c31-loop
Skill1 starsChanged 3 months agoMITView on GitHub
将 C31 接入 Loop Engineering 调度层,使其从"人工触发的 Harness"升级为"自主定时运行的 Loop System"。 通过 5 问访谈收集配置意图,自动生成 STATE.md、CONSTRAINTS.md、loop-budget.md, 以及平台专属部署文件(GitHub Actions workflow 或 Windows Task Scheduler 脚本)。 访谈结束后一键激活——C31 开始定时自主执行任务,无需人工干预。
- Reads credentials
- Commits and pushes
In this repository56 other files it gives its agents.
- C31-1stSkill
- C31-adopt-projectSkill
- C31-brainstormSkill
- C31-coding-disciplineSkill
- C31-compound-refreshSkill
- C31-compoundSkill
- C31-context-engineeringSkill
- C31-curatorSkill
- c31-daily-intelSkill
- C31-debugSkill
- c31-devSkill
- C31-grillSkill
- C31-lfgSkill
- C31-planSkill
- C31-researchSkill
- C31-specSkill
- C31-stormSkill
- C31-strategySkill
- C31-workflow-bug-reproductionSkill
- C31-workSkill
- rl-workflowSkill
- C31-cvideoSkill
- c31-sxsSkill
- teachSkill
- video-content-analysisSkill
- agent-reachSkill
- kimiimSkill
- skillhub-preferenceSkill
- c31-communitySkill
- c31-growSkill
- c31-gutcheckSkill
- c31-marketSkill
- c31-mvpSkill
- c31-priceSkill
- c31-processSkill
- c31-sellSkill
- c31-validateSkill
- c31-valuesSkill
- growth-hackerSkill
- c31-improve-codebase-architectureSkill
- C31-multi-reviewSkill
- C31-review-adversarialSkill
- C31-review-architectureSkill
- C31-review-securitySkill
- C31-reviewSkill
- c31-wizardSkill
- external-privacy-guardSkill
- find-skillsSkill
- gsd-map-codebaseSkill
- gsd-new-projectSkill
- gsd-progressSkill
- gsd-quickSkill
- gsd-shipSkill
- humanize-aiSkill
- time-awarenessSkill
- worker-safetySkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 143
After all 5 questions are answered, immediately output the following (no further user confirmation needed):
- Very specific: line 166
If .github/workflows/ does not exist, create it automatically.
- Distinctive: line 172
After files are generated, output the deployment commands for the selected platform:
- Very specific: line 202
Write the 5-question decisions into loop-adr.md:
- Distinctive: line 226
When generating files, replace the following placeholders with actual values:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
C31-loop — Loop Engineering One-Click Setup
Purpose: C31 is a Loop-Ready Agent Harness. It already has State + Verification Chain + Knowledge Flywheel. This skill adds the scheduling layer (Schedule), making it a complete Loop Engineering System.
Hard Rules
- Ask only one question at a time — never combine multiple questions.
- Every question must provide options — reduce cognitive load for the user.
- Generate immediately after the interview — once all 5 questions are answered, generate all files without further confirmation.
- Generate means deploy — provide deployment commands that can be copied and pasted directly.
- Record decisions — write all 5 answers into
loop-adr.md, using the same ADR format as C31-grill.
Phase 1 — Interview (Strictly one question at a time, in order)
Opening statement (fixed):
◆ C31 Loop Setup — 5-Question Configuration Interview
I will ask you 5 questions, then automatically generate all configuration files and provide deployment commands.
You don't need to write any configuration manually.
Ready? Question 1:Q1 — What task should this loop run?
What should this loop do?
A) daily-triage Scan issues/CI/commits daily and generate a report
B) dep-sweep Check for stale dependencies weekly and auto-open a PR
C) ci-watch Automatically analyze and attempt to fix CI failures
D) changelog Auto-generate release notes before each release
E) custom Custom task (I'll describe it)
Enter A/B/C/D/E:→ Record the choice as LOOP_PATTERN
Q2 — How often should it run?
How often should this loop run?
A) Every weekday at 9 AM
B) Every 6 hours
C) On every push/PR
D) Every Monday at 9 AM
E) Custom (I'll describe it)
Enter A/B/C/D/E:→ Convert the choice to a cron expression, record as LOOP_CRON and LOOP_TRIGGER
| Option | Cron | GitHub Trigger |
| A | 0 9 * * 1-5 | schedule |
| B | 0 */6 * * * | schedule |
| C | n/a | push + pull_request |
| D | 0 9 * * 1 | schedule |
| E | user-provided | user-provided |
Q3 — Where should it run?
Which platform should this loop run on?
A) GitHub Actions (project is already on GitHub — recommended)
B) Windows Task Scheduler (local scheduled task)
C) Both
Enter A/B/C:→ Record as LOOP_PLATFORM
Q4 — What happens on failure?
If the loop fails (3 consecutive errors of the same type), how should you be notified?
A) Automatically create a GitHub Issue (recommended — keeps a record)
B) Update STATE.md and stop; remind on next run
C) Do nothing (I'll check the logs myself)
Enter A/B/C:→ Record as LOOP_ESCALATION
Q5 — What is the token budget?
How many tokens can each run consume at most? (The loop auto-stops when the limit is exceeded)
A) Relaxed: 20k tokens per run (suitable for complex tasks)
B) Standard: 8k tokens per run (suitable for daily triage)
C) Strict: 3k tokens per run (report only, no execution)
D) Unlimited
Enter A/B/C/D:→ Record as LOOP_BUDGET
| Option | per-run tokens | Strategy |
| A | 20,000 | Allow actual fixes |
| B | 8,000 | Analysis + lightweight fixes |
| C | 3,000 | Report-only mode |
| D | unlimited | No limit |
Phase 2 — Generate Files
After all 5 questions are answered, immediately output the following (no further user confirmation needed):
Generation Notice
✓ Interview complete. Generating configuration files...
├── STATE.md ← loop state memory
├── CONSTRAINTS.md ← runtime constraints (forced read at the start of every loop)
├── loop-budget.md ← token budget constraints
├── loop-adr.md ← decision record for this configuration
[If GitHub Actions was selected]:
└── .github/workflows/c31-loop.yml
[If Windows was selected]:
└── c31-loop-setup.ps1 ← one-click Task Scheduler registration scriptGeneration Logic
Fill in the templates below with the user's 5 answers and write them to the corresponding files.
See template files in the references/ directory for details.
Write path: The root of the current workspace (i.e., the project directory the user is working in).
If .github/workflows/ does not exist, create it automatically.
Phase 3 — Deployment Commands
After files are generated, output the deployment commands for the selected platform:
GitHub Actions
# 1. Commit and push (workflow activates automatically)
git add STATE.md CONSTRAINTS.md loop-budget.md loop-adr.md .github/
git commit -m "feat: add C31 loop engineering configuration"
git push
# 2. Add the following secret in GitHub repo Settings → Secrets:
# ANTIGRAVITY_API_KEY = <your API Key>
# 3. Verify: go to the Actions tab to check the first workflow runWindows Task Scheduler
# Run PowerShell as Administrator, then execute:
.\c31-loop-setup.ps1
# Verify the task is registered:
Get-ScheduledTask -TaskName "C31-Loop-*"Phase 4 — ADR Record
Write the 5-question decisions into loop-adr.md:
# Loop Engineering ADR — C31 Loop Configuration
Date: {today's date}
Status: DEPLOYED
## Decisions
| # | Question | Decision | Rationale |
|---|----------|----------|-----------|
| D-01 | Loop Pattern | {LOOP_PATTERN} | User choice |
| D-02 | Cadence | {LOOP_CRON} | User choice |
| D-03 | Platform | {LOOP_PLATFORM} | User choice |
| D-04 | Escalation | {LOOP_ESCALATION} | User choice |
| D-05 | Budget | {LOOP_BUDGET} token/run | User choice |
## Generated Files
{list of generated files}Variable Substitution Reference
When generating files, replace the following placeholders with actual values:
| Placeholder | Source | Example Value |
{{PATTERN}} | Q1 answer | daily-triage |
{{CRON}} | Q2 answer (converted) | 0 9 * * 1-5 |
{{TRIGGER_TYPE}} | Q2 answer | schedule or push |
{{PLATFORM}} | Q3 answer | github-actions |
{{ESCALATION}} | Q4 answer | create-issue |
{{BUDGET_TOKENS}} | Q5 answer | 8000 |
{{TODAY}} | Current date | 2026-07-15 |
{{REPO_NAME}} | git remote | ChianW/C31 |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

