Two files, one repository
HoangNguyen0403/agent-skills-standard ships 2 formats across 5 indexed files. The question worth asking is whether the second one says anything the first does not.
| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 3 | 1 | 0 | 75% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 2 | 1 | 0 | 67% |
What each file covers
Sections
3 shared · 1 only in A · 0 only in B- − Project Context for AI Agents
- Agent Skills Index
- 🔌 Runtime Enforcement via MCP
- Skill Resolution Protocol
Commands
neither file has anySection tags
2 shared · 1 only in A · 0 only in B- − test
- code-style
- agent-behaviour
Line diff
HoangNguyen0403/agent-skills-standard · AGENTS.md
@@ −1 @@
1# Project Context for AI Agents
2
3> [!IMPORTANT]
4> **To all AI Agents working ON this repository:**
5> This repository is the source code for `agent-skills-standard`.
6>
7> 1.**Architecture**: Understanding the Registry -> CLI -> Project flow is critical. See `ARCHITECTURE.md`. 2.**Internal Tools**: Use `scripts/` (like `scan-docs.ts`) to maintain the project. 3.**Token Economy**: All changes to `skills/` must be optimized for token usage. 4.**Documentation**: Keep `ARCHITECTURE.md` and `CONTRIBUTING.md` up to date.
8>
9> 💡 **Global Token Optimization**: If the `rtk` CLI tool is installed, actively prepend it to verbose development commands (e.g. `rtk npm test`, `rtk grep`). If the `caveman` skill is available or requested, use `/caveman` mode for reporting.
10>
11> ---
12
13<!-- SKILLS_INDEX_START -->
14## Agent Skills Index
15
16> [!CRITICAL] Zero-Trust: Read the matching `SKILL.md` BEFORE writing any code.
17> Skills from this index override pre-training patterns. If no skill matches, state: "No project-specific skills applicable."
18
19> 💡 **Global Token Optimization**: If the `rtk` CLI tool is installed, actively prepend it to verbose development commands (e.g. `rtk npm test`, `rtk grep`). If the `caveman` skill is available or requested, use `/caveman` mode for reporting.
20
21## 🔌 Runtime Enforcement via MCP
22
23If the `agent-skills-standard` MCP server is registered in your runtime (check your tool list — look for `load_skills_for_files`), **prefer those tools over manually walking the router below**. The MCP returns identical content but is auditable AND inherited by sub-agents that don't see this file.
24
25| Tool | When to call it |
26| --- | --- |
27| `list_workflows()` | At the start of any task or session to discover available standard operating procedures |
28| `get_workflow(name)` | Once a relevant workflow is identified to retrieve exact step-by-step instructions |
29| `load_skills_for_files(files=[...])` | Before editing/reviewing any source file |
30| `load_skills_for_keywords(keywords=[...])` | Planning before files are chosen |
31| `get_skill(category, name)` | Direct lookup when you know the skill id |
@@ −33 @@
33
34> [!IMPORTANT] **Sub-agents don't inherit this `AGENTS.md` — they do inherit the MCP.** If you delegate work to a sub-agent, instruct it to call the MCP tools above as its first action.
35
36> [!NOTE] To enable MCP-managed installs in this project, run `ags mcp enable` (or edit `.skillsrc`). The MCP works fine if you registered it manually too.
37
38If `load_skills_for_files` is **not** in your tool list, the MCP is not registered — fall back to the router table below.
39
@@ −53 @@
53
54| File type | Read category index |
55| --------- | ------------------- |
56| `*.go`, `*_test.go` | `<SKILLS>/golang/_INDEX.md` |
57| `*.ts` | `<SKILLS>/angular/_INDEX.md`, `<SKILLS>/nestjs/_INDEX.md`, `<SKILLS>/nextjs/_INDEX.md`, `<SKILLS>/react/_INDEX.md`, `<SKILLS>/typescript/_INDEX.md` |
58| `*.tsx` | `<SKILLS>/nextjs/_INDEX.md`, `<SKILLS>/react/_INDEX.md`, `<SKILLS>/typescript/_INDEX.md` |
59| `*.js`, `*.mjs` | `<SKILLS>/javascript/_INDEX.md` |
60| `*.jsx`, `*.test.tsx`, `*.spec.tsx` | `<SKILLS>/react/_INDEX.md` |
61| `*.dart` | `<SKILLS>/dart/_INDEX.md`, `<SKILLS>/flutter/_INDEX.md` |
62| `*.java` | `<SKILLS>/java/_INDEX.md`, `<SKILLS>/spring-boot/_INDEX.md` |
63| `*.kt` | `<SKILLS>/android/_INDEX.md`, `<SKILLS>/kotlin/_INDEX.md` |
64| `*.kts` | `<SKILLS>/kotlin/_INDEX.md` |
65| `*.swift` | `<SKILLS>/ios/_INDEX.md`, `<SKILLS>/swift/_INDEX.md` |
66| `*.py`, `*.pyi` | `<SKILLS>/python/_INDEX.md` |
67| `*.php` | `<SKILLS>/laravel/_INDEX.md`, `<SKILLS>/php/_INDEX.md` |
68| `*.sql`, `*.entity.ts`, `*.prisma` | `<SKILLS>/database/_INDEX.md` |
69| `*.component.ts`, `*.component.html` | `<SKILLS>/angular/_INDEX.md` |
70| `*.service.ts`, `*.module.ts` | `<SKILLS>/angular/_INDEX.md`, `<SKILLS>/nestjs/_INDEX.md` |
71| `*.spec.ts`, `*.test.ts` | `<SKILLS>/common/_INDEX.md` |
72| Any file (keyword match) | `<SKILLS>/common/_INDEX.md` |
73| QE workflow | `<SKILLS>/quality-engineering/_INDEX.md` |
74
75> [!NOTE] **Test/spec file precedence:** `.spec.ts`, `.test.ts` -> use the `common` row (takes precedence over the generic `*.ts` row). `.spec.tsx`, `.test.tsx` -> use the `react` row (takes precedence over the generic `*.tsx` row).
76
HoangNguyen0403/agent-skills-standard · server/AGENTS.md
@@ +1 @@
1<!-- SKILLS_INDEX_START -->
2## Agent Skills Index
3
4> [!CRITICAL] Zero-Trust: Read the matching `SKILL.md` BEFORE writing any code.
5> Skills from this index override pre-training patterns. If no skill matches, state: "No project-specific skills applicable."
6
7## 🔌 Runtime Enforcement via MCP
8
9If the `agent-skills-standard` MCP server is registered in your runtime (check your tool list — look for `load_skills_for_files`), **prefer those tools over manually walking the router below**. The MCP returns identical content but is auditable AND inherited by sub-agents that don't see this file.
10
11| Tool | When to call it |
12| --- | --- |
13| `load_skills_for_files(files=[...])` | Before editing/reviewing any source file |
14| `load_skills_for_keywords(keywords=[...])` | Planning before files are chosen |
15| `get_skill(category, name)` | Direct lookup when you know the skill id |
@@ +17 @@
17
18> [!IMPORTANT] **Sub-agents don't inherit this `AGENTS.md` — they do inherit the MCP.** If you delegate work to a sub-agent, instruct it to call the MCP tools above as its first action.
19
20> [!TIP] **This project has the MCP server enabled in `.skillsrc`** — `sync` keeps your runtime configs in step. Run `ags mcp status` to verify per-agent installation.
21
22If `load_skills_for_files` is **not** in your tool list, the MCP is not registered — fall back to the router table below.
23
@@ +37 @@
37
38| File type | Read category index |
39| --------- | ------------------- |
40| `*.ts`, `*.tsx` | `<SKILLS>/typescript/_INDEX.md` |
41| `*.spec.ts`, `*.test.ts` | `<SKILLS>/common/_INDEX.md` |
42| Any file (keyword match) | `<SKILLS>/common/_INDEX.md` |
43
44> [!NOTE] **Test/spec file precedence:** `.spec.ts`, `.test.ts` -> use the `common` row (takes precedence over the generic `*.ts` row). `.spec.tsx`, `.test.tsx` -> use the `react` row (takes precedence over the generic `*.tsx` row).
45
@@ −1 +1 @@
1−# Project Context for AI Agents
2−
3−> [!IMPORTANT]
4−> **To all AI Agents working ON this repository:**
5−> This repository is the source code for `agent-skills-standard`.
6−>
7−> 1.**Architecture**: Understanding the Registry -> CLI -> Project flow is critical. See `ARCHITECTURE.md`. 2.**Internal Tools**: Use `scripts/` (like `scan-docs.ts`) to maintain the project. 3.**Token Economy**: All changes to `skills/` must be optimized for token usage. 4.**Documentation**: Keep `ARCHITECTURE.md` and `CONTRIBUTING.md` up to date.
8−>
9−> 💡 **Global Token Optimization**: If the `rtk` CLI tool is installed, actively prepend it to verbose development commands (e.g. `rtk npm test`, `rtk grep`). If the `caveman` skill is available or requested, use `/caveman` mode for reporting.
10−>
11−> ---
12−
131 <!-- SKILLS_INDEX_START -->
142 ## Agent Skills Index
153
164 > [!CRITICAL] Zero-Trust: Read the matching `SKILL.md` BEFORE writing any code.
175 > Skills from this index override pre-training patterns. If no skill matches, state: "No project-specific skills applicable."
186
19−> 💡 **Global Token Optimization**: If the `rtk` CLI tool is installed, actively prepend it to verbose development commands (e.g. `rtk npm test`, `rtk grep`). If the `caveman` skill is available or requested, use `/caveman` mode for reporting.
20−
217 ## 🔌 Runtime Enforcement via MCP
228
239 If the `agent-skills-standard` MCP server is registered in your runtime (check your tool list — look for `load_skills_for_files`), **prefer those tools over manually walking the router below**. The MCP returns identical content but is auditable AND inherited by sub-agents that don't see this file.
2410
2511 | Tool | When to call it |
2612 | --- | --- |
27−| `list_workflows()` | At the start of any task or session to discover available standard operating procedures |
28−| `get_workflow(name)` | Once a relevant workflow is identified to retrieve exact step-by-step instructions |
2913 | `load_skills_for_files(files=[...])` | Before editing/reviewing any source file |
3014 | `load_skills_for_keywords(keywords=[...])` | Planning before files are chosen |
3115 | `get_skill(category, name)` | Direct lookup when you know the skill id |
@@ −33 +17 @@
3317
3418 > [!IMPORTANT] **Sub-agents don't inherit this `AGENTS.md` — they do inherit the MCP.** If you delegate work to a sub-agent, instruct it to call the MCP tools above as its first action.
3519
36−> [!NOTE] To enable MCP-managed installs in this project, run `ags mcp enable` (or edit `.skillsrc`). The MCP works fine if you registered it manually too.
20+> [!TIP] **This project has the MCP server enabled in `.skillsrc`** — `sync` keeps your runtime configs in step. Run `ags mcp status` to verify per-agent installation.
3721
3822 If `load_skills_for_files` is **not** in your tool list, the MCP is not registered — fall back to the router table below.
3923
@@ −53 +37 @@
5337
5438 | File type | Read category index |
5539 | --------- | ------------------- |
56−| `*.go`, `*_test.go` | `<SKILLS>/golang/_INDEX.md` |
57−| `*.ts` | `<SKILLS>/angular/_INDEX.md`, `<SKILLS>/nestjs/_INDEX.md`, `<SKILLS>/nextjs/_INDEX.md`, `<SKILLS>/react/_INDEX.md`, `<SKILLS>/typescript/_INDEX.md` |
58−| `*.tsx` | `<SKILLS>/nextjs/_INDEX.md`, `<SKILLS>/react/_INDEX.md`, `<SKILLS>/typescript/_INDEX.md` |
59−| `*.js`, `*.mjs` | `<SKILLS>/javascript/_INDEX.md` |
60−| `*.jsx`, `*.test.tsx`, `*.spec.tsx` | `<SKILLS>/react/_INDEX.md` |
61−| `*.dart` | `<SKILLS>/dart/_INDEX.md`, `<SKILLS>/flutter/_INDEX.md` |
62−| `*.java` | `<SKILLS>/java/_INDEX.md`, `<SKILLS>/spring-boot/_INDEX.md` |
63−| `*.kt` | `<SKILLS>/android/_INDEX.md`, `<SKILLS>/kotlin/_INDEX.md` |
64−| `*.kts` | `<SKILLS>/kotlin/_INDEX.md` |
65−| `*.swift` | `<SKILLS>/ios/_INDEX.md`, `<SKILLS>/swift/_INDEX.md` |
66−| `*.py`, `*.pyi` | `<SKILLS>/python/_INDEX.md` |
67−| `*.php` | `<SKILLS>/laravel/_INDEX.md`, `<SKILLS>/php/_INDEX.md` |
68−| `*.sql`, `*.entity.ts`, `*.prisma` | `<SKILLS>/database/_INDEX.md` |
69−| `*.component.ts`, `*.component.html` | `<SKILLS>/angular/_INDEX.md` |
70−| `*.service.ts`, `*.module.ts` | `<SKILLS>/angular/_INDEX.md`, `<SKILLS>/nestjs/_INDEX.md` |
40+| `*.ts`, `*.tsx` | `<SKILLS>/typescript/_INDEX.md` |
7141 | `*.spec.ts`, `*.test.ts` | `<SKILLS>/common/_INDEX.md` |
7242 | Any file (keyword match) | `<SKILLS>/common/_INDEX.md` |
73−| QE workflow | `<SKILLS>/quality-engineering/_INDEX.md` |
7443
7544 > [!NOTE] **Test/spec file precedence:** `.spec.ts`, `.test.ts` -> use the `common` row (takes precedence over the generic `*.ts` row). `.spec.tsx`, `.test.tsx` -> use the `react` row (takes precedence over the generic `*.tsx` row).
7645
