tusharsrivastava/shark-skills
Running Claude Code like an engineering team: one operator, parallel lanes, audited merges.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ claude mcp add mcp-debugger -- npx -y @debugmcp/mcp-debugger@0.24.2 stdio --log-file .claude/mcp-debugger.log $ npx degit tusharsrivastava/shark-skills/skills ./rig-shark-skills/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add mcp-debugger -- npx -y @debugmcp/mcp-debugger@0.24.2 stdio --log-file .claude/mcp-debugger.log $ npx degit tusharsrivastava/shark-skills/skills/commit-blocks .claude/skills/commit-blocks $ npx degit tusharsrivastava/shark-skills/skills/cookbook-writing .claude/skills/cookbook-writing $ npx degit tusharsrivastava/shark-skills/skills/debug-rca .claude/skills/debug-rca $ npx degit tusharsrivastava/shark-skills/skills/gitignore .claude/skills/gitignore $ npx degit tusharsrivastava/shark-skills/skills/goal-loop .claude/skills/goal-loop $ npx degit tusharsrivastava/shark-skills/skills/handoff .claude/skills/handoff $ npx degit tusharsrivastava/shark-skills/skills/init .claude/skills/init $ npx degit tusharsrivastava/shark-skills/skills/lead-merge .claude/skills/lead-merge $ npx degit tusharsrivastava/shark-skills/skills/merge-audit .claude/skills/merge-audit $ npx degit tusharsrivastava/shark-skills/skills/operator .claude/skills/operator $ npx degit tusharsrivastava/shark-skills/skills/patch-fanout .claude/skills/patch-fanout $ npx degit tusharsrivastava/shark-skills/skills/port-audit .claude/skills/port-audit $ npx degit tusharsrivastava/shark-skills/skills/system-design .claude/skills/system-design
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| @debugmcp/mcp-debugger · "mcp-debugger" | npm | 2.5k |
Skills (13)
Similar rigs
AshwinSathian/workdeck
Run a project as cards: one card per Claude Code session, with a scope gate, a separate review and one pull request.
Pragmatist 296 tok · · Q0
PhilippKlinger/buildorder
A Claude Code plugin that sets up a workspace and engineering standards for your project.
Skill Collector 989 tok · · Q0
tammai/rspec
Claude Code plugin: reverse-spec an existing product into features, user stories and technical specs, ready to rebuild it for learning or personal use.
Skill Collector 124 tok · · Q15
erayozenn/BigHead-2ndBrain
A personal second brain for Claude Code + Obsidian, built on Karpathy's LLM Wiki pattern: immutable sources, an LLM-maintained cited wiki, guard and schema hooks, study mode.
Skill Collector 2.2k tok · · Q3