@pratikpsl/agent-skills 0.5.0 → 0.7.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (40) hide show
  1. package/README.md +113 -51
  2. package/dist/cli/commands/add.d.ts.map +1 -1
  3. package/dist/cli/commands/add.js +2 -0
  4. package/dist/cli/commands/add.js.map +1 -1
  5. package/dist/cli/commands/dotnet-setup.d.ts +2 -11
  6. package/dist/cli/commands/dotnet-setup.d.ts.map +1 -1
  7. package/dist/cli/commands/dotnet-setup.js +5 -32
  8. package/dist/cli/commands/dotnet-setup.js.map +1 -1
  9. package/dist/cli/commands/list.js +1 -1
  10. package/dist/cli/commands/list.js.map +1 -1
  11. package/dist/cli/commands/setup.d.ts +9 -0
  12. package/dist/cli/commands/setup.d.ts.map +1 -0
  13. package/dist/cli/commands/setup.js +77 -0
  14. package/dist/cli/commands/setup.js.map +1 -0
  15. package/dist/cli/index.js +16 -2
  16. package/dist/cli/index.js.map +1 -1
  17. package/dist/core/copy-skills.d.ts +3 -1
  18. package/dist/core/copy-skills.d.ts.map +1 -1
  19. package/dist/core/copy-skills.js +35 -11
  20. package/dist/core/copy-skills.js.map +1 -1
  21. package/dist/core/ide-map.d.ts +10 -0
  22. package/dist/core/ide-map.d.ts.map +1 -0
  23. package/dist/core/ide-map.js +37 -0
  24. package/dist/core/ide-map.js.map +1 -0
  25. package/dist/core/manifest.d.ts +2 -10
  26. package/dist/core/manifest.d.ts.map +1 -1
  27. package/dist/core/manifest.js +120 -24
  28. package/dist/core/manifest.js.map +1 -1
  29. package/dist/core/resolve-pack.d.ts.map +1 -1
  30. package/dist/core/resolve-pack.js +23 -2
  31. package/dist/core/resolve-pack.js.map +1 -1
  32. package/package.json +25 -7
  33. package/templates/default/instructions.md +34 -0
  34. package/templates/dotnet/AgentSkills/entry-points/{copilot-instructions.md → entry-point.md} +2 -3
  35. package/templates/shared/manifest.json +62 -0
  36. package/templates/dotnet/AgentSkills/entry-points/AGENTS.md +0 -50
  37. package/templates/dotnet/AgentSkills/entry-points/CLAUDE.md +0 -50
  38. package/templates/dotnet/AgentSkills/entry-points/antigravity-instructions.md +0 -50
  39. package/templates/dotnet/AgentSkills/entry-points/cursor-instructions.md +0 -50
  40. package/templates/dotnet/manifest.json +0 -92
@@ -1,50 +0,0 @@
1
- # Antigravity Entry Point
2
-
3
- This file is a lightweight entry point for the Antigravity IDE (Google DeepMind).
4
-
5
- `AgentSkills/` is the single source of truth for skills, agents, memory,
6
- prerequisites, checklists, and project rules used by all coding agents and
7
- AI-enabled IDEs in this repository.
8
-
9
- ## Start Here
10
-
11
- 1. Read `AgentSkills/OPERATING.md`.
12
- 2. Follow skill routing in `AgentSkills/skills/INDEX.md`.
13
- 3. Load role definitions from `AgentSkills/agents/` only when the task requires them.
14
-
15
- Do not duplicate canonical instructions in this file. Edit shared guidance in
16
- `AgentSkills/`.
17
-
18
- ## Mandatory Bootstrap (All Agents — Enforced)
19
-
20
- Before changing any file or producing a final answer for any **code-changing**
21
- task in this repository, you MUST complete the following bootstrap sequence
22
- in order. Do NOT skip this sequence even for tasks that appear simple or quick.
23
-
24
- 1. Read `AgentSkills/OPERATING.md`.
25
- 2. Read `AgentSkills/memory/index.md`; load only the domain lesson file(s)
26
- relevant to the current task (do not load all files at once).
27
- 3. Read `AgentSkills/skills/INDEX.md` (when it exists).
28
- 4. Always load `AgentSkills/skills/core/SKILL.md`.
29
- 5. Load any task-specific skill from `AgentSkills/skills/` that matches the task.
30
- 6. For .NET / C# implementation tasks, load `AgentSkills/agents/developer.agent.md`.
31
- 7. For design, CQRS structure, SQL schema, or architecture tasks, load
32
- `AgentSkills/agents/architect.agent.md`.
33
- 8. Inspect the worktree context before editing so existing user changes are
34
- preserved.
35
- 9. Define the verification path for the task before making changes.
36
-
37
- ## Completion Gate (All Agents — Enforced)
38
-
39
- Before marking any code-changing task complete:
40
-
41
- 1. Run the pre-submit checklist in `AgentSkills/skills/core/SKILL.md`.
42
- 2. Run the harness validator (unless the task is documentation-only or the
43
- environment cannot run it — in that case, state the reason explicitly):
44
-
45
- ```powershell
46
- pwsh ./tools/Harness/validate.ps1
47
- ```
48
-
49
- 3. Do not claim completion when required checks fail. List failures clearly and
50
- leave the work in a reviewable state.
@@ -1,50 +0,0 @@
1
- # Cursor / Antigravity Entry Point
2
-
3
- This file is a lightweight entry point for Cursor and Antigravity IDEs.
4
-
5
- `AgentSkills/` is the single source of truth for skills, agents, memory,
6
- prerequisites, checklists, and project rules used by all coding agents and
7
- AI-enabled IDEs in this repository.
8
-
9
- ## Start Here
10
-
11
- 1. Read `AgentSkills/OPERATING.md`.
12
- 2. Follow skill routing in `AgentSkills/skills/INDEX.md`.
13
- 3. Load role definitions from `AgentSkills/agents/` only when the task requires them.
14
-
15
- Do not duplicate canonical instructions in this file. Edit shared guidance in
16
- `AgentSkills/`.
17
-
18
- ## Mandatory Bootstrap (All Agents — Enforced)
19
-
20
- Before changing any file or producing a final answer for any **code-changing**
21
- task in this repository, you MUST complete the following bootstrap sequence
22
- in order. Do NOT skip this sequence even for tasks that appear simple or quick.
23
-
24
- 1. Read `AgentSkills/OPERATING.md`.
25
- 2. Read `AgentSkills/memory/index.md`; load only the domain lesson file(s)
26
- relevant to the current task (do not load all files at once).
27
- 3. Read `AgentSkills/skills/INDEX.md` (when it exists).
28
- 4. Always load `AgentSkills/skills/core/SKILL.md`.
29
- 5. Load any task-specific skill from `AgentSkills/skills/` that matches the task.
30
- 6. For .NET / C# implementation tasks, load `AgentSkills/agents/developer.agent.md`.
31
- 7. For design, CQRS structure, SQL schema, or architecture tasks, load
32
- `AgentSkills/agents/architect.agent.md`.
33
- 8. Inspect the worktree context before editing so existing user changes are
34
- preserved.
35
- 9. Define the verification path for the task before making changes.
36
-
37
- ## Completion Gate (All Agents — Enforced)
38
-
39
- Before marking any code-changing task complete:
40
-
41
- 1. Run the pre-submit checklist in `AgentSkills/skills/core/SKILL.md`.
42
- 2. Run the harness validator (unless the task is documentation-only or the
43
- environment cannot run it — in that case, state the reason explicitly):
44
-
45
- ```powershell
46
- pwsh ./tools/Harness/validate.ps1
47
- ```
48
-
49
- 3. Do not claim completion when required checks fail. List failures clearly and
50
- leave the work in a reviewable state.
@@ -1,92 +0,0 @@
1
- {
2
- "name": "@pratikpsl/agent-skills-dotnet",
3
- "version": "0.5.0",
4
- "description": "AI agent skill definitions for .NET/C# projects (CQRS, MediatR, EF Core, xUnit, ASP.NET Core).",
5
- "skills": [
6
- {
7
- "name": "OPERATING",
8
- "description": "Shared operating contract: bootstrap sequence, working rules, completion gate for all agents.",
9
- "path": "AgentSkills/OPERATING.md"
10
- },
11
- {
12
- "name": "core",
13
- "description": "Load on every task. Core principles: think before coding, surgical changes, goal-driven testing.",
14
- "path": "AgentSkills/skills/core"
15
- },
16
- {
17
- "name": "code-standards",
18
- "description": "C# coding standards: naming, no magic values, DRY, readability rules.",
19
- "path": "AgentSkills/skills/code-standards"
20
- },
21
- {
22
- "name": "design",
23
- "description": "SOLID, KISS, YAGNI, and design pattern rules for .NET architecture.",
24
- "path": "AgentSkills/skills/design"
25
- },
26
- {
27
- "name": "dotnet-best-practices",
28
- "description": "General .NET and EF Core best practices: async, cancellation, no N+1, projection.",
29
- "path": "AgentSkills/skills/dotnet-best-practices"
30
- },
31
- {
32
- "name": "csharp-xunit",
33
- "description": "xUnit unit testing guidelines including data-driven tests and mocking patterns.",
34
- "path": "AgentSkills/skills/csharp-xunit"
35
- },
36
- {
37
- "name": "mcp_dotnet",
38
- "description": "Model Context Protocol tool rules for building and reviewing .NET MCP server tools.",
39
- "path": "AgentSkills/skills/mcp_dotnet"
40
- },
41
- {
42
- "name": "dotnet-api",
43
- "description": "RESTful API structure, pipeline, OpenAPI, CORS, auth, versioning for .NET 10 Web API.",
44
- "path": "AgentSkills/skills/dotnet-api"
45
- },
46
- {
47
- "name": "harness",
48
- "description": "Guide and sensor setup for agent operations, CI hooks, and validation scripts.",
49
- "path": "AgentSkills/skills/harness"
50
- },
51
- {
52
- "name": "agents",
53
- "description": "Agent persona definitions: architect (design/CQRS) and developer (.NET C# implementation).",
54
- "path": "AgentSkills/agents"
55
- },
56
- {
57
- "name": "memory",
58
- "description": "Persistent agent memory: domain lesson files and memory schema for learning loops.",
59
- "path": "AgentSkills/memory"
60
- },
61
- {
62
- "name": "entry-point:claude",
63
- "description": "Lightweight Claude entry point — routes the agent to AgentSkills/OPERATING.md.",
64
- "path": "AgentSkills/entry-points/CLAUDE.md",
65
- "dest": "CLAUDE.md"
66
- },
67
- {
68
- "name": "entry-point:codex",
69
- "description": "Lightweight Codex/OpenAI entry point — routes the agent to AgentSkills/OPERATING.md.",
70
- "path": "AgentSkills/entry-points/AGENTS.md",
71
- "dest": "AGENTS.md"
72
- },
73
- {
74
- "name": "entry-point:copilot",
75
- "description": "Lightweight GitHub Copilot entry point — routes the agent to AgentSkills/OPERATING.md.",
76
- "path": "AgentSkills/entry-points/copilot-instructions.md",
77
- "dest": ".github/copilot-instructions.md"
78
- },
79
- {
80
- "name": "entry-point:cursor",
81
- "description": "Lightweight Cursor entry point — routes the agent to AgentSkills/OPERATING.md.",
82
- "path": "AgentSkills/entry-points/cursor-instructions.md",
83
- "dest": ".cursor/rules/instructions.md"
84
- },
85
- {
86
- "name": "entry-point:antigravity",
87
- "description": "Lightweight Antigravity (Google DeepMind) entry point — routes the agent to AgentSkills/OPERATING.md.",
88
- "path": "AgentSkills/entry-points/antigravity-instructions.md",
89
- "dest": ".agents/GEMINI.md"
90
- }
91
- ]
92
- }