running-routines
The contract every unattended agent routine follows in a company repository — the project data file, the develop gate that opens every run, which issues an…
Skill by galileo-studio-dev
Chalk Labs
Need help deploying running-routines?
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.
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/galileo-studio-dev-running-routines
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.
About
Use cases: documents, data, writing, agent-building
Reviews
Write a reviewNo 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 and code. Checked Nov 2, 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/running-routines
What's inside
- Skill name
running-routines- Description
- The contract every unattended agent routine follows in a company repository — the project data file, the develop gate that opens every run, which issues an agent may take, how it claims, asks and gives up, which tracker states it may set, and what it never does. Use at the start of any scheduled or remotely fired Claude Code routine session, and when writing or changing a routine prompt. The mode skills `working-the-queue`, `scanning-for-issues` and `sweeping-open-work` build on it.
- License
- unknown
- Instructions
- 108 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- project-data-template.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from galileo-studio-dev/skills
- 0.559score
scanning-for-issues
galileo-studio-dev
Find mode of an unattended routine — runs the develop gate, enforces the needs-human and queue caps, reminds about stale needs-human issues, scans what…
SkillAFreshness: AClaude Code +9 - 0.559score
delivering-changes
galileo-studio-dev
Runs the implement, review, and deliver stages of an approved plan through Worker and Reviewer subagents with gates between stages.
SkillAFreshness: AClaude Code +9 - 0.559score
filing-followups
galileo-studio-dev
Turns the deferred findings of work that is already finished into tracker issues an engineer can pick up cold.
SkillAFreshness: AClaude Code +9 - 0.519score
designing-error-handling
galileo-studio-dev
Decides where and how failures are handled.
SkillBFreshness: BClaude Code +9 - 0.519score
learning-codebase-conventions
galileo-studio-dev
Discovers and follows the conventions of the codebase being changed.
SkillBFreshness: BClaude Code +9 - 0.519score
instrumenting-for-observability
galileo-studio-dev
Adds logging, metrics, tracing, and error reporting that let someone else diagnose a failure.
SkillBFreshness: BClaude Code +9 - 0.519score
changing-schemas-safely
galileo-studio-dev
Plans and writes schema and data migrations that survive rollout and rollback.
SkillBFreshness: BClaude Code +9 - 0.519score
reviewing-pull-requests
galileo-studio-dev
Reviews a pull request or branch end to end and reports findings in the company's pull request format.
SkillBFreshness: BClaude Code +9 - 0.519score
scoping-changes
galileo-studio-dev
Keeps a change to the scope that was requested.
SkillBFreshness: BClaude Code +9 - 0.499score
ponytail
galileo-studio-dev
Forces the laziest solution that actually works, simplest, shortest, most minimal.
SkillBFreshness: BClaude Code +9 - 0.494score
finishing-a-development-branch
galileo-studio-dev
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting…
SkillBFreshness: BClaude Code +9 - 0.493score
requesting-code-review
galileo-studio-dev
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 16, 2026 (17 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/galileo-studio-dev/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from galileo-studio-dev
- 0.559score
filing-followups
galileo-studio-dev
Turns the deferred findings of work that is already finished into tracker issues an engineer can pick up cold.
SkillAFreshness: AClaude Code +9 - 0.559score
scanning-for-issues
galileo-studio-dev
Find mode of an unattended routine — runs the develop gate, enforces the needs-human and queue caps, reminds about stale needs-human issues, scans what…
SkillAFreshness: AClaude Code +9 - 0.559score
delivering-changes
galileo-studio-dev
Runs the implement, review, and deliver stages of an approved plan through Worker and Reviewer subagents with gates between stages.
SkillAFreshness: AClaude Code +9 - 0.519score
learning-codebase-conventions
galileo-studio-dev
Discovers and follows the conventions of the codebase being changed.
SkillBFreshness: BClaude Code +9 - 0.519score
designing-error-handling
galileo-studio-dev
Decides where and how failures are handled.
SkillBFreshness: BClaude Code +9 - 0.519score
instrumenting-for-observability
galileo-studio-dev
Adds logging, metrics, tracing, and error reporting that let someone else diagnose a failure.
SkillBFreshness: BClaude Code +9
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 running-routines 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.
Cite this page
running-routines skill. Agent Mart. https://agentmart.dev/skills/galileo-studio-dev-running-routines (last updated 2026-10-24)