github
starsforks
How to install github?
avalonreset/legends-github/github
$npx -y skills add avalonreset/legends-github --skill githubGitHub repository optimization suite. Orchestrates sub-skills to audit and professionalize repos across README, legal, metadata, SEO, community, and releases.
SKILL.md
| 1 | # GitHub -- Repository Optimization Suite |
| 2 | |
| 3 | Comprehensive GitHub optimization across SEO, legal, community, and discoverability. |
| 4 | Orchestrates 8 specialized sub-skills and 6 scoring workers: Claude Code |
| 5 | subagents or Codex multi-agents. Data-first: every recommendation |
| 6 | traces back to a data source. |
| 7 | |
| 8 | ## Quick Reference |
| 9 | |
| 10 | | Entry point | What it does | |
| 11 | |---------|-------------| |
| 12 | | `github-audit` | Full repo health audit with 0-100 scoring | |
| 13 | | `github-audit` with remote target | Audit a specific remote repo | |
| 14 | | `github-empire` or portfolio audit flow | Audit an entire portfolio | |
| 15 | | `github-readme` | Generate or optimize README | |
| 16 | | `github-legal` | License, SECURITY.md, CITATION.cff, fork compliance | |
| 17 | | `github-meta` | Description, topics, settings, social preview | |
| 18 | | `github-seo` | Keyword research and content optimization strategy | |
| 19 | | `github-community` | Templates, CONTRIBUTING, CODE_OF_CONDUCT, devcontainer | |
| 20 | | `github-release` | CHANGELOG, badges, versioning, release strategy | |
| 21 | | `github-empire` | Multi-repo portfolio strategy, profile README | |
| 22 | | `extensions/dataforseo` | Live keyword/SERP data (requires DataForSEO account) | |
| 23 | |
| 24 | ## Prerequisites |
| 25 | |
| 26 | Before any skill can operate, check these in order: |
| 27 | |
| 28 | 1. **Git installed?** Run `git --version`. If missing, guide user to install. |
| 29 | 2. **GitHub CLI installed?** Run `gh --version`. If missing: `winget install GitHub.cli` (Windows) or `brew install gh` (macOS). |
| 30 | 3. **Authenticated?** Run `gh auth status`. If not logged in, guide through `gh auth login`. |
| 31 | 4. **In a git repo?** Run `git rev-parse --is-inside-work-tree`. If not, ask if they want to create one or point to an existing repo. |
| 32 | |
| 33 | If a user has no GitHub account, direct them to https://github.com/signup and wait for them to complete signup before proceeding with `gh auth login`. |
| 34 | |
| 35 | ### API Credentials |
| 36 | |
| 37 | Two recommended services power SEO research and banner generation. The install |
| 38 | script walks users through setting both up during installation. If they skipped |
| 39 | setup, Step 0 below will catch it and guide them before any skill runs. |
| 40 | |
| 41 | **1. DataForSEO (MCP server -- NOT .env)** |
| 42 | DataForSEO provides live keyword and SERP data. It runs as an MCP server |
| 43 | The install script handles this automatically. When configured, tools like |
| 44 | `dataforseo_labs_google_keyword_suggestions` are available directly in conversation. |
| 45 | If the MCP server is not configured, SEO skills fall back to codebase analysis. |
| 46 | |
| 47 | **2. KIE.ai (REST API -- uses .env)** |
| 48 | KIE.ai generates banner images for READMEs. It requires an API key in a `.env` file. |
| 49 | |
| 50 | **Standard dotenv locations:** Check these paths in order: |
| 51 | 1. Current working directory: `./.env.local`, then `./.env` |
| 52 | 2. Skill root: `github/.env.local`, then `github/.env` |
| 53 | 3. User home: `~/.env.local`, then `~/.env` |
| 54 | |
| 55 | **Loading credentials:** Before banner generation, load the .env: |
| 56 | ```bash |
| 57 | for envfile in ./.env.local ./.env github/.env.local github/.env ~/.env.local ~/.env; do |
| 58 | if [ -f "$envfile" ]; then |
| 59 | export $(grep -v '^#' "$envfile" | xargs) 2>/dev/null |
| 60 | break |
| 61 | fi |
| 62 | done |
| 63 | ``` |
| 64 | |
| 65 | | Key | Required By | Purpose | |
| 66 | |-----|------------|---------| |
| 67 | | `KIE_API_KEY` | `github-readme` banner generation | KIE.ai image generation | |
| 68 | | DataForSEO credentials | SEO data pass across `github-seo`, `github-meta`, `github-readme`, `github-empire` | Configured via MCP server, not .env | |
| 69 | |
| 70 | ## Shared Data Cache |
| 71 | |
| 72 | Skills persist their outputs to `.github-audit/` so other skills can reuse data |
| 73 | without re-gathering. The orchestrator writes `repo-context.json` after baseline |
| 74 | gathering. Each sub-skill reads cached data before gathering and writes its own |
| 75 | cache file after executing. |
| 76 | |
| 77 | Reference: Read `github/references/shared-data-cache.md` for |
| 78 | JSON schemas, dependency map, and freshness rules. |
| 79 | |
| 80 | **Orchestrator responsibilities:** Cache writes are embedded directly in Step 2 |
| 81 | and Step 3.5 below -- look for the **CACHE:** callouts in each step. |
| 82 | |
| 83 | ## Headless Contract |
| 84 | |
| 85 | For API agents and non-interactive runners, use the deterministic script entrypoint: |
| 86 | |
| 87 | ```bash |
| 88 | python3 scripts/run_headless.py verify --mode both --path /path/to/repo |
| 89 | python3 scripts/run_headless.py audit --path /path/to/repo |
| 90 | python3 scripts/run_headless.py seo --path /path/to/repo |
| 91 | python3 scripts/run_headless.py legal --path /path/to/repo |
| 92 | python3 scripts/run_headless.py legal --path /path/to/repo --write-files |
| 93 | python3 scripts/run_headless.py meta --path /path/to/repo |
| 94 | python3 scripts/run_headless.py community --path /path/to/repo |
| 95 | python3 scripts/run_headless.py community --path /path/to/repo --write-files |
| 96 | python3 scripts/run_headless.py readme --path /path/to/repo |
| 97 | python3 scripts/run_headless.py readme --path /path/to/repo --generate-assets |
| 98 | python3 scripts/run_headless.py release --path /path/to/repo |
| 99 | python3 scripts/run_headless.py release --path /path/to/repo --write-files |
| 100 | python3 scripts/run_he |
People who liked this also viewed
6 picksType
- caveman-commitUltra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. UsSkillsJul 2026
- git-guardrails-claude-codeSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- setup-pre-commitSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- resolving-merge-conflictsSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- using-git-worktreesUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackSkillsJul 2026
- finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanupSkillsJul 2026
