agentrigs
+ submit rig
~ / rigs / yha9806 / academic-writing-toolkit

yha9806/academic-writing-toolkit

Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

↗ GitHub ★ 43 MIT updated today project Claude CodeCodexCursorGemini CLI
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~2.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit yha9806/academic-writing-toolkit/.claude ./rig-academic-writing-toolkit  # inspect, then merge into .claude/

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.

$ npx degit yha9806/academic-writing-toolkit/.claude/skills/audit .claude/skills/audit
$ npx degit yha9806/academic-writing-toolkit/.claude/skills/export .claude/skills/export
$ npx degit yha9806/academic-writing-toolkit/.claude/skills/integrate .claude/skills/integrate
$ npx degit yha9806/academic-writing-toolkit/.claude/skills/map .claude/skills/map
$ npx degit yha9806/academic-writing-toolkit/.claude/skills/note .claude/skills/note
$ npx degit yha9806/academic-writing-toolkit/.claude/skills/read .claude/skills/read
$ npx degit yha9806/academic-writing-toolkit/.claude/skills/readers .claude/skills/readers
$ npx degit yha9806/academic-writing-toolkit/.claude/skills/review .claude/skills/review
$ npx degit yha9806/academic-writing-toolkit/.claude/skills/verify-refs .claude/skills/verify-refs
$ npx degit yha9806/academic-writing-toolkit/archive/skills/argument-governance .claude/skills/argument-governance
$ npx degit yha9806/academic-writing-toolkit/archive/skills/evidence-review .claude/skills/evidence-review
$ npx degit yha9806/academic-writing-toolkit/archive/skills/human-eval-handoff-repair .claude/skills/human-eval-handoff-repair
$ npx degit yha9806/academic-writing-toolkit/archive/skills/logic-review .claude/skills/logic-review
$ npx degit yha9806/academic-writing-toolkit/archive/skills/manuscript-reframe .claude/skills/manuscript-reframe
$ npx degit yha9806/academic-writing-toolkit/archive/skills/peer-review .claude/skills/peer-review
$ npx degit yha9806/academic-writing-toolkit/archive/skills/progress .claude/skills/progress
$ npx degit yha9806/academic-writing-toolkit/archive/skills/release-governance .claude/skills/release-governance
$ npx degit yha9806/academic-writing-toolkit/archive/skills/revision-escalation .claude/skills/revision-escalation
$ npx degit yha9806/academic-writing-toolkit/archive/skills/self-review .claude/skills/self-review
$ npx degit yha9806/academic-writing-toolkit/archive/skills/style .claude/skills/style
$ npx degit yha9806/academic-writing-toolkit/archive/skills/thesis-control .claude/skills/thesis-control
$ npx degit yha9806/academic-writing-toolkit/archive/skills/verify .claude/skills/verify

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (22)

auditexportintegratemapnotereadreadersreviewverify-refsargument-governanceevidence-reviewhuman-eval-handoff-repairlogic-reviewmanuscript-reframepeer-reviewprogressrelease-governancerevision-escalationself-reviewstylethesis-controlverify

Cursor rules (1)

academic-writing · always

Similar rigs

songjiao/claude_dotfiles
—
★ 0 setup Claude Code 5 skills 9mo ago
Pragmatist 837 tok ·
mag123c/toktrack
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
★ 194 project Claude CodeCodex 6 skills 5 hooks 8d ago
Automator 499 tok ·
ccch1mneyyy/dsh-TUI
DSH's officially recommended TUI plugin — high performance, low overhead, cute pixel whale, smooth mouse interaction. One-command install via npm. / DSH 官方推荐的 TUI 插件, 高性能低占用, 可爱像素鲸鱼, 流畅鼠标交互, npm一键安装
★ 3,939 project Claude CodeCodex 8 skills 7d ago
Pragmatist 1.9k tok ·
andreacanes/Claude-work-flow-optimizer
Claude Work Flow Optimizer — Audit and maintain Claude Code config against best practices
★ 1 project Claude Code 6 skills 4 agents 6mo ago
Pragmatist 1.0k tok ·
copied ✓