonic/AndroidPilot · 79 tokens

android-ui-theming

Rules for Android XML layouts, Material 3 components, semantic color tokens, light/dark theming, dimensions (sdp/ssp), string resources and localization, accessibility, and edge-to-edge insets. Use when creating or editing any layout, drawable, style, color, vector, or string resource, or when a screen must work in…

orbitalsonic/AndroidPilot · 81 tokens

android-upgrade

Workflow for changing an existing working Android project — upgrading dependencies, AGP/Gradle or SDK levels, migrating deprecated APIs, refactoring, and fixing bugs, without breaking what already works. Covers baseline verification, scoping the diff, targetSdk behaviour changes, SharedPreferences/Room data…

orbitalsonic/AndroidPilot · 86 tokens