_template
暂无简介
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
02 资源文件 3
- 参考文档contract.json986 B
- 参考文档SOURCE.md188 B
- 参考文档TRUST.auto.yaml2.2 KB
03 SKILL.md 正文
SKILL.md — {skill_name}
Intent
One sentence describing what this procedure accomplishes.
When to Use
- Condition 1
- Condition 2
When NOT to Use
- Quick fix that can be done inline
- No existing code to work with
- Not in the skills list
Inputs
| Name | Type | Description |
|---|---|---|
| target_paths | paths | Files/directories to modify |
| goal | string | Desired end state |
Outputs
| Name | Type | Description |
|---|---|---|
| report | markdown | Path to outputs/{skill}/{timestamp}/report.md |
| changed_files | list | Files that were modified |
Procedure
- Identify scope — Confirm which files need changes
- Gather baseline — Run tests, record current state
- Make smallest safe change — One logical change at a time
- Verify — Run tests, check for regressions
- Record receipts — Log what was done and why
Verification
cargo test(for Rust projects)npm test(for Node projects)- Manual verification steps
Rollback
How to undo this change if something goes wrong.
Safety & Escalation
- Escalate to user if: [conditions]
- Never do: [forbidden actions]
- If stuck for >3 steps: Ask for help
Metadata
- version: 1.0.0
- author: {agent_name}
- created: {date}
- parent: reference to parent skill (if any)
04 同仓库更多 Skills
jev
Ask typed System One judgments (noul / choice / score) against Allternit's LOCAL System One server instead of prompting a chat model to "return JSON". Use when classifying, routing, scoring, or screening something and code needs a probability it can branch on, or when the user runs /jev. Official TypeSafe Jev is an optional, explicit remote lane.
jev-route
Route with local System One answers — map Choice + confidence to act / confirm / human lanes, or pick a model tier by Choice label. Also documents the separate `route-model` helper for OpenRouter's typesafe/jev-router (a chat-model router, NOT System One). Use for confidence routing, model-tier routing, or when the user runs /jev-route.
jev-guardrail
Screen text or agent tool calls with a battery of local System One Noul hazards plus a Score, with policy in code — and the Claude Code PreToolUse guard (hooks/pretooluse-guard) that puts deterministic hard rules first and lets Jev only raise friction. Use for injection/secret/destructive-action screening or when the user runs /jev-guardrail.
jev-fanout
Ask every independent System One question over the same state in ONE POST /v1/systemone to the local server (speculative fan-out). Use for parallel judgments, compound commands, one-call turn assessment, or when the user runs /jev-fanout. Do not fire one HTTP call per question.
memory-drive
Read and write the user's Allternit Memory Drive, a git repo of markdown memories in the open Agent Memory Repo format. Use at the start of a session to load what the user's agents remember (MEMORY.md), when the user says "remember this", when you learn a durable fact about the user or their work, and before answering questions that depend on past sessions.
agent-orchestrator
Orchestrate external CLI agents (kimi, codex, agy, claude, grok, gizzi) through the Allternit Factory (gizzi agents / orchestration / workspace / workflows). Use when the user asks to delegate, offload, or farm out implementation work to another CLI agent / terminal session, or to run work outside this session to save tokens. Part of Allternit Agents / Bot Agents — not a separate product.