Skip to content
Agentmart
Submit a tool

operations

Diagnose runtime issues, manage incident response, verify policy posture, and execute safe operational changes with rollback planning.

Skill by goatcitadel

IndexedApache-2.0★ 2
Write a review

Chalk Labs

Need help deploying operations?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/goatcitadel-operations

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Diagnose runtime issues, manage incident response, verify policy posture, and execute safe operational changes with rollback planning. Use when GoatCitadel encounters service health problems, needs deployment verification, requires incident triage, or must execute runtime-changing actions with blast radius awareness.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/operations

What's inside

Skill name
operations
Description
Diagnose runtime issues, manage incident response, verify policy posture, and execute safe operational changes with rollback planning. Use when GoatCitadel encounters service health problems, needs deployment verification, requires incident triage, or must execute runtime-changing actions with blast radius awareness.
License
Apache-2.0
Metadata
version: 0.1.0
Instructions
60 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Operations

Maintain runtime reliability, enforce policy posture, and run incident response workflows for GoatCitadel services.

Use this skill when:
- A service is unhealthy or unreachable and needs diagnosis
- A deployment needs pre/post verification
- An incident requires structured triage, timeline recording, and mitigation
- A runtime-changing action needs blast radius assessment and rollback planning
- Policy posture or safety boundaries need verification

Do not use this skill when:
- The task is purely code implementation (use `coding` instead)
- The task is test strategy or regression analysis (use `qa` instead)
- The task is architecture or interface design (use the relevant design skill)

## Workflow

### Diagnose

1. Check service status with `session.status` or `http.get` health endpoints
2. Gather logs, error messages, and recent change history
3. Identify the failing component and its dependencies
4. Classify severity: **P0** (full outage), **P1** (degraded), **P2** (minor), **P3** (cosmetic)

### Plan

1. Identify the fix or mitigation action
2. Assess blast radius - what else could break
3. Define rollback path - how to undo if the fix fails
4. Verify policy impact - does this change safety boundaries, permissions, or deny-wins rules

### Execute

1. Apply the change with the smallest possible scope
2. Verify the fix resolved the issue
3. Confirm no regressions in dependent services
4. Record the incident timeline: detection -> diagnosis -> mitigation -> resolution

### Post-Incident

1. Document what happened, root cause, and resolution
2. Identify preventive measures for recurrence
3. Update monitoring or alerting if gaps were found

## Safety Rules

- Always run safe diagnostics before runtime-changing actions
- Never bypass policy engine checks or approval gates
- Never auto-disable safety boundaries to unblock a fix
- Prefer the smallest possible change that resolves the issue
- If uncertain about blast radius, escalate to the user before executing

## Tools You May Use

- `session.status` - check current session and service state
- `shell.exec` - run diagnostic or remediation commands
- `http.get` - probe health endpoints and external service status

From goatcitadel/GoatCitadel, Apache-2.0.

More from goatcitadel/GoatCitadel

Signals

Stars
2
Forks
2
Open issues
14
Last commit (this folder)
May 7, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
0.1.0
License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from goatcitadel

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get operations running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying operations?

CallGet help
Cite this page

operations skill. Agent Mart. https://agentmart.dev/skills/goatcitadel-operations (last updated 2026-10-24)