principle-never-block-on-the-human
Apply when tempted to ask 'should I do X?' on reversible work.
Skill by dotts-h
Chalk Labs
Need help deploying principle-never-block-on-the-human?
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/dotts-h-principle-never-block-on-the-human
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
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/principle-never-block-on-the-human
What's inside
- Skill name
principle-never-block-on-the-human- Description
- Apply when tempted to ask 'should I do X?' on reversible work. Decide, proceed, and let the human course-correct after the fact.
- License
- MIT
- Instructions
- 12 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Never block on the human The human supervises asynchronously. Agents must stay unblocked. Make reasonable decisions, proceed, and let the human course-correct after the fact. Code changes are reversible and reviewable, so a wrong decision usually costs less than blocking. - Proceed, then present. Do the work, and show the result. Do not ask "should I do X?" Do it, and explain why. - Make the system self-healing. When you notice a problem, log it and fix it in the next round. - Irreversible actions still require confirmation. A force-push, deleting production data, and sending an external message are irreversible. - Reversible actions should proceed without blocking. Writing code, editing notes, and splitting tasks are reversible. - Some reversible QA calls still wait for a person, because each one changes what counts as correct. Accepting a healed locator or a repaired check, updating a visual or snapshot baseline, and judging an assistive-technology outcome are such calls. Finish the work around each call, then present it with its evidence. - Product direction comes from the human. Execution should not block.
From dotts-h/qstack, MIT.
More from dotts-h/qstack
- 0.567score
qstack-mode
dotts-h
Run structured QA workflows in Cursor: test chartering, real-surface reproduction with recorded runs, defect triage, baseline-versus-patch fix verification…
SkillAFreshness: AClaude Code +9 - 0.567score
triage-defect
dotts-h
Triage bug reports with bounded cause tracing, duplicate detection, bug-versus-feature classification, and self-contained defect report formatting.
SkillAFreshness: AClaude Code +9 - 0.567score
reproduce-issue
dotts-h
Reproduce reported defects through the target app's real UI or CLI on at least two recorded runs, verify existing fixes against baseline and patched builds…
SkillAFreshness: AClaude Code +9 - 0.565score
setup-qstack
dotts-h
Configure which models the qstack how and why skills give their subagents and at what reasoning budget.
SkillAFreshness: AClaude Code +9 - 0.561score
principle-build-the-lever
dotts-h
Apply to any non-trivial work, including edits, migrations, analyses, and checks.
SkillAFreshness: AClaude Code +9 - 0.561score
regression-pin
dotts-h
Pin a reproduced bug or regression signal with a focused executable check that fails before the fix and passes after it, or select the closest live…
SkillAFreshness: AClaude Code +9 - 0.556score
principle-explain-the-number
dotts-h
Apply before you trust, report, or act on a number you measured.
SkillAFreshness: AClaude Code +9 - 0.556score
principle-sequence-verifiable-units
dotts-h
Apply to multi-step work such as sweeps, migrations, and runs of similar edits, and to how you stack commits and PRs.
SkillAFreshness: AClaude Code +9 - 0.556score
in-your-own-words
dotts-h
Restate the testing goal, target surface, and risk hypothesis in your own words before test execution.
SkillAFreshness: AClaude Code +9 - 0.541score
how
dotts-h
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: AClaude Code +9 - 0.536score
maintain-verification-skill
dotts-h
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature…
SkillAFreshness: AClaude Code +9 - 0.536score
blast-radius
dotts-h
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dotts-h/qstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dotts-h
- 0.567score
reproduce-issue
dotts-h
Reproduce reported defects through the target app's real UI or CLI on at least two recorded runs, verify existing fixes against baseline and patched builds…
SkillAFreshness: AClaude Code +9 - 0.567score
triage-defect
dotts-h
Triage bug reports with bounded cause tracing, duplicate detection, bug-versus-feature classification, and self-contained defect report formatting.
SkillAFreshness: AClaude Code +9 - 0.567score
qstack-mode
dotts-h
Run structured QA workflows in Cursor: test chartering, real-surface reproduction with recorded runs, defect triage, baseline-versus-patch fix verification…
SkillAFreshness: AClaude Code +9 - 0.565score
setup-qstack
dotts-h
Configure which models the qstack how and why skills give their subagents and at what reasoning budget.
SkillAFreshness: AClaude Code +9 - 0.561score
regression-pin
dotts-h
Pin a reproduced bug or regression signal with a focused executable check that fails before the fix and passes after it, or select the closest live…
SkillAFreshness: AClaude Code +9 - 0.561score
principle-build-the-lever
dotts-h
Apply to any non-trivial work, including edits, migrations, analyses, and checks.
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 principle-never-block-on-the-human 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
principle-never-block-on-the-human skill. Agent Mart. https://agentmart.dev/skills/dotts-h-principle-never-block-on-the-human (last updated 2026-10-24)