feat: ecosystem discovery and skill recommender#11
Open
itsdevcoffee wants to merge 10 commits intomainfrom
Open
feat: ecosystem discovery and skill recommender#11itsdevcoffee wants to merge 10 commits intomainfrom
itsdevcoffee wants to merge 10 commits intomainfrom
Conversation
Implements a comprehensive ecosystem tracking and discovery system for Claude Code extensions including plugins, skills, agents, MCP servers, and marketplaces. ## Components **Ecosystem Data (ecosystem/):** - plugins.json - Plugin registry and metadata - skills.json - Skills catalog - agents.json - Agent definitions - mcp-servers.json - MCP server registry - marketplaces.json - Marketplace tracking - skills-leaderboard.json - Skills ranking and popularity - metadata.json - Ecosystem metadata and stats **Discovery Scripts (scripts/ecosystem/):** - detect_stack.py - Stack detection for tech recommendations - recommend.py - Recommendation engine for plugins/skills **Research Documentation:** - Claude Code ecosystem discovery research - Skills ecosystem analysis **Handoff Documentation:** - Unified facets handoff (for project continuity) ## Purpose Enables discovery, tracking, and recommendation of Claude Code extensions to help users find relevant tools for their projects and workflows.
Add Claude Code skill that invokes the ecosystem recommender scripts to suggest relevant tools based on detected tech stack. Also add __pycache__/ to gitignore for Python script artifacts.
Covers scoring engine extraction, ecosystem data enrichment, deduplication, new CLI flags, and SKILL.md updates.
9 tasks covering scorer engine, recommend.py refactor, ecosystem JSON tag enrichment, SKILL.md updates, and end-to-end verification.
Add language, framework, and domain tags across all 5 ecosystem JSON files to improve recommendation accuracy. Includes Go, Python, CLI, TUI, development, and other tags where factually supported.
…ests Replace substring-based keyword matching with compiled regex patterns using \b word boundaries. This prevents false positives like "go" being inferred from "Django" or "cargo". Also removes the broken --json flag (was a no-op due to action=store_true with default=True) and adds 30 unit tests covering tag inference, scoring, popularity normalization, deduplication, and the hard gate.
Addresses superpowers code review findings: - Raise DEFAULT_MIN_SCORE from 20 to 35, eliminating single-tag false positives in skills_leaderboard (supabase-postgres matching only on "backend", pdf/docx/pptx/xlsx matching only on "python") - Remove unused TAG_MATCH_WEIGHT constant (dead code) - Remove 3 duplicate entries in skills.json that had owner/name format in the name field (BehiSecc, ComposioHQ, travisvn) - Update SKILL.md to reflect new default threshold
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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
ecosystem/) with 5 JSON files covering 140+ skills, plugins, agents, and MCP servers — with stars, install commands, and curated tagsskill-recommender) so users can run "recommend skills" or "what plugins should I use" from any projectScoring Engine
CLI
Files Added (19 files, ~4500 lines)
ecosystem/— 5 JSON reference maps + README + research docsscripts/ecosystem/— detect_stack.py, scorer.py, recommend.py, test_scorer.py.claude/skills/skill-recommender/SKILL.mddocs/plans/Test plan
python3 -m unittest scripts/ecosystem/test_scorer -v)--markdown,--pretty,--exclude-no-installflags verified