@cyanheads/mcp-ts-core 0.5.0 → 0.5.3

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 (30) hide show
  1. package/CLAUDE.md +3 -5
  2. package/README.md +2 -2
  3. package/dist/cli/init.js +8 -1
  4. package/dist/cli/init.js.map +1 -1
  5. package/dist/linter/rules/format-parity-rules.d.ts +37 -0
  6. package/dist/linter/rules/format-parity-rules.d.ts.map +1 -0
  7. package/dist/linter/rules/format-parity-rules.js +341 -0
  8. package/dist/linter/rules/format-parity-rules.js.map +1 -0
  9. package/dist/linter/rules/tool-rules.d.ts.map +1 -1
  10. package/dist/linter/rules/tool-rules.js +5 -0
  11. package/dist/linter/rules/tool-rules.js.map +1 -1
  12. package/dist/mcp-server/tools/utils/toolDefinition.d.ts +10 -9
  13. package/dist/mcp-server/tools/utils/toolDefinition.d.ts.map +1 -1
  14. package/dist/mcp-server/tools/utils/toolDefinition.js +2 -2
  15. package/dist/mcp-server/tools/utils/toolDefinition.js.map +1 -1
  16. package/package.json +3 -2
  17. package/scripts/check-docs-sync.ts +85 -0
  18. package/scripts/devcheck.ts +8 -0
  19. package/skills/add-tool/SKILL.md +6 -5
  20. package/skills/api-config/SKILL.md +1 -1
  21. package/skills/design-mcp-server/SKILL.md +3 -3
  22. package/skills/field-test/SKILL.md +2 -2
  23. package/skills/polish-docs-meta/SKILL.md +2 -2
  24. package/skills/polish-docs-meta/references/readme.md +217 -79
  25. package/skills/setup/SKILL.md +1 -1
  26. package/templates/AGENTS.md +5 -3
  27. package/templates/CLAUDE.md +5 -3
  28. package/templates/src/mcp-server/tools/definitions/echo.tool.ts +3 -2
  29. package/skills/devcheck/SKILL.md +0 -54
  30. package/skills/walkthrough-init/SKILL.md +0 -50
package/skills/walkthrough-init/SKILL.md DELETED
@@ -1,50 +0,0 @@
1
- ---
2
- name: walkthrough-init
3
- description: >
4
- Trace the agent onboarding flow after `init` scaffolds a new project. Starts from the agent reading CLAUDE.md for the first time and follows every instruction chain through skills and framework docs. Use to audit the onboarding path, find dead ends, or catch missing instructions.
5
- metadata:
6
- author: cyanheads
7
- version: "1.0"
8
- audience: internal
9
- type: debug
10
- ---
11
-
12
- ## What this skill does
13
-
14
- A developer has run `npx @cyanheads/mcp-ts-core init banking-mcp-server` and `bun install`. They open the project and run `claude`. You are that agent, seeing this project for the first time.
15
-
16
- Trace the onboarding path through the actual files as they exist right now. Follow every instruction chain — read what you're told to read, do what you're told to do, and report what happens.
17
-
18
- ---
19
-
20
- ## Instructions
21
-
22
- ### Step 1: Read the project's CLAUDE.md
23
-
24
- This is the first file the agent sees. Read `CLAUDE.md` at the project root. Report:
25
-
26
- - What does it tell you to do first?
27
- - What files does it point you to?
28
- - Does it mention the `setup` skill? How?
29
-
30
- ### Step 2: Follow the first instruction
31
-
32
- Whatever CLAUDE.md says to do first — do it. If it says to read a file, read it. If it says to run a skill, read that skill's SKILL.md. Report what you find and what it tells you to do next.
33
-
34
- ### Step 3: Keep following the chain
35
-
36
- Continue following instructions until you've completed the full onboarding loop. At each step:
37
-
38
- - What file are you reading?
39
- - What does it tell you to do?
40
- - Can you actually do it? (Do the referenced files/paths exist?)
41
- - What's the next step it points you to?
42
-
43
- ### Step 4: Report
44
-
45
- After the chain ends (or breaks), produce:
46
-
47
- 1. **The path you followed** — ordered list of files read and actions taken
48
- 2. **Broken links** — instructions that point to files that don't exist, skills that aren't written, or actions that can't be completed
49
- 3. **Dead ends** — places where the instructions stop and you don't know what to do next
50
- 4. **The complete onboarding flow** — a summary of what a new agent actually experiences, step by step