---
title: "boshu2/agentops skills ยท skilld"
canonical_url: "https://skilld.dev/gh/boshu2/agentops"
meta:
description: "DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it."
"og:description": "DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it."
"og:title": "boshu2/agentops skills"
"twitter:description": "DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it."
"twitter:title": "boshu2/agentops skills"
---
`
[All skills](https://skilld.dev/skills)
[](https://skilld.dev/gh/boshu2)
# **boshu2/agentops**
DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it.
main Updated 17 hours ago [GitHub](https://github.com/boshu2/agentops)
## Repository statistics
- Indexed skills
**30**
- Skill groups
**3**
- GitHub stars
**447**
- Forks
**42**
## Skills by folder
30 total
Sort skills
### **Fixtures**
2 skills
[
**/good-skill**
A planted fixture that satisfies every blocking skill-eval rule so the gate passes cleanly. /good-skill](https://skilld.dev/gh/boshu2/agentops/good-skill)
Updated last week
[
**/bad-skill**
DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it. /bad-skill](https://skilld.dev/gh/boshu2/agentops/bad-skill)
Updated 4 months ago
### **Skills**
3 skills
[
**/implement**
Implement changes, repairs or waves; return per-lane evidence. Use when: coding, service operations, reliability, delivery, incident recovery, resilience or toil is authorized. /implement](https://skilld.dev/gh/boshu2/agentops/implement)
Updated 6 days ago
[
**/using-gc**
Operate Gas City through its Mayor, registry packs and native run state. Use when: the caller explicitly selects Gas City; factory completion does not replace independent judgment. /using-gc](https://skilld.dev/gh/boshu2/agentops/using-gc)
Updated 6 days ago
[
**/validate**
Freshly judge a finished change and its claims against original acceptance. Use when: acceptance verdict or independent proof is sought. Clarify generic checks or readiness first. /validate](https://skilld.dev/gh/boshu2/agentops/validate)
Updated 6 days ago
### **Skills codex**
25 skills
[
**/agent-native**
Dispatch independent tasks to parallel workers or selected persistent roles. Use when: delegation is authorized with disjoint scopes; execution does not validate output. /agent-native](https://skilld.dev/gh/boshu2/agentops/agent-native)
Updated 6 days ago
[
**/doc**
Write grounded docs, READMEs, repo instructions or continuity handoffs. Use when: these documents are requested; no reports as a routine completion ritual. /doc](https://skilld.dev/gh/boshu2/agentops/doc)
Updated 6 days ago
[
**/council**
Compare model perspectives for brainstorming, planning, validation, idea duels or interviews. Use when: independent proposals or judgments need optional bounded debate. /council](https://skilld.dev/gh/boshu2/agentops/council)
Updated 6 days ago
[
**/skill-builder**
Create, adapt, consolidate or repair skill packages and projections. Use when: authoring guidance, descriptions or structure; Skill Eval measures behavioral benefit. /skill-builder](https://skilld.dev/gh/boshu2/agentops/skill-builder)
Updated 6 days ago
[
**/idea-genie**
Generate evidenced options or challenge an idea. Use when: deciding what to build or comparing alternatives; exploration does not authorize implementation. /idea-genie](https://skilld.dev/gh/boshu2/agentops/idea-genie)
Updated last week
[
**/interview**
Interview the caller one question at a time to settle a big outcome before agents work alone. Use when: shaping a goal or large RPI. Not for one question on one slice; use Plan. /interview](https://skilld.dev/gh/boshu2/agentops/interview)
Updated last week
[
**/craft-goal**
Draft or lint a bounded persistent goal above a bead graph of RPI experiments. Use when: this goal workflow is explicitly selected; shaping a single change belongs to Plan. /craft-goal](https://skilld.dev/gh/boshu2/agentops/craft-goal)
Updated last week
[
**/navigate**
Pick the next wave on a bead graph and keep the graph honest toward frozen acceptance. Use when: a goal starts a wave, or you ask what is next on an epic. /navigate](https://skilld.dev/gh/boshu2/agentops/navigate)
Updated last week
[
**/orchestrate**
Coordinate authorized workers, prerequisites, isolated scopes and review capacity. Use when: dispatching, recovering or routing feedback. Not for implementation or judgment. /orchestrate](https://skilld.dev/gh/boshu2/agentops/orchestrate)
Updated last week
[
**/plan**
Define intended behavior, review write scope and assess reversible decisions. Use when: discovery needs clarification or resumption before one complete slice; stop once actionable. /plan](https://skilld.dev/gh/boshu2/agentops/plan)
Updated last week
[
**/rpi**
Apply the outcome-to-judgment charter. Use when: the caller explicitly selects RPI; ordinary coding, delegation and native goals do not require this workflow. /rpi](https://skilld.dev/gh/boshu2/agentops/rpi)
Updated last week
[
**/reality-check**
Audit claimed state, goals or native status. Use when: a claim audit or snapshot is requested. Clarify advice versus acceptance for ambiguous checking or readiness requests. /reality-check](https://skilld.dev/gh/boshu2/agentops/reality-check)
Updated last week
[
**/review**
Give advisory feedback on a plan, design or code. Use when: suggestions, tradeoffs or a second look are wanted. Not for acceptance or write scope; use Validate or Plan. /review](https://skilld.dev/gh/boshu2/agentops/review)
Updated last week
[
**/domain**
Clarify domain terms, bounded contexts and repository conventions. Use when: naming, rule ownership or Go and other language standards are unclear; avoid a broad survey. /domain](https://skilld.dev/gh/boshu2/agentops/domain)
Updated last week
[
**/premortem**
Challenge a rollout plan with one fresh judge before implementation; identify what could make it fail. Not for finished-code judgment. Triggers: "one judge", "challenge this plan". /premortem](https://skilld.dev/gh/boshu2/agentops/premortem)
Updated last week
[
**/research**
Trace code or test a recurring pattern to answer one cited question. Use when: uncertainty needs evidence. Not for external feature teardowns; use reverse-engineer. /research](https://skilld.dev/gh/boshu2/agentops/research)
Updated last week
[
**/memory**
Find reviewed context, capture evidence or curate maintained claims. Use when: prior evidence can change an action, or learning is requested; no mandatory recall or lesson. /memory](https://skilld.dev/gh/boshu2/agentops/memory)
Updated last week
[
**/postmortem**
Analyze outcomes or an interim cutoff. Use when: a postmortem is explicitly requested; consumes available judgment, never gates code acceptance or requires a lesson. /postmortem](https://skilld.dev/gh/boshu2/agentops/postmortem)
Updated 3 weeks ago
[
**/skill-eval**
Measure whether a skill helps a named task or needs revision or removal. Use when: a bounded routing or coding evaluation is requested; conformance alone cannot show benefit. /skill-eval](https://skilld.dev/gh/boshu2/agentops/skill-eval)
Updated 3 weeks ago
[
**/agy-native**
Run a supplied task in AGY Antigravity and collect its result. Use when: the caller selects AGY; never a fallback for native coding. /agy-native](https://skilld.dev/gh/boshu2/agentops/agy-native)
Updated 3 weeks ago
[
**/codex-exec**
Run one prompt through headless Codex and capture its result. Use when: requesting a single noninteractive Codex process. Not for worker batches or retries. /codex-exec](https://skilld.dev/gh/boshu2/agentops/codex-exec)
Updated 3 weeks ago
[
**/refactor**
Simplify structure, interfaces or responsibilities while preserving behavior. Use when: a focused refactor is requested; feature changes need their own intent. /refactor](https://skilld.dev/gh/boshu2/agentops/refactor)
Updated 3 weeks ago
[
**/reverse-engineer**
Tear down an authorized competitor repo, binary or product into a feature inventory and adoption choices. Use when: comparing an external system; local questions go to Research. /reverse-engineer](https://skilld.dev/gh/boshu2/agentops/reverse-engineer)
Updated 3 weeks ago
[
**/security**
Review code or scan for security vulnerabilities, secrets, dependencies and prompt risks. Use when: concrete exposure needs assessment; never silently change policy. /security](https://skilld.dev/gh/boshu2/agentops/security)
Updated 3 weeks ago
[
**/test**
Write behavioral tests, practice TDD or inspect important coverage gaps. Use when: test design or missing proof needs work; running an existing suite needs no skill. /test](https://skilld.dev/gh/boshu2/agentops/test)
Updated 3 weeks ago
## Add to your README
The badge links readers to this page. It shows the skilld mark and no counts, and it follows the reader's light or dark GitHub theme.
``