Skip to content
Agentmart
Submit a tool

surface-human-topics

Surface decision-worthy and uncertainty-heavy topics inside one project's active context.

Skill by armin-haghi

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying surface-human-topics?

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/armin-haghi-surface-human-topics

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

Surface decision-worthy and uncertainty-heavy topics inside one project's active context.

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/surface-human-topics

What's inside

Skill name
surface-human-topics
Description
Surface decision-worthy and uncertainty-heavy topics inside one project's active context.
License
MIT
Instructions
82 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Surface Human Topics

Use this skill to turn project-local ambiguity, risk, and decision pressure
into a concise set of human-facing topics.

This skill is project-local.
It does not aggregate across multiple projects.

## Read order

Use the repo's live project-doc surface.
The default layout is `docs/`, but follow any repo-local override declared in
`AGENTS.md`.

Read only the smallest sufficient project context:
1. `session-brief.md` on the live project-doc surface
2. `current-milestone.md` on the live project-doc surface
3. `open-questions.md` on the live project-doc surface only if needed
4. `project-spine.md` on the live project-doc surface only if milestone intent or project boundary is
   unclear

Do not load broad context by default.
Do not load broad background material unless the topic explicitly depends on
design or operating-model reference material.
In `llm-os`, that means `llm-os-docs/background/`.

## What to surface

Surface only items that are genuinely decision-worthy or likely to block safe
execution.

Each surfaced topic should include:
- project
- stage
- active milestone
- recommendation
- uncertainty
- risks
- explicit question for the human
- default next step if the human does not immediately respond

Good candidates:
- unresolved tradeoffs
- assumptions that could change milestone outcome
- blockers that now need human resolution
- scope or priority questions that can no longer be handled safely by default

Do not surface routine implementation details that can be handled locally.

## Write-back behavior

Write to the smallest correct durable artifact.

Typical targets:
- `open-questions.md` on the live project-doc surface when a real human decision or unresolved tradeoff
  needs an owner and default assumption
- `session-brief.md` on the live project-doc surface when the topic mainly affects the current working
  context, next action, or immediate risk framing
- `current-milestone.md` on the live project-doc surface only when the surfaced topic materially changes
  milestone scope, acceptance, dependency framing, or blocker wording

Avoid duplicating the same surfaced topic across multiple artifacts unless the
repo's rules clearly require it.

## Behavior

- keep the output concise and decision-oriented
- prefer one clearly framed human topic over a long list of weak questions
- make the default assumption explicit when safe
- separate uncertainty from actual human decisions
- prefer project-local clarity over portfolio-style rollups

## Escalation

Escalate or request broader context only when:
- the project boundary itself is unclear
- the correct write-back target cannot be chosen safely
- the topic depends on cross-project prioritization
- the current project context is too stale or contradictory to surface topics
  responsibly

From armin-haghi/llm-os, MIT.

More from armin-haghi/llm-os

Signals

Stars
1
Forks
0
Open issues
1
Last commit (this folder)
Apr 23, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from armin-haghi

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 surface-human-topics 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 surface-human-topics?

CallGet help
Cite this page

surface-human-topics skill. Agent Mart. https://agentmart.dev/skills/armin-haghi-surface-human-topics (last updated 2026-10-24)