claudient 0.1.0

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 (283) hide show
  1. package/.claude-plugin/plugin.json +42 -0
  2. package/CONTEXT.md +58 -0
  3. package/README.md +165 -0
  4. package/agents/build-resolvers/de/python-resolver.md +64 -0
  5. package/agents/build-resolvers/de/typescript-resolver.md +65 -0
  6. package/agents/build-resolvers/es/python-resolver.md +64 -0
  7. package/agents/build-resolvers/es/typescript-resolver.md +65 -0
  8. package/agents/build-resolvers/fr/python-resolver.md +64 -0
  9. package/agents/build-resolvers/fr/typescript-resolver.md +65 -0
  10. package/agents/build-resolvers/nl/python-resolver.md +64 -0
  11. package/agents/build-resolvers/nl/typescript-resolver.md +65 -0
  12. package/agents/build-resolvers/python-resolver.md +62 -0
  13. package/agents/build-resolvers/typescript-resolver.md +63 -0
  14. package/agents/core/architect.md +64 -0
  15. package/agents/core/code-reviewer.md +78 -0
  16. package/agents/core/de/architect.md +66 -0
  17. package/agents/core/de/code-reviewer.md +80 -0
  18. package/agents/core/de/planner.md +63 -0
  19. package/agents/core/de/security-reviewer.md +93 -0
  20. package/agents/core/es/architect.md +66 -0
  21. package/agents/core/es/code-reviewer.md +80 -0
  22. package/agents/core/es/planner.md +63 -0
  23. package/agents/core/es/security-reviewer.md +93 -0
  24. package/agents/core/fr/architect.md +66 -0
  25. package/agents/core/fr/code-reviewer.md +80 -0
  26. package/agents/core/fr/planner.md +63 -0
  27. package/agents/core/fr/security-reviewer.md +93 -0
  28. package/agents/core/nl/architect.md +66 -0
  29. package/agents/core/nl/code-reviewer.md +80 -0
  30. package/agents/core/nl/planner.md +63 -0
  31. package/agents/core/nl/security-reviewer.md +93 -0
  32. package/agents/core/planner.md +61 -0
  33. package/agents/core/security-reviewer.md +91 -0
  34. package/guides/agent-orchestration.md +231 -0
  35. package/guides/de/agent-orchestration.md +174 -0
  36. package/guides/de/getting-started.md +164 -0
  37. package/guides/de/hooks-cookbook.md +160 -0
  38. package/guides/de/memory-management.md +153 -0
  39. package/guides/de/security.md +180 -0
  40. package/guides/de/skill-authoring.md +214 -0
  41. package/guides/de/token-optimization.md +156 -0
  42. package/guides/es/agent-orchestration.md +174 -0
  43. package/guides/es/getting-started.md +164 -0
  44. package/guides/es/hooks-cookbook.md +160 -0
  45. package/guides/es/memory-management.md +153 -0
  46. package/guides/es/security.md +180 -0
  47. package/guides/es/skill-authoring.md +214 -0
  48. package/guides/es/token-optimization.md +156 -0
  49. package/guides/fr/agent-orchestration.md +174 -0
  50. package/guides/fr/getting-started.md +164 -0
  51. package/guides/fr/hooks-cookbook.md +227 -0
  52. package/guides/fr/memory-management.md +169 -0
  53. package/guides/fr/security.md +180 -0
  54. package/guides/fr/skill-authoring.md +214 -0
  55. package/guides/fr/token-optimization.md +158 -0
  56. package/guides/getting-started.md +164 -0
  57. package/guides/hooks-cookbook.md +423 -0
  58. package/guides/memory-management.md +192 -0
  59. package/guides/nl/agent-orchestration.md +174 -0
  60. package/guides/nl/getting-started.md +164 -0
  61. package/guides/nl/hooks-cookbook.md +160 -0
  62. package/guides/nl/memory-management.md +153 -0
  63. package/guides/nl/security.md +180 -0
  64. package/guides/nl/skill-authoring.md +214 -0
  65. package/guides/nl/token-optimization.md +156 -0
  66. package/guides/security.md +229 -0
  67. package/guides/skill-authoring.md +226 -0
  68. package/guides/token-optimization.md +169 -0
  69. package/hooks/lifecycle/cost-tracker.md +49 -0
  70. package/hooks/lifecycle/cost-tracker.sh +59 -0
  71. package/hooks/lifecycle/pre-compact-save.md +56 -0
  72. package/hooks/lifecycle/pre-compact-save.sh +37 -0
  73. package/hooks/lifecycle/session-start.md +50 -0
  74. package/hooks/lifecycle/session-start.sh +47 -0
  75. package/hooks/post-tool-use/audit-log.md +53 -0
  76. package/hooks/post-tool-use/audit-log.sh +53 -0
  77. package/hooks/post-tool-use/prettier.md +53 -0
  78. package/hooks/post-tool-use/prettier.sh +49 -0
  79. package/hooks/pre-tool-use/block-dangerous.md +48 -0
  80. package/hooks/pre-tool-use/block-dangerous.sh +76 -0
  81. package/hooks/pre-tool-use/git-push-confirm.md +46 -0
  82. package/hooks/pre-tool-use/git-push-confirm.sh +36 -0
  83. package/mcp/configs/github.json +11 -0
  84. package/mcp/configs/postgres.json +11 -0
  85. package/mcp/de/recommended-servers.md +170 -0
  86. package/mcp/es/recommended-servers.md +170 -0
  87. package/mcp/fr/recommended-servers.md +170 -0
  88. package/mcp/nl/recommended-servers.md +170 -0
  89. package/mcp/recommended-servers.md +168 -0
  90. package/package.json +45 -0
  91. package/prompts/project-starters/de/fastapi-project.md +62 -0
  92. package/prompts/project-starters/de/nextjs-project.md +82 -0
  93. package/prompts/project-starters/es/fastapi-project.md +62 -0
  94. package/prompts/project-starters/es/nextjs-project.md +82 -0
  95. package/prompts/project-starters/fastapi-project.md +60 -0
  96. package/prompts/project-starters/fr/fastapi-project.md +62 -0
  97. package/prompts/project-starters/fr/nextjs-project.md +82 -0
  98. package/prompts/project-starters/nextjs-project.md +80 -0
  99. package/prompts/project-starters/nl/fastapi-project.md +62 -0
  100. package/prompts/project-starters/nl/nextjs-project.md +82 -0
  101. package/prompts/system-prompts/ai-product.md +80 -0
  102. package/prompts/system-prompts/data-pipeline.md +76 -0
  103. package/prompts/system-prompts/de/ai-product.md +82 -0
  104. package/prompts/system-prompts/de/data-pipeline.md +78 -0
  105. package/prompts/system-prompts/de/saas-backend.md +71 -0
  106. package/prompts/system-prompts/es/ai-product.md +82 -0
  107. package/prompts/system-prompts/es/data-pipeline.md +78 -0
  108. package/prompts/system-prompts/es/saas-backend.md +71 -0
  109. package/prompts/system-prompts/fr/ai-product.md +82 -0
  110. package/prompts/system-prompts/fr/data-pipeline.md +78 -0
  111. package/prompts/system-prompts/fr/saas-backend.md +71 -0
  112. package/prompts/system-prompts/nl/ai-product.md +82 -0
  113. package/prompts/system-prompts/nl/data-pipeline.md +78 -0
  114. package/prompts/system-prompts/nl/saas-backend.md +71 -0
  115. package/prompts/system-prompts/saas-backend.md +69 -0
  116. package/prompts/task-specific/changelog.md +81 -0
  117. package/prompts/task-specific/de/changelog.md +83 -0
  118. package/prompts/task-specific/de/debugging.md +78 -0
  119. package/prompts/task-specific/de/pr-description.md +69 -0
  120. package/prompts/task-specific/debugging.md +76 -0
  121. package/prompts/task-specific/es/changelog.md +83 -0
  122. package/prompts/task-specific/es/debugging.md +78 -0
  123. package/prompts/task-specific/es/pr-description.md +69 -0
  124. package/prompts/task-specific/fr/changelog.md +83 -0
  125. package/prompts/task-specific/fr/debugging.md +78 -0
  126. package/prompts/task-specific/fr/pr-description.md +69 -0
  127. package/prompts/task-specific/nl/changelog.md +83 -0
  128. package/prompts/task-specific/nl/debugging.md +78 -0
  129. package/prompts/task-specific/nl/pr-description.md +69 -0
  130. package/prompts/task-specific/pr-description.md +67 -0
  131. package/rules/common/coding-style.md +45 -0
  132. package/rules/common/de/coding-style.md +47 -0
  133. package/rules/common/de/git.md +48 -0
  134. package/rules/common/de/performance.md +40 -0
  135. package/rules/common/de/security.md +45 -0
  136. package/rules/common/de/testing.md +45 -0
  137. package/rules/common/es/coding-style.md +47 -0
  138. package/rules/common/es/git.md +48 -0
  139. package/rules/common/es/performance.md +40 -0
  140. package/rules/common/es/security.md +45 -0
  141. package/rules/common/es/testing.md +45 -0
  142. package/rules/common/fr/coding-style.md +47 -0
  143. package/rules/common/fr/git.md +48 -0
  144. package/rules/common/fr/performance.md +40 -0
  145. package/rules/common/fr/security.md +45 -0
  146. package/rules/common/fr/testing.md +45 -0
  147. package/rules/common/git.md +46 -0
  148. package/rules/common/nl/coding-style.md +47 -0
  149. package/rules/common/nl/git.md +48 -0
  150. package/rules/common/nl/performance.md +40 -0
  151. package/rules/common/nl/security.md +45 -0
  152. package/rules/common/nl/testing.md +45 -0
  153. package/rules/common/performance.md +38 -0
  154. package/rules/common/security.md +43 -0
  155. package/rules/common/testing.md +43 -0
  156. package/rules/language-specific/de/go.md +48 -0
  157. package/rules/language-specific/de/python.md +38 -0
  158. package/rules/language-specific/de/typescript.md +51 -0
  159. package/rules/language-specific/es/go.md +48 -0
  160. package/rules/language-specific/es/python.md +38 -0
  161. package/rules/language-specific/es/typescript.md +51 -0
  162. package/rules/language-specific/fr/go.md +48 -0
  163. package/rules/language-specific/fr/python.md +38 -0
  164. package/rules/language-specific/fr/typescript.md +51 -0
  165. package/rules/language-specific/go.md +46 -0
  166. package/rules/language-specific/nl/go.md +48 -0
  167. package/rules/language-specific/nl/python.md +38 -0
  168. package/rules/language-specific/nl/typescript.md +51 -0
  169. package/rules/language-specific/python.md +36 -0
  170. package/rules/language-specific/typescript.md +49 -0
  171. package/scripts/cli.js +161 -0
  172. package/scripts/link-skills.sh +35 -0
  173. package/scripts/list-skills.sh +34 -0
  174. package/skills/ai-engineering/agent-construction.md +285 -0
  175. package/skills/ai-engineering/claude-api.md +248 -0
  176. package/skills/ai-engineering/de/agent-construction.md +287 -0
  177. package/skills/ai-engineering/de/claude-api.md +250 -0
  178. package/skills/ai-engineering/es/agent-construction.md +287 -0
  179. package/skills/ai-engineering/es/claude-api.md +250 -0
  180. package/skills/ai-engineering/fr/agent-construction.md +287 -0
  181. package/skills/ai-engineering/fr/claude-api.md +250 -0
  182. package/skills/ai-engineering/nl/agent-construction.md +287 -0
  183. package/skills/ai-engineering/nl/claude-api.md +250 -0
  184. package/skills/backend/dotnet/csharp.md +304 -0
  185. package/skills/backend/dotnet/de/csharp.md +306 -0
  186. package/skills/backend/dotnet/es/csharp.md +306 -0
  187. package/skills/backend/dotnet/fr/csharp.md +306 -0
  188. package/skills/backend/dotnet/nl/csharp.md +306 -0
  189. package/skills/backend/go/de/go.md +307 -0
  190. package/skills/backend/go/es/go.md +307 -0
  191. package/skills/backend/go/fr/go.md +307 -0
  192. package/skills/backend/go/go.md +305 -0
  193. package/skills/backend/go/nl/go.md +307 -0
  194. package/skills/backend/nodejs/de/nestjs.md +274 -0
  195. package/skills/backend/nodejs/de/nextjs.md +222 -0
  196. package/skills/backend/nodejs/es/nestjs.md +274 -0
  197. package/skills/backend/nodejs/es/nextjs.md +222 -0
  198. package/skills/backend/nodejs/fr/nestjs.md +274 -0
  199. package/skills/backend/nodejs/fr/nextjs.md +222 -0
  200. package/skills/backend/nodejs/nestjs.md +272 -0
  201. package/skills/backend/nodejs/nextjs.md +220 -0
  202. package/skills/backend/nodejs/nl/nestjs.md +274 -0
  203. package/skills/backend/nodejs/nl/nextjs.md +222 -0
  204. package/skills/backend/python/de/django.md +285 -0
  205. package/skills/backend/python/de/fastapi.md +244 -0
  206. package/skills/backend/python/django.md +283 -0
  207. package/skills/backend/python/es/django.md +285 -0
  208. package/skills/backend/python/es/fastapi.md +244 -0
  209. package/skills/backend/python/fastapi.md +242 -0
  210. package/skills/backend/python/fr/django.md +285 -0
  211. package/skills/backend/python/fr/fastapi.md +244 -0
  212. package/skills/backend/python/nl/django.md +285 -0
  213. package/skills/backend/python/nl/fastapi.md +244 -0
  214. package/skills/data-ml/dbt-data-pipelines.md +155 -0
  215. package/skills/data-ml/de/dbt-data-pipelines.md +157 -0
  216. package/skills/data-ml/de/pandas-polars.md +147 -0
  217. package/skills/data-ml/de/pytorch-tensorflow.md +171 -0
  218. package/skills/data-ml/es/dbt-data-pipelines.md +157 -0
  219. package/skills/data-ml/es/pandas-polars.md +147 -0
  220. package/skills/data-ml/es/pytorch-tensorflow.md +171 -0
  221. package/skills/data-ml/fr/dbt-data-pipelines.md +157 -0
  222. package/skills/data-ml/fr/pandas-polars.md +147 -0
  223. package/skills/data-ml/fr/pytorch-tensorflow.md +171 -0
  224. package/skills/data-ml/nl/dbt-data-pipelines.md +157 -0
  225. package/skills/data-ml/nl/pandas-polars.md +147 -0
  226. package/skills/data-ml/nl/pytorch-tensorflow.md +171 -0
  227. package/skills/data-ml/pandas-polars.md +145 -0
  228. package/skills/data-ml/pytorch-tensorflow.md +169 -0
  229. package/skills/database/de/graphql.md +181 -0
  230. package/skills/database/es/graphql.md +181 -0
  231. package/skills/database/fr/graphql.md +181 -0
  232. package/skills/database/graphql.md +179 -0
  233. package/skills/database/nl/graphql.md +181 -0
  234. package/skills/devops-infra/de/docker.md +133 -0
  235. package/skills/devops-infra/de/github-actions.md +179 -0
  236. package/skills/devops-infra/de/kubernetes.md +129 -0
  237. package/skills/devops-infra/de/terraform.md +130 -0
  238. package/skills/devops-infra/docker.md +131 -0
  239. package/skills/devops-infra/es/docker.md +133 -0
  240. package/skills/devops-infra/es/github-actions.md +179 -0
  241. package/skills/devops-infra/es/kubernetes.md +129 -0
  242. package/skills/devops-infra/es/terraform.md +130 -0
  243. package/skills/devops-infra/fr/docker.md +133 -0
  244. package/skills/devops-infra/fr/github-actions.md +179 -0
  245. package/skills/devops-infra/fr/kubernetes.md +129 -0
  246. package/skills/devops-infra/fr/terraform.md +130 -0
  247. package/skills/devops-infra/github-actions.md +177 -0
  248. package/skills/devops-infra/kubernetes.md +127 -0
  249. package/skills/devops-infra/nl/docker.md +133 -0
  250. package/skills/devops-infra/nl/github-actions.md +179 -0
  251. package/skills/devops-infra/nl/kubernetes.md +129 -0
  252. package/skills/devops-infra/nl/terraform.md +130 -0
  253. package/skills/devops-infra/terraform.md +128 -0
  254. package/skills/finance-payments/de/stripe.md +187 -0
  255. package/skills/finance-payments/es/stripe.md +187 -0
  256. package/skills/finance-payments/fr/stripe.md +187 -0
  257. package/skills/finance-payments/nl/stripe.md +187 -0
  258. package/skills/finance-payments/stripe.md +185 -0
  259. package/workflows/code-review.md +151 -0
  260. package/workflows/de/code-review.md +153 -0
  261. package/workflows/de/debugging-session.md +146 -0
  262. package/workflows/de/feature-development.md +155 -0
  263. package/workflows/de/new-project-bootstrap.md +175 -0
  264. package/workflows/de/refactor-safely.md +150 -0
  265. package/workflows/debugging-session.md +144 -0
  266. package/workflows/es/code-review.md +153 -0
  267. package/workflows/es/debugging-session.md +146 -0
  268. package/workflows/es/feature-development.md +155 -0
  269. package/workflows/es/new-project-bootstrap.md +175 -0
  270. package/workflows/es/refactor-safely.md +150 -0
  271. package/workflows/feature-development.md +153 -0
  272. package/workflows/fr/code-review.md +153 -0
  273. package/workflows/fr/debugging-session.md +146 -0
  274. package/workflows/fr/feature-development.md +155 -0
  275. package/workflows/fr/new-project-bootstrap.md +175 -0
  276. package/workflows/fr/refactor-safely.md +150 -0
  277. package/workflows/new-project-bootstrap.md +173 -0
  278. package/workflows/nl/code-review.md +153 -0
  279. package/workflows/nl/debugging-session.md +146 -0
  280. package/workflows/nl/feature-development.md +155 -0
  281. package/workflows/nl/new-project-bootstrap.md +175 -0
  282. package/workflows/nl/refactor-safely.md +150 -0
  283. package/workflows/refactor-safely.md +148 -0
@@ -0,0 +1,42 @@
1
+ {
2
+ "name": "claudient",
3
+ "version": "0.1.0",
4
+ "description": "The definitive Claude Code knowledge system — skills, agents, hooks, rules, and workflows.",
5
+ "skills": [
6
+ { "id": "backend/python/fastapi", "name": "FastAPI", "file": "skills/backend/python/fastapi.md", "status": "active" },
7
+ { "id": "backend/python/django", "name": "Django", "file": "skills/backend/python/django.md", "status": "active" },
8
+ { "id": "backend/nodejs/nextjs", "name": "Next.js", "file": "skills/backend/nodejs/nextjs.md", "status": "active" },
9
+ { "id": "backend/nodejs/nestjs", "name": "NestJS", "file": "skills/backend/nodejs/nestjs.md", "status": "active" },
10
+ { "id": "backend/go/go", "name": "Go", "file": "skills/backend/go/go.md", "status": "active" },
11
+ { "id": "backend/dotnet/csharp", "name": "C#/.NET", "file": "skills/backend/dotnet/csharp.md", "status": "active" },
12
+ { "id": "ai-engineering/claude-api", "name": "Claude API", "file": "skills/ai-engineering/claude-api.md", "status": "active" },
13
+ { "id": "ai-engineering/agent-construction", "name": "Agent Construction", "file": "skills/ai-engineering/agent-construction.md", "status": "active" },
14
+ { "id": "devops-infra/kubernetes", "name": "Kubernetes", "file": "skills/devops-infra/kubernetes.md", "status": "active" },
15
+ { "id": "devops-infra/terraform", "name": "Terraform", "file": "skills/devops-infra/terraform.md", "status": "active" },
16
+ { "id": "devops-infra/docker", "name": "Docker", "file": "skills/devops-infra/docker.md", "status": "active" },
17
+ { "id": "devops-infra/github-actions", "name": "GitHub Actions", "file": "skills/devops-infra/github-actions.md", "status": "active" },
18
+ { "id": "data-ml/pandas-polars", "name": "Pandas & Polars", "file": "skills/data-ml/pandas-polars.md", "status": "active" },
19
+ { "id": "data-ml/pytorch-tensorflow", "name": "PyTorch & TensorFlow", "file": "skills/data-ml/pytorch-tensorflow.md", "status": "active" },
20
+ { "id": "data-ml/dbt-data-pipelines", "name": "dbt & Data Pipelines", "file": "skills/data-ml/dbt-data-pipelines.md", "status": "active" },
21
+ { "id": "database/graphql", "name": "GraphQL", "file": "skills/database/graphql.md", "status": "active" },
22
+ { "id": "finance-payments/stripe", "name": "Stripe", "file": "skills/finance-payments/stripe.md", "status": "active" }
23
+ ],
24
+ "agents": [
25
+ { "id": "core/planner", "name": "Planner", "file": "agents/core/planner.md", "status": "active" },
26
+ { "id": "core/architect", "name": "Architect", "file": "agents/core/architect.md", "status": "active" },
27
+ { "id": "core/code-reviewer", "name": "Code Reviewer", "file": "agents/core/code-reviewer.md", "status": "active" },
28
+ { "id": "core/security-reviewer", "name": "Security Reviewer", "file": "agents/core/security-reviewer.md", "status": "active" },
29
+ { "id": "build-resolvers/python-resolver", "name": "Python Build Resolver", "file": "agents/build-resolvers/python-resolver.md", "status": "active" },
30
+ { "id": "build-resolvers/typescript-resolver", "name": "TypeScript Build Resolver", "file": "agents/build-resolvers/typescript-resolver.md", "status": "active" }
31
+ ],
32
+ "rules": [
33
+ { "id": "common/coding-style", "name": "Coding Style", "file": "rules/common/coding-style.md", "status": "active" },
34
+ { "id": "common/git", "name": "Git", "file": "rules/common/git.md", "status": "active" },
35
+ { "id": "common/performance", "name": "Performance", "file": "rules/common/performance.md", "status": "active" },
36
+ { "id": "common/security", "name": "Security", "file": "rules/common/security.md", "status": "active" },
37
+ { "id": "common/testing", "name": "Testing", "file": "rules/common/testing.md", "status": "active" },
38
+ { "id": "language-specific/python", "name": "Python Rules", "file": "rules/language-specific/python.md", "status": "active" },
39
+ { "id": "language-specific/typescript", "name": "TypeScript Rules", "file": "rules/language-specific/typescript.md", "status": "active" },
40
+ { "id": "language-specific/go", "name": "Go Rules", "file": "rules/language-specific/go.md", "status": "active" }
41
+ ]
42
+ }
package/CONTEXT.md ADDED
@@ -0,0 +1,58 @@
1
+ # Claudient — Context Map
2
+
3
+ This file defines shared terminology for the Claudient repository. When Claude Code works inside this repo, it uses these definitions as ground truth.
4
+
5
+ ---
6
+
7
+ ## Language
8
+
9
+ **skill** — A Markdown file in `skills/` that defines a slash command for Claude Code. Activated by the user via `/skill-name`. Contains when to activate, when not to, instructions, and an example. Skills are scoped to a domain (backend, devops, data, etc.).
10
+
11
+ **agent** — A Markdown file in `agents/` that defines a subagent: a separate Claude instance spawned by the orchestrator to handle a bounded task. Agents have a specific tool subset and model recommendation.
12
+
13
+ **hook** — A shell script or Python script in `hooks/` that Claude Code executes automatically in response to events: `PreToolUse`, `PostToolUse`, `PreCompact`, `Notification`. Hooks are configured in `settings.json`.
14
+
15
+ **rule** — A Markdown file in `rules/` that describes always-on behavioral guidelines. Rules are included in CLAUDE.md and apply to all sessions in the project.
16
+
17
+ **workflow** — A Markdown file in `workflows/` that documents a multi-step end-to-end process (e.g., feature development, debugging session). Workflows are reference documents, not slash commands.
18
+
19
+ **prompt** — A Markdown file in `prompts/` containing a reusable prompt template. Includes system prompts, project starters, and task-specific prompts.
20
+
21
+ **guide** — A Markdown file in `guides/` that documents a Claude Code concept in depth. Guides are human-readable documentation translated into all 5 languages.
22
+
23
+ **MCP (Model Context Protocol)** — A protocol that allows Claude Code to connect to external servers, exposing additional tools (database access, web search, browser automation). Each MCP server adds tools and consumes context window tokens.
24
+
25
+ **slash command** — A `/command-name` invocation in Claude Code that activates a skill. The skill file is loaded from `.claude/commands/` or `~/.claude/commands/`.
26
+
27
+ **Claude Code** — Anthropic's CLI and IDE extension for using Claude as an interactive coding assistant. Not to be confused with the Claude API or Claude.ai chat interface.
28
+
29
+ **subagent** — A Claude instance spawned by the parent session via the `Agent` tool. Gets a fresh context window, specific tool subset, and model selection. Returns one result to the parent.
30
+
31
+ **tool** — A function Claude can call during a session (Read, Write, Bash, Agent, WebFetch, etc.). In MCP contexts, also refers to functions exposed by MCP servers.
32
+
33
+ **context window** — The total token limit for a Claude session: ~200k tokens for Sonnet/Opus. Includes system prompt, conversation history, tool descriptions, and MCP tool schemas.
34
+
35
+ **CLAUDE.md** — The project instructions file read by Claude Code at session start. Can exist at project, user, or workspace level. Governs Claude's behavior for that context.
36
+
37
+ ---
38
+
39
+ ## Relationships
40
+
41
+ - A **skill** is to Claude Code what a VS Code extension command is to VS Code — a named, activatable behavior
42
+ - A **rule** is always applied; a **skill** is explicitly invoked
43
+ - An **agent** is a subagent spawned by the parent; a **skill** is activated within the current session
44
+ - A **hook** is automatic (event-driven); a **skill** is manual (slash command)
45
+ - A **workflow** describes what to do step by step; a **skill** tells Claude how to do one specific thing
46
+ - A **prompt** is a reusable template; a **guide** is explanatory documentation
47
+
48
+ ---
49
+
50
+ ## Flagged Ambiguities
51
+
52
+ **"skill" vs "command"** — In Claude Code, the underlying files are called "slash commands" or "commands". Claudient uses "skill" to describe the same files when they encode reusable domain expertise. Functionally identical.
53
+
54
+ **"agent" vs "subagent"** — In Claudient's `agents/` directory, files define subagent specifications. In general Claude Code usage, "agent" often means the primary session. Here, "agent" always means a subagent spawned via the `Agent` tool.
55
+
56
+ **"hook" vs "rule"** — Hooks run code; rules set behavioral guidelines. A hook is executable; a rule is instructional.
57
+
58
+ **"workflow" vs "skill"** — A workflow is a multi-step reference document you read before starting a task. A skill is invoked mid-task via slash command to get domain-specific guidance.
package/README.md ADDED
@@ -0,0 +1,165 @@
1
+ # Claudient
2
+
3
+ > The definitive knowledge base for Claude Code — skills, agents, hooks, workflows, prompts, and patterns that multiply what you can build.
4
+
5
+ [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
6
+ [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
7
+ [![Languages](https://img.shields.io/badge/languages-EN%20%7C%20FR%20%7C%20DE%20%7C%20NL%20%7C%20ES-blue)](#translations)
8
+
9
+ **Claudient** is not a tool. It is a *knowledge system* — a community-maintained collection of everything you can drop into your Claude Code environment to immediately work faster, smarter, and with less friction.
10
+
11
+ ---
12
+
13
+ ## Why Claudient?
14
+
15
+ Claude Code is powerful out of the box. But the gap between "it works" and "it works at 10x" is filled with patterns most developers never discover on their own: the right skill for a task, a hook that enforces quality automatically, an agent that handles an entire domain, a workflow that turns a vague goal into shipped code.
16
+
17
+ Claudient collects all of that in one place — organized, searchable, and ready to use.
18
+
19
+ | | Everything-claude-code | **Claudient** |
20
+ |---|---|---|
21
+ | C#/.NET coverage | None | Full |
22
+ | Kubernetes / Terraform | Sparse | Dedicated skill sets |
23
+ | GraphQL / Prisma | None | Full |
24
+ | ML / Data Engineering | Limited | dbt, Spark, MLflow, PyTorch |
25
+ | Fintech / Payments | None | Stripe, payment flows |
26
+ | End-to-end workflows | None | 5 complete workflows |
27
+ | Skill authoring guide | None | First-class guide |
28
+ | Prompt templates | None | Full library |
29
+ | Token optimization | Scattered across 3 docs | Single authoritative guide |
30
+ | Languages | 8 (inconsistent) | EN · FR · DE · NL · ES |
31
+
32
+ ---
33
+
34
+ ## What's Inside
35
+
36
+ ```
37
+ Claudient/
38
+
39
+ ├── guides/ Deep-dive documentation
40
+ │ ├── getting-started.md
41
+ │ ├── skill-authoring.md
42
+ │ ├── token-optimization.md
43
+ │ ├── memory-management.md
44
+ │ ├── security.md
45
+ │ ├── agent-orchestration.md
46
+ │ └── hooks-cookbook.md
47
+
48
+ ├── skills/ Slash command skill definitions
49
+ │ ├── ai-engineering/
50
+ │ ├── backend/ python · nodejs · go · rust · java · dotnet · php
51
+ │ ├── frontend/ react · vue · mobile
52
+ │ ├── data-ml/ pandas · pytorch · mlflow · dbt · spark
53
+ │ ├── devops-infra/ kubernetes · terraform · docker · github-actions · cloud
54
+ │ ├── database/ postgresql · mongodb · redis · graphql
55
+ │ ├── security/ appsec · devsecops · compliance
56
+ │ ├── finance-payments/
57
+ │ └── content-docs/
58
+
59
+ ├── agents/ Specialized subagent definitions
60
+ │ ├── core/ planner · architect · reviewer · security
61
+ │ ├── build-resolvers/ language-specific error resolvers
62
+ │ └── domain/ database · devops · ml specialists
63
+
64
+ ├── hooks/ Event-triggered automations
65
+ │ ├── pre-tool-use/
66
+ │ ├── post-tool-use/
67
+ │ └── lifecycle/
68
+
69
+ ├── rules/ Always-follow guidelines
70
+ │ ├── common/
71
+ │ └── language-specific/
72
+
73
+ ├── workflows/ End-to-end multi-skill workflows
74
+ │ ├── feature-development.md
75
+ │ ├── debugging-session.md
76
+ │ ├── code-review.md
77
+ │ ├── refactor-safely.md
78
+ │ └── new-project-bootstrap.md
79
+
80
+ ├── prompts/ High-value prompt templates
81
+ │ ├── system-prompts/
82
+ │ ├── project-starters/
83
+ │ └── task-specific/
84
+
85
+ ├── mcp/ MCP configs and recommended servers
86
+ └── examples/ Complete working project references
87
+ ```
88
+
89
+ ---
90
+
91
+ ## Quick Start
92
+
93
+ **No installation required.** Clone the repo and copy what you need into your project.
94
+
95
+ ```bash
96
+ git clone https://github.com/Claudient/Claudient.git
97
+ ```
98
+
99
+ **To use a skill** — copy the `.md` file into `.claude/commands/` in your project:
100
+
101
+ ```bash
102
+ cp Claudient/skills/backend/python/fastapi.md your-project/.claude/commands/
103
+ ```
104
+
105
+ Then trigger it in Claude Code with `/fastapi`.
106
+
107
+ **To use an agent** — reference it in your Claude session using the `subagent_type` parameter in your Agent tool calls.
108
+
109
+ **To use a hook** — add the hook JSON to the `hooks` array in your `.claude/settings.json`.
110
+
111
+ **To use a rule** — copy the content into your `CLAUDE.md`.
112
+
113
+ See [guides/getting-started.md](guides/getting-started.md) for a 5-minute setup walkthrough.
114
+
115
+ ---
116
+
117
+ ## Guides
118
+
119
+ | Guide | What it covers |
120
+ |---|---|
121
+ | [Getting Started](guides/getting-started.md) | Setup, first skill, first hook — 5 minutes |
122
+ | [Skill Authoring](guides/skill-authoring.md) | How to write a skill that actually works |
123
+ | [Token Optimization](guides/token-optimization.md) | Model selection, context math, cost reduction |
124
+ | [Memory Management](guides/memory-management.md) | Session persistence, compaction strategies |
125
+ | [Security](guides/security.md) | Isolation, approval boundaries, sanitization |
126
+ | [Agent Orchestration](guides/agent-orchestration.md) | Sub-agent patterns, parallelization |
127
+ | [Hooks Cookbook](guides/hooks-cookbook.md) | Hook patterns with real examples |
128
+
129
+ ---
130
+
131
+ ## Translations
132
+
133
+ All guides and documentation are available in:
134
+
135
+ - [English](guides/) (primary)
136
+ - [Français](guides/fr/)
137
+ - [Deutsch](guides/de/)
138
+ - [Nederlands](guides/nl/)
139
+ - [Español](guides/es/)
140
+
141
+ Skills, agents, and hooks remain in English — they are code-adjacent and translation adds noise without value.
142
+
143
+ ---
144
+
145
+ ## Contributing
146
+
147
+ Claudient grows through community contributions. Every skill, agent, hook, and workflow in this repo was written by someone who solved a real problem.
148
+
149
+ See [CONTRIBUTING.md](CONTRIBUTING.md) for how to add your own — including the skill template, quality checklist, and review process.
150
+
151
+ ---
152
+
153
+ ## Work With Us
154
+
155
+ Claudient is backed by [Uitbreiden](https://uitbreiden.com/) — we build AI products with developer communities and deliver B2B AI solutions.
156
+
157
+ If you're a developer, startup, or enterprise team looking to build with Claude Code at scale, integrate AI into your product, or need a technical partner who lives and breathes this stack — come talk to us.
158
+
159
+ **[uitbreiden.com](https://uitbreiden.com/)**
160
+
161
+ ---
162
+
163
+ ## License
164
+
165
+ MIT — use freely, attribution appreciated.
@@ -0,0 +1,64 @@
1
+ > 🇩🇪 Dies ist die deutsche Übersetzung. [Englische Version](../python-resolver.md).
2
+
3
+ # Python Build Resolver Agent
4
+
5
+ ## Zweck
6
+ Diagnostiziert und behebt Python-Import-Fehler, Laufzeit-Ausnahmen, Type-Annotation-Konflikte (mypy) und Abhängigkeitskonflikte — und gibt korrigierten Code mit einer Erklärung zurück.
7
+
8
+ ## Modellempfehlung
9
+ **Haiku 4.5** für Einzeldatei-Fehler (ImportError, AttributeError, NameError, einfache Type-Annotation-Probleme).
10
+
11
+ **Sonnet 4.6** für Fehler, die mehrere Module umspannen, zirkuläre Imports, mypy-Strict-Mode-Fehler oder Abhängigkeitsversions-Konflikte.
12
+
13
+ ## Tools
14
+ - `Read` — die fehlerhaften Datei und verwandte Module lesen
15
+ - `Edit` — gezielte Korrekturen anwenden
16
+ - `Bash` — `python -m mypy file.py 2>&1`, `python -c "import module"`, `pip show package` zur Diagnose ausführen
17
+
18
+ ## Wann hierher delegieren
19
+ - `ImportError` oder `ModuleNotFoundError` beim Start oder beim Test-Run
20
+ - `mypy`-Typprüfungsfehler in einer streng typisierten Codebase
21
+ - `AttributeError: module 'x' has no attribute 'y'` (API in Paket-Upgrade geändert)
22
+ - Zirkuläre Import-Fehler
23
+ - Abhängigkeitsversions-Konflikte (`pip install` schlägt fehl oder erzeugt inkompatible Versionen)
24
+
25
+ ## Wann NICHT hierher delegieren
26
+ - Logikfehler, die keine Import-/Typfehler sind
27
+ - Performance-Probleme
28
+ - Laufzeitfehler, die durch falsche Geschäftslogik verursacht werden (keine strukturellen Python-Fehler)
29
+
30
+ ## Prompt-Vorlage
31
+ ```
32
+ You are a Python error resolver. Fix the error — minimal changes only. Do not refactor.
33
+
34
+ Error:
35
+ [paste full traceback or mypy output]
36
+
37
+ Relevant files:
38
+ [paste file contents where errors occur]
39
+
40
+ Python version: [e.g., 3.12]
41
+ Package versions: [paste pip freeze output if relevant]
42
+
43
+ For each error:
44
+ 1. Explain why the error occurs in one sentence
45
+ 2. Apply the minimal fix
46
+ 3. If a dependency version conflict: specify the exact version constraint to add/change
47
+
48
+ Do not change logic. Do not refactor. Fix the error only.
49
+ ```
50
+
51
+ ## Beispiel-Anwendungsfall
52
+ **Fehler:**
53
+ ```
54
+ ImportError: cannot import name 'AsyncClient' from 'httpx' (0.23.0)
55
+ ```
56
+
57
+ **Was Resolver zurückgibt:**
58
+ - Ursache: `AsyncClient` wurde in `httpx 0.18.0` hinzugefügt, aber die Verwendung erfordert `httpx>=0.23.0` für die verwendete spezifische API
59
+ - Lösung: `requirements.txt` auf `httpx>=0.23.0,<1.0.0` aktualisieren und `pip install -r requirements.txt` ausführen
60
+ - Falls kein Upgrade möglich: äquivalenten Code für die installierte Version zeigen
61
+
62
+ ---
63
+
64
+ > **Mit uns arbeiten:** Claudient wird von [Uitbreiden](https://uitbreiden.com/) unterstützt — wir bauen KI-Produkte und B2B-Lösungen mit Entwickler-Communities. [uitbreiden.com](https://uitbreiden.com/)
@@ -0,0 +1,65 @@
1
+ > 🇩🇪 Dies ist die deutsche Übersetzung. [Englische Version](../typescript-resolver.md).
2
+
3
+ # TypeScript Build Resolver Agent
4
+
5
+ ## Zweck
6
+ Diagnostiziert und behebt TypeScript-Kompilierungsfehler, Typ-Konflikte und `tsc`-Fehler — und gibt korrigierten Code mit einer Erklärung zurück, was falsch war.
7
+
8
+ ## Modellempfehlung
9
+ **Haiku 4.5** für unkomplizierte Typfehler (fehlende Eigenschaft, falscher Argumenttyp, `any`-Leckage).
10
+
11
+ **Sonnet 4.6** wenn Fehler mehrere Dateien umspannen, generische Typ-Einschränkungen, bedingte Typen oder komplexe Typ-Inferenz-Ketten beinhalten.
12
+
13
+ ## Tools
14
+ - `Read` — die fehlerhafte Datei und relevante Typdefinitionen lesen
15
+ - `Edit` — gezielte Korrekturen anwenden (nur minimale Änderungen)
16
+ - `Bash` — `npx tsc --noEmit 2>&1` ausführen, um Korrektur zu bestätigen, `grep` für verwandte Typdefinitionen
17
+
18
+ ## Wann hierher delegieren
19
+ - `tsc --noEmit` schlägt mit Typfehlern fehl, die diagnostiziert und behoben werden sollen
20
+ - `Type 'X' is not assignable to type 'Y'`-Fehler, die nicht sofort offensichtlich sind
21
+ - Generische Typ-Inferenz-Fehler
22
+ - Drittanbieter-Typdefinitions-Konflikte (z.B. nach einem Paket-Upgrade)
23
+ - Beheben von `any`-Typen, die in die Codebase geleckt sind
24
+
25
+ ## Wann NICHT hierher delegieren
26
+ - Laufzeitfehler, die keine Typfehler sind
27
+ - ESLint-Regelverletzungen (keine TypeScript-Kompilierung)
28
+ - Logikfehler, die die Typprüfung passieren
29
+
30
+ ## Prompt-Vorlage
31
+ ```
32
+ You are a TypeScript error resolver. Fix the type errors — minimal changes only. Do not refactor.
33
+
34
+ Error output from tsc:
35
+ [paste full tsc error output]
36
+
37
+ Relevant files:
38
+ [paste file contents where errors occur]
39
+
40
+ Type definitions context (if relevant):
41
+ [paste relevant .d.ts or interface definitions]
42
+
43
+ For each error:
44
+ 1. Explain why the error occurs in one sentence
45
+ 2. Apply the minimal fix
46
+ 3. Confirm the fix is correct by reasoning through the types
47
+
48
+ Do not change logic. Do not refactor. Fix types only.
49
+ ```
50
+
51
+ ## Beispiel-Anwendungsfall
52
+ **Fehler:**
53
+ ```
54
+ src/api/orders.ts:45:18 - error TS2345:
55
+ Argument of type 'string | undefined' is not assignable to parameter of type 'string'.
56
+ ```
57
+
58
+ **Was Resolver zurückgibt:**
59
+ - Ursache: `req.params.id` ist `string | undefined`, aber `getOrder()` erwartet `string`
60
+ - Lösung: Guard `if (!req.params.id) return res.status(400).json({ error: 'id required' })` vor dem Aufruf hinzufügen — TypeScript schränkt den Typ nach dem Guard ein
61
+ - Minimal: 2-Zeilen-Ergänzung, keine Logikänderung
62
+
63
+ ---
64
+
65
+ > **Mit uns arbeiten:** Claudient wird von [Uitbreiden](https://uitbreiden.com/) unterstützt — wir bauen KI-Produkte und B2B-Lösungen mit Entwickler-Communities. [uitbreiden.com](https://uitbreiden.com/)
@@ -0,0 +1,64 @@
1
+ > 🇪🇸 Esta es la traducción en español. [Versión en inglés](../python-resolver.md).
2
+
3
+ # Agente Resolvedor de Builds Python
4
+
5
+ ## Propósito
6
+ Diagnostica y corrige errores de importación de Python, excepciones en tiempo de ejecución, incompatibilidades de anotaciones de tipos (mypy) y conflictos de dependencias — devolviendo código corregido con una explicación.
7
+
8
+ ## Orientación sobre el modelo
9
+ **Haiku 4.5** para errores de un solo archivo (ImportError, AttributeError, NameError, problemas simples de anotaciones de tipos).
10
+
11
+ **Sonnet 4.6** para errores que abarcan múltiples módulos, importaciones circulares, fallos en modo estricto de mypy o conflictos de versión de dependencias.
12
+
13
+ ## Herramientas
14
+ - `Read` — leer el archivo fallido y los módulos relacionados
15
+ - `Edit` — aplicar correcciones específicas
16
+ - `Bash` — ejecutar `python -m mypy file.py 2>&1`, `python -c "import module"`, `pip show package` para diagnosticar
17
+
18
+ ## Cuándo delegar aquí
19
+ - `ImportError` o `ModuleNotFoundError` al inicio o en la ejecución de pruebas
20
+ - Fallos de verificación de tipos `mypy` en un codebase estrictamente tipado
21
+ - `AttributeError: module 'x' has no attribute 'y'` (API cambió al actualizar un paquete)
22
+ - Errores de importación circular
23
+ - Conflictos de versión de dependencias (`pip install` falla o produce versiones incompatibles)
24
+
25
+ ## Cuándo NO delegar aquí
26
+ - Bugs lógicos que no son errores de importación/tipo
27
+ - Problemas de rendimiento
28
+ - Errores en tiempo de ejecución causados por lógica de negocio incorrecta (no errores estructurales de Python)
29
+
30
+ ## Plantilla de prompt
31
+ ```
32
+ You are a Python error resolver. Fix the error — minimal changes only. Do not refactor.
33
+
34
+ Error:
35
+ [paste full traceback or mypy output]
36
+
37
+ Relevant files:
38
+ [paste file contents where errors occur]
39
+
40
+ Python version: [e.g., 3.12]
41
+ Package versions: [paste pip freeze output if relevant]
42
+
43
+ For each error:
44
+ 1. Explain why the error occurs in one sentence
45
+ 2. Apply the minimal fix
46
+ 3. If a dependency version conflict: specify the exact version constraint to add/change
47
+
48
+ Do not change logic. Do not refactor. Fix the error only.
49
+ ```
50
+
51
+ ## Caso de uso de ejemplo
52
+ **Error:**
53
+ ```
54
+ ImportError: cannot import name 'AsyncClient' from 'httpx' (0.23.0)
55
+ ```
56
+
57
+ **Lo que devuelve el Resolvedor:**
58
+ - Causa: `AsyncClient` fue agregado en `httpx 0.18.0` pero el uso requiere `httpx>=0.23.0` para la API específica usada
59
+ - Corrección: actualizar `requirements.txt` a `httpx>=0.23.0,<1.0.0` y ejecutar `pip install -r requirements.txt`
60
+ - Si no se puede actualizar: mostrar el código equivalente para la versión instalada
61
+
62
+ ---
63
+
64
+ > **Trabaja con nosotros:** Claudient está respaldado por [Uitbreiden](https://uitbreiden.com/) — construimos productos de IA y soluciones B2B con comunidades de desarrolladores. [uitbreiden.com](https://uitbreiden.com/)
@@ -0,0 +1,65 @@
1
+ > 🇪🇸 Esta es la traducción en español. [Versión en inglés](../typescript-resolver.md).
2
+
3
+ # Agente Resolvedor de Builds TypeScript
4
+
5
+ ## Propósito
6
+ Diagnostica y corrige errores de compilación de TypeScript, incompatibilidades de tipos y fallos de `tsc` — devolviendo código corregido con una explicación de lo que estaba mal.
7
+
8
+ ## Orientación sobre el modelo
9
+ **Haiku 4.5** para errores de tipos simples (propiedad faltante, tipo de argumento incorrecto, `any` que se filtra).
10
+
11
+ **Sonnet 4.6** cuando los errores abarcan múltiples archivos, involucran restricciones de tipos genéricos, tipos condicionales o cadenas complejas de inferencia de tipos.
12
+
13
+ ## Herramientas
14
+ - `Read` — leer el archivo fallido y las definiciones de tipos relevantes
15
+ - `Edit` — aplicar correcciones específicas (solo cambios mínimos)
16
+ - `Bash` — ejecutar `npx tsc --noEmit 2>&1` para confirmar la corrección, `grep` para definiciones de tipos relacionadas
17
+
18
+ ## Cuándo delegar aquí
19
+ - `tsc --noEmit` falla con errores de tipos que quieres diagnosticar y corregir
20
+ - Errores `Type 'X' is not assignable to type 'Y'` que no son inmediatamente obvios
21
+ - Fallos de inferencia de tipos genéricos
22
+ - Incompatibilidades de definiciones de tipos de terceros (p.ej., tras actualizar un paquete)
23
+ - Corrección de tipos `any` que se han filtrado al codebase
24
+
25
+ ## Cuándo NO delegar aquí
26
+ - Errores en tiempo de ejecución que no son errores de tipos
27
+ - Violaciones de reglas de ESLint (no compilación de TypeScript)
28
+ - Bugs lógicos que pasan la verificación de tipos
29
+
30
+ ## Plantilla de prompt
31
+ ```
32
+ You are a TypeScript error resolver. Fix the type errors — minimal changes only. Do not refactor.
33
+
34
+ Error output from tsc:
35
+ [paste full tsc error output]
36
+
37
+ Relevant files:
38
+ [paste file contents where errors occur]
39
+
40
+ Type definitions context (if relevant):
41
+ [paste relevant .d.ts or interface definitions]
42
+
43
+ For each error:
44
+ 1. Explain why the error occurs in one sentence
45
+ 2. Apply the minimal fix
46
+ 3. Confirm the fix is correct by reasoning through the types
47
+
48
+ Do not change logic. Do not refactor. Fix types only.
49
+ ```
50
+
51
+ ## Caso de uso de ejemplo
52
+ **Error:**
53
+ ```
54
+ src/api/orders.ts:45:18 - error TS2345:
55
+ Argument of type 'string | undefined' is not assignable to parameter of type 'string'.
56
+ ```
57
+
58
+ **Lo que devuelve el Resolvedor:**
59
+ - Causa: `req.params.id` es `string | undefined` pero `getOrder()` espera `string`
60
+ - Corrección: agregar una guarda `if (!req.params.id) return res.status(400).json({ error: 'id required' })` antes de la llamada — TypeScript reduce el tipo después de la guarda
61
+ - Mínimo: adición de 2 líneas, sin cambio de lógica
62
+
63
+ ---
64
+
65
+ > **Trabaja con nosotros:** Claudient está respaldado por [Uitbreiden](https://uitbreiden.com/) — construimos productos de IA y soluciones B2B con comunidades de desarrolladores. [uitbreiden.com](https://uitbreiden.com/)
@@ -0,0 +1,64 @@
1
+ > 🇫🇷 This is the French translation. [English version](../python-resolver.md).
2
+
3
+ # Agent Résolveur de Build Python
4
+
5
+ ## Objectif
6
+ Diagnostique et corrige les erreurs d'import Python, les exceptions runtime, les incompatibilités d'annotations de type (mypy) et les conflits de dépendances — en retournant le code corrigé avec une explication.
7
+
8
+ ## Conseil sur le modèle
9
+ **Haiku 4.5** pour les erreurs dans un seul fichier (ImportError, AttributeError, NameError, problèmes simples d'annotations de type).
10
+
11
+ **Sonnet 4.6** pour les erreurs couvrant plusieurs modules, les imports circulaires, les échecs mypy en mode strict, ou les conflits de versions de dépendances.
12
+
13
+ ## Outils
14
+ - `Read` — lire le fichier en échec et les modules liés
15
+ - `Edit` — appliquer des corrections ciblées
16
+ - `Bash` — exécuter `python -m mypy file.py 2>&1`, `python -c "import module"`, `pip show package` pour diagnostiquer
17
+
18
+ ## Quand déléguer ici
19
+ - `ImportError` ou `ModuleNotFoundError` au démarrage ou à l'exécution des tests
20
+ - Échecs de vérification de type `mypy` dans une base de code strictement typée
21
+ - `AttributeError: module 'x' has no attribute 'y'` (API changée lors d'une mise à niveau de package)
22
+ - Erreurs d'import circulaire
23
+ - Conflits de versions de dépendances (`pip install` échoue ou produit des versions incompatibles)
24
+
25
+ ## Quand NE PAS déléguer ici
26
+ - Bugs de logique qui ne sont pas des erreurs d'import/type
27
+ - Problèmes de performance
28
+ - Erreurs runtime causées par une logique métier incorrecte (pas des erreurs Python structurelles)
29
+
30
+ ## Template de prompt
31
+ ```
32
+ You are a Python error resolver. Fix the error — minimal changes only. Do not refactor.
33
+
34
+ Error:
35
+ [paste full traceback or mypy output]
36
+
37
+ Relevant files:
38
+ [paste file contents where errors occur]
39
+
40
+ Python version: [e.g., 3.12]
41
+ Package versions: [paste pip freeze output if relevant]
42
+
43
+ For each error:
44
+ 1. Explain why the error occurs in one sentence
45
+ 2. Apply the minimal fix
46
+ 3. If a dependency version conflict: specify the exact version constraint to add/change
47
+
48
+ Do not change logic. Do not refactor. Fix the error only.
49
+ ```
50
+
51
+ ## Exemple de cas d'utilisation
52
+ **Erreur :**
53
+ ```
54
+ ImportError: cannot import name 'AsyncClient' from 'httpx' (0.23.0)
55
+ ```
56
+
57
+ **Ce que retourne le Résolveur :**
58
+ - Cause : `AsyncClient` a été ajouté dans `httpx 0.18.0` mais l'utilisation nécessite `httpx>=0.23.0` pour l'API spécifique utilisée
59
+ - Correction : mettre à jour `requirements.txt` vers `httpx>=0.23.0,<1.0.0` et exécuter `pip install -r requirements.txt`
60
+ - Si impossible de mettre à niveau : montrer le code équivalent pour la version installée
61
+
62
+ ---
63
+
64
+ > **Travaillez avec nous :** Claudient est soutenu par [Uitbreiden](https://uitbreiden.com/) — nous construisons des produits IA et des solutions B2B avec des communautés de développeurs. [uitbreiden.com](https://uitbreiden.com/)
@@ -0,0 +1,65 @@
1
+ > 🇫🇷 This is the French translation. [English version](../typescript-resolver.md).
2
+
3
+ # Agent Résolveur de Build TypeScript
4
+
5
+ ## Objectif
6
+ Diagnostique et corrige les erreurs de compilation TypeScript, les incompatibilités de types et les échecs `tsc` — en retournant le code corrigé avec une explication de ce qui était incorrect.
7
+
8
+ ## Conseil sur le modèle
9
+ **Haiku 4.5** pour les erreurs de type simples (propriété manquante, mauvais type d'argument, fuite de `any`).
10
+
11
+ **Sonnet 4.6** quand les erreurs couvrent plusieurs fichiers, impliquent des contraintes de types génériques, des types conditionnels, ou des chaînes d'inférence de type complexes.
12
+
13
+ ## Outils
14
+ - `Read` — lire le fichier en échec et les définitions de type pertinentes
15
+ - `Edit` — appliquer des corrections ciblées (changements minimaux uniquement)
16
+ - `Bash` — exécuter `npx tsc --noEmit 2>&1` pour confirmer la correction, `grep` pour les définitions de type liées
17
+
18
+ ## Quand déléguer ici
19
+ - `tsc --noEmit` échoue avec des erreurs de type que vous voulez diagnostiquer et corriger
20
+ - Erreurs `Type 'X' is not assignable to type 'Y'` qui ne sont pas immédiatement évidentes
21
+ - Échecs d'inférence de type générique
22
+ - Incompatibilités de définitions de type tierces (ex: après mise à niveau d'un package)
23
+ - Correction de types `any` qui ont fui dans la base de code
24
+
25
+ ## Quand NE PAS déléguer ici
26
+ - Erreurs runtime qui ne sont pas des erreurs de type
27
+ - Violations de règles ESLint (pas de compilation TypeScript)
28
+ - Bugs de logique qui passent la vérification de type
29
+
30
+ ## Template de prompt
31
+ ```
32
+ You are a TypeScript error resolver. Fix the type errors — minimal changes only. Do not refactor.
33
+
34
+ Error output from tsc:
35
+ [paste full tsc error output]
36
+
37
+ Relevant files:
38
+ [paste file contents where errors occur]
39
+
40
+ Type definitions context (if relevant):
41
+ [paste relevant .d.ts or interface definitions]
42
+
43
+ For each error:
44
+ 1. Explain why the error occurs in one sentence
45
+ 2. Apply the minimal fix
46
+ 3. Confirm the fix is correct by reasoning through the types
47
+
48
+ Do not change logic. Do not refactor. Fix types only.
49
+ ```
50
+
51
+ ## Exemple de cas d'utilisation
52
+ **Erreur :**
53
+ ```
54
+ src/api/orders.ts:45:18 - error TS2345:
55
+ Argument of type 'string | undefined' is not assignable to parameter of type 'string'.
56
+ ```
57
+
58
+ **Ce que retourne le Résolveur :**
59
+ - Cause : `req.params.id` est `string | undefined` mais `getOrder()` attend `string`
60
+ - Correction : ajouter une garde `if (!req.params.id) return res.status(400).json({ error: 'id required' })` avant l'appel — TypeScript restreint le type après la garde
61
+ - Minimal : ajout de 2 lignes, pas de changement de logique
62
+
63
+ ---
64
+
65
+ > **Travaillez avec nous :** Claudient est soutenu par [Uitbreiden](https://uitbreiden.com/) — nous construisons des produits IA et des solutions B2B avec des communautés de développeurs. [uitbreiden.com](https://uitbreiden.com/)