ai
Use when product or application work adds, changes, reviews, tests, or evaluates model behavior, inference prompts, model context, model tools, routing…
Skill by kristofferremback
Chalk Labs
Need help deploying ai?
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/kristofferremback-ai
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: ml
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. 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/ai
What's inside
- Skill name
ai- Description
- Use when product or application work adds, changes, reviews, tests, or evaluates model behavior, inference prompts, model context, model tools, routing, settings, or AI features.
- License
- MIT
- Instructions
- 15 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# AI Treat AI behavior as experimental. Production and evaluation must exercise the same implementation. - Keep model, system prompt, context, temperature, toolset, and relevant inference settings overrideable at the production entry point. - Pass overrides through one typed boundary. Never copy production logic into an eval harness. - Preserve provider semantics and report unsupported overrides rather than silently dropping or translating them. - Capture outcomes, trajectories, tool calls, latency, token use, and cost needed to compare experiments. - Evaluate representative user behavior and failure cases. A passing prompt snapshot is not proof of product quality. - Keep defaults centralized and observable. Record the exact configuration behind every result. - Separate deterministic application behavior from probabilistic model behavior so each can be tested honestly. Load `test` for proof and `frontend` when model behavior changes what users see or control.
From kristofferremback/slopestyle, MIT.
More from kristofferremback/slopestyle
- 0.566score
datadog
kristofferremback
Use when querying Datadog traces or diagnosing Datadog API authentication, including Galdera startup and post-deploy checks.
SkillAFreshness: AClaude Code +9 - 0.565score
daily-check-in
kristofferremback
Use when Kris asks for a daily work check-in, morning prioritization, or a refreshed check-in report.
SkillAFreshness: AClaude Code +9 - 0.564score
breakdown
kristofferremback
Use when Kris asks to break down a project or large change into tickets, or to write or rewrite a ticket.
SkillAFreshness: AClaude Code +9 - 0.564score
deploy
kristofferremback
Use when the developer explicitly asks to merge, deploy, release, roll out, or promote a ready pull request or stack.
SkillAFreshness: AClaude Code +9 - 0.559score
coding-style-review
kristofferremback
Use when asked for a standalone coding-style review against CODINGSTYLE.md.
SkillAFreshness: AClaude Code +9 - 0.558score
describe-changes
kristofferremback
Use when the developer asks for a description or reminder of the current changes, PR, or stack of PRs.
SkillAFreshness: AClaude Code +9 - 0.550score
beg-for-reviews
kristofferremback
Ask for PR reviews or :eyes: in Slack.
SkillAFreshness: AClaude Code +9 - 0.544score
build
kristofferremback
Use when the user asks to build or implement substantial work, or when a feature, fix, or refactor needs planning across one or more reviewable changes.
SkillAFreshness: AClaude Code +9 - 0.524score
quota
kristofferremback
Use when Kris asks what is eating Claude or Codex quota, which sessions use the most, how close a limit is, or for usage by session, subagent, model, effort…
SkillBFreshness: BClaude Code +9 - 0.524score
recall
kristofferremback
Use when Kris asks to catch up, recall work on a topic, resume stale work, find where he left off, or reconstruct current state from prior sessions.
SkillBFreshness: BClaude Code +9 - 0.524score
migrate
kristofferremback
Use when changing persistent data, database schemas, migrations, backfills, compatibility windows, data repair, or rollout sequencing around stored state.
SkillBFreshness: BClaude Code +9 - 0.524score
monitor
kristofferremback
Use after deployment, or when the user asks to verify production, confirm a revision is live, watch rollout health, or investigate post-deploy behavior.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 19, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kristofferremback/slopestyle
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kristofferremback
- 0.566score
datadog
kristofferremback
Use when querying Datadog traces or diagnosing Datadog API authentication, including Galdera startup and post-deploy checks.
SkillAFreshness: AClaude Code +9 - 0.565score
daily-check-in
kristofferremback
Use when Kris asks for a daily work check-in, morning prioritization, or a refreshed check-in report.
SkillAFreshness: AClaude Code +9 - 0.564score
breakdown
kristofferremback
Use when Kris asks to break down a project or large change into tickets, or to write or rewrite a ticket.
SkillAFreshness: AClaude Code +9 - 0.564score
deploy
kristofferremback
Use when the developer explicitly asks to merge, deploy, release, roll out, or promote a ready pull request or stack.
SkillAFreshness: AClaude Code +9 - 0.559score
coding-style-review
kristofferremback
Use when asked for a standalone coding-style review against CODINGSTYLE.md.
SkillAFreshness: AClaude Code +9 - 0.558score
describe-changes
kristofferremback
Use when the developer asks for a description or reminder of the current changes, PR, or stack of PRs.
SkillAFreshness: AClaude 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 ai 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
ai skill. Agent Mart. https://agentmart.dev/skills/kristofferremback-ai (last updated 2026-10-24)