This repository was archived by the owner on Sep 30, 2026. It is now read-only.
Repository navigation
feat: rewrite plugin as skill-based architecture for v2.0.0 - #22
Merged
Merged
Conversation
Replace the command/agent-driven MCP workflow (setup, sync, search, test, mock, docs, security, learn, flows commands + readiness-analyzer agent) with a consolidated set of task-oriented skills (bootstrap, api-discovery, api-mocking, api-monitoring, api-testing, ci-integration, collection-schema-v3, performance-testing, postman-mcp-fallback), and bump plugin.json to 2.0.0. Syncs .mcp.json X-Plugin-Version/User-Agent headers to 2.0.0 per the plugin's versioning convention. Co-Authored-By: Claude <noreply@anthropic.com>
…wn lint The v2.0.0 skill-based rewrite removes commands/ and agents/ entirely, but validate-structure.py and validate-frontmatter.py still hard-required both directories to exist. Make them optional (validated only if present) so a skill-only plugin passes. Also fixes two real markdownlint violations in the new skill files: missing blank lines around tables in api-discovery/reference/search_filters.md (MD058), and multiple top-level headings in bootstrap/SKILL.md (MD025). Co-Authored-By: Claude <noreply@anthropic.com>
garciasdos
previously approved these changes
Sep 18, 2026
vedkribhu
changed the title
Adopt postman-plugin as source of truth for skill content: add the ai-readiness and api-flows skills, replace postman-mcp-fallback with postman-mcp-server's guidance-oriented rewrite (plus its references/), and pull in the diverged bootstrap, ci-integration, and api-discovery reference content. Co-Authored-By: Claude <noreply@anthropic.com>
Matches the naming used for other single-concern skills; update the bootstrap cross-reference to match. Co-Authored-By: Claude <noreply@anthropic.com>
Collapse extra blank lines in ai-readiness, add blank lines around tables in api-discovery's search_filters reference, and demote two stray H1s in bootstrap back to H2 so there's a single top-level heading per file. Co-Authored-By: Claude <noreply@anthropic.com>
garciasdos
approved these changes
Sep 18, 2026
3 of 4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
.claude-plugin/plugin.jsonto2.0.0and syncs.mcp.json'sX-Plugin-Version/User-Agentheaders to match (per this repo's versioning convention).Known gaps (not addressed in this PR)
.github/scripts/validate-structure.pystill hard-requirescommands/andagents/directories to exist — both are fully removed by this rewrite, so CI's Structure Integrity check will fail until that script is updated for the new skill-only architecture.README.md,CHANGELOG.md, andCLAUDE.mdstill document the removed v1 commands/skills and have not been updated here — left for a follow-up since reconciling them is a judgment call on how the new architecture should be presented, not part of the source patch.Test plan
validate-structure.py(or the workflow) to stop requiringcommands//agents/before merging, or confirm CI is expected to fail/be updated separatelyclaude --plugin-dir .) and confirm the 9 new skills route correctly for representative prompts (bootstrap, mocking, monitoring, testing, discovery, CI, performance)Generated with Claude Code