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.
npx skills add TashanGKD/tashan-cursor-skills --skill skill-capture-closuregit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote 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.
[](https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-capture-closure)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-capture-closure"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-capture-closure/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.
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-capture-closure"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-capture-closure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00157 | $0.05908 |
| Opus 5 | $0.00078 | $0.02954 |
| Sonnet 5 | $0.00031 | $0.01182 |
| Haiku 4.5 | $0.00016 | $0.00591 |
Grade A, and why
skill-capture-closure 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任务复盘(skill-capture-closure)
核心原则:复盘 = 修改(B/K 对象有缺陷 → 修复)+ 沉淀(新经验/洞见 → 写入系统)
主分类轴是「目标对象类型(B/K)」,不是「经验现象类型」。
- B-objects = 行为规范(Skill / Rule / Agent)
- K-objects = 知识对象(原则 K0 / 框架 K1 / 参考 K2 / 规范 K3 / 项目规格 K4 / 碎片)
知识导航表(执行前必须理解的概念根)
本 Skill 的步骤设计基于以下文档的核心概念。若不理解这些概念,步骤无法正确执行。 执行前应确认已理解(或快速扫读关键章节)。
| 层级 | 文档 | 需要理解的关键概念 |
|---|---|---|
| D0 认知根(必读) | _内部总控/认知结构/L1_系统性文档/系统架构思维维度/自进化智能体系统形式规范_v1.0.md |
层1:B/K/S 三类对象定义;层2:间隙(Gap)定义;层5:R/M/G 基础设施;层7:D_op = {create, modify, delete, merge, split} |
| D3 规范参考 | _内部总控/认知结构/L1_系统性文档/系统架构思维维度/Skill体系设计原则_v1.0.md |
§2.2 Rule 本质;§2.3 Skill 本质;§2.4 Agent 本质;§2.5 三型统一决策树 |
| D3 对象分类 | _内部总控/认知结构/L1_系统性文档/系统架构思维维度/系统对象全量分类表_20260320.md |
类型A(Rule)/ B(Skill)/ C(Agent)/ E(认知文档)/ G(开发规范)的完整定义与存放位置 |
| D4 运行时数据 | .cursor/skills/skill-index/SKILL-INDEX.md |
当前所有 B-objects 的目录名、版本、状态(Step 1 读取) |
核心概念速查(如无法读完整文档,至少理解这三条):
① B-object(行为对象)= 编码「在条件C下执行动作A」的可执行规则
= Skill(任务流程)/ Rule(普遍约束)/ Agent(隔离执行器)
→ 修改 B-object = 改变系统的行为方式
② K-object(知识对象)= 编码「关于世界的陈述性事实」的知识文档
= K0原则 / K1框架 / K2外部参考 / K3执行规范 / K4项目规格 / fragment
→ 修改 K-object = 更新系统的知识储备
③ D_op = modify(修复:对象已存在但有缺陷)
vs create(沉淀:对象应存在但尚未存在)
→ 复盘 = 找出所有 modify Gap + create Gap,分别处理
激活后立即执行(顺序不可跳过)
Step 1 【建立知识基础】
Read: .cursor/skills/skill-index/SKILL-INDEX.md
→ 了解现有 Skill 全貌,防止重复新建
Step 2 【双向诊断】产出 Gap 清单
─── 修复方向(向后看,找失败)───
① 这次任务哪里执行不符合预期?
② 哪个 B-object(Skill/Rule/Agent)步骤不清晰/不完整/有问题?
③ 哪个 K-object(文档/规范/踩坑速查)内容有误、过时或缺失?
─── 沉淀方向(向前看,找收获)───
④ 有什么新发现/洞见值得记录?
⑤ 有什么可复用模式,但目前没有对应的 B-object?
⑥ 有什么实践经验,下次遇到同类任务会用到?
→ 对每个有内容的问题,产出一条 Gap 记录(一句话描述)
→ 若全部为空 → 输出「本次无需复盘,任务已完整执行」,结束
Step 3 【Gap 分类】对每条 Gap,按三个维度分类
维度1 — 目标对象类型:
B-object = 行为规范(Skill / Rule / Agent)
K-object = 知识对象(原则/框架/参考/规范/项目规格/碎片)
维度2 — 操作类型:
modify = 对象已存在,内容需修改(来自修复方向 ①②③)
create = 对象应存在但不存在,需新建(来自沉淀方向 ④⑤⑥)
维度3 — 子类型:
B → Skill | Rule | Agent
K → K0原则 | K1框架 | K2外部参考 | K3规范 | K4项目规格 | fragment
→ 输出分类清单,确认后进入 Step 4
Step 4 【根因诊断】仅对 B-object.modify 类型执行,K-object 和 create 类型跳过
────────────────────────────────────────
问题A:AI 是否知道相关规范的存在?
→ 【不知道】→ 根因:【连接缺口】
规范/文档没有通过 D0 / alwaysApply Rule / Step 1 进入 AI 上下文。
→ 产物方向:修复连接机制(补 D0 行 / 新建 Rule / 调整引用位置)
────────────────────────────────────────
→ 【知道,但没执行】→ 继续问题B:
问题B:规范通过什么机制传递的?
→ 只在某个被触发的 Skill 里(Skill 这次没被触发):
根因:【类型错误】应升为 alwaysApply Rule
→ 规范在 Rule/D0 中,但表述模糊/有歧义:
根因:【规范质量问题】重写使其更明确
→ 规范表述是「建议/应该」而非「必须/禁止」:
根因:【执行力度不足】升级为禁止表述
→ 以上皆否,AI 确实疏忽了:
根因:【执行层疏忽】加注意事项/提醒即可
────────────────────────────────────────
→ 输出:「根因:[类型] — [一句话说明]」
→ 写入后续 ceremony 变更记录的「经验核心」字段
Step 5 【路由执行】按 Step 3 分类,对每条 Gap 执行对应 ceremony
B-object ceremonies:
B.Skill.modify → Step B-S-M
B.Skill.create → Step B-S-C
B.Rule.modify → Step B-R-M
B.Rule.create → Step B-R-C
B.Agent.modify → Step B-A-M
B.Agent.create → Step B-A-C
K-object ceremonies:
K.K3.modify → Step K-3-M
K.K3.create → Step K-3-C
K.K1.modify → Step K-1-M
K.K1.create → Step K-1-C
K.K0.modify → Step K-0-M
K.fragment → Step K-F-C
K.K2.* → Step K-2
K.K4.* → Step K-4
Step 6 【注册更新】所有 ceremony 执行完后
→ B-object 有变动 → 更新 SKILL-INDEX(版本/状态/日期 + 底部变更记录)
→ 新建 Skill 时 → 执行 role-menu 同步检查(见下方说明)
→ K-object 有变动 → 不更新 SKILL-INDEX
Step 7 【收尾反馈】
「✅ 复盘完成:
修改类:B-object [N] 个 / K-object [M] 个
沉淀类:B-object [N] 个 / K-object [M] 个
[每条处理结果简述]」
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 440 lines · 157 tokens per session scan A 03073edd59e9
skill-capture-closure is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 157 tokens to every session and 5,908 once invoked, about $0.0008 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.
Other skills, from other repositories
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…
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…
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…
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…
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…
android-build-config
Gradle and build configuration rules for this template — AGP 9 / Gradle 9 DSL (built-in Kotlin, compileSdk block, optimization block instead of minify/proguard), the gradle/libs.versions.toml version catalog, R8 keep rules in keepRules/.keep, gradle.properties defaults, and manifest registration. Use when editing…