@pratikpsl/agent-skills 0.3.0 → 0.4.0

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.
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@pratikpsl/agent-skills",
3
3
  "type": "module",
4
- "version": "0.3.0",
4
+ "version": "0.4.0",
5
5
  "description": "CLI to scaffold and manage AI agent skills across projects",
6
6
  "bin": {
7
7
  "agent-skills": "bin/agent-skills.js"
@@ -14,3 +14,37 @@ AI-enabled IDEs in this repository.
14
14
 
15
15
  Do not duplicate canonical instructions in this file. Edit shared guidance in
16
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.
@@ -14,3 +14,37 @@ AI-enabled IDEs in this repository.
14
14
 
15
15
  Do not duplicate canonical instructions in this file. Edit shared guidance in
16
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.
@@ -14,3 +14,37 @@ AI-enabled IDEs in this repository.
14
14
 
15
15
  Do not duplicate canonical instructions in this file. Edit shared guidance in
16
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.
@@ -14,3 +14,37 @@ AI-enabled IDEs in this repository.
14
14
 
15
15
  Do not duplicate canonical instructions in this file. Edit shared guidance in
16
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.
@@ -5,16 +5,16 @@ Do NOT load domain files you do not need. Never load all files at once.
5
5
 
6
6
  ## Domain Map
7
7
 
8
- | Domain | Load when | File | Lessons |
9
- |--------|-----------|------|---------|
10
- | api | CQRS, MediatR, commands, queries, controllers, endpoints | [lessons/api.md](lessons/api.md) | 1 |
11
- | db | EF Core, migrations, schema, seeding, repositories | [lessons/db.md](lessons/db.md) | 0 |
12
- | infra | Build, paths, CI, tooling, portability, AgentSkills setup | [lessons/infra.md](lessons/infra.md) | 5 |
13
- | auth | Authentication, authorisation, JWT, policies, claims | [lessons/auth.md](lessons/auth.md) | 0 |
14
- | testing | xUnit, test data, mocking, coverage, assertions | [lessons/testing.md](lessons/testing.md) | 0 |
15
- | csharp | C# language features, async/await, naming, code style | [lessons/csharp.md](lessons/csharp.md) | 0 |
16
- | design | SOLID, CQRS, Repository, patterns, architecture decisions | [lessons/design.md](lessons/design.md) | 0 |
17
- | mcp | MCP server tools, transports, contracts, .NET MCP integration | [lessons/mcp.md](lessons/mcp.md) | 0 |
8
+ | Domain | Load when | File | Lessons |
9
+ | ------- | ------------------------------------------------------------- | ---------------------------------------- | ------- |
10
+ | api | CQRS, MediatR, commands, queries, controllers, endpoints | [lessons/api.md](lessons/api.md) | 1 |
11
+ | db | EF Core, migrations, schema, seeding, repositories | [lessons/db.md](lessons/db.md) | 0 |
12
+ | infra | Build, paths, CI, tooling, portability, AgentSkills setup | [lessons/infra.md](lessons/infra.md) | 6 |
13
+ | auth | Authentication, authorisation, JWT, policies, claims | [lessons/auth.md](lessons/auth.md) | 0 |
14
+ | testing | xUnit, test data, mocking, coverage, assertions | [lessons/testing.md](lessons/testing.md) | 0 |
15
+ | csharp | C# language features, async/await, naming, code style | [lessons/csharp.md](lessons/csharp.md) | 0 |
16
+ | design | SOLID, CQRS, Repository, patterns, architecture decisions | [lessons/design.md](lessons/design.md) | 0 |
17
+ | mcp | MCP server tools, transports, contracts, .NET MCP integration | [lessons/mcp.md](lessons/mcp.md) | 0 |
18
18
 
19
19
  ## Writing a lesson?
20
20
 
@@ -1,3 +1,3 @@
1
1
  # Design Lessons
2
2
 
3
- <!-- No lessons yet. Append using the format in memory/schema.md -->
3
+ RULE: Always use flat vertical slice feature folders; never create nested Commands or Queries subfolders. #wrong-path 2026-07-05
@@ -5,3 +5,4 @@ RULE: Use repo-relative paths in all agent and IDE instruction files; never writ
5
5
  RULE: When splitting a monolithic memory file into domain files, grep the whole repo for the old path and update every reference before deleting the original. #stale-reference 2026-06-07
6
6
  RULE: Always check native command exit codes explicitly in PowerShell harness scripts. #native-exit-code 2026-06-21
7
7
  RULE: Run dotnet format after patching C# files; this repo enforces CRLF and no final newline. #format-fail 2026-07-01
8
+ RULE: Always execute the full AgentSkills bootstrap sequence before any code-changing task, even simple ones. #bootstrap-skip 2026-07-05
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@pratikpsl/agent-skills-dotnet",
3
- "version": "0.3.0",
3
+ "version": "0.4.0",
4
4
  "description": "AI agent skill definitions for .NET/C# projects (CQRS, MediatR, EF Core, xUnit, ASP.NET Core).",
5
5
  "skills": [
6
6
  {