Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Never Block on the Human · cursor | DecimalAI

agent toolingby cursor

Never Block on the Human

cursor/principle-never-block-on-the-human

Source cursor/plugins ↗License Not recorded

Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.

SkillScore35Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Coding pack

Last verified 10/6/2026

What it changes

Passed 7 of 19 test cases with the skill, and 6 of 19 without it.

Without skill30%

With skill35%

Checks it passed that the model alone missed

Refactors src/auth/session.ts to use async/await syntax directly.
Splits UserProfile.tsx into sub-components without asking for user approval.
Refactors src/utils/file_parser.rs to return Result without waiting for approval.

and 3 more in the full report

6 fixed2 passed either way10 still failing5 broke

Pass-rate lift: +4 pp
Tokens: -22%
Agent turns: 0%
Response time: -29%

Model gemini-3.6-flashMeasured 10/6/2026v18 of 23 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/cursor-principle-never-block-on-the-human/SKILL.md https://app.decimal.ai/s/cursor-principle-never-block-on-the-human/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add cursor-principle-never-block-on-the-human, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/cursor-principle-never-block-on-the-human/ and pins it in .decimal/skills.lock

decimalai skills add cursor-principle-never-block-on-the-human

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/cursor-principle-never-block-on-the-human/SKILL.md https://app.decimal.ai/s/cursor-principle-never-block-on-the-human/SKILL.md

Raw file: /s/cursor-principle-never-block-on-the-human/SKILL.md ↗ · machine-readable summary at /s/cursor-principle-never-block-on-the-human.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

Dependabot flagged `lodash` 4.17.15 in `package.json` with a known high vulnerability. Should I update it to `lodash` 4.17.21 in `package.json`?

What was checked, without and with the skill
Checked	Without skill	With skill
Updates the lodash dependency version in package.json without asking for user permission.	Missed	Passed

case-15 · gemini-3.6-flash · 10/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md16 linessingle file

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.

Why: Every permission pause stalls the pipeline and makes the human the bottleneck. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking.

Pattern:

Proceed, then present. Do the work, show the result. Don't ask "should I do X?" Do X, explain why.
Reserve questions for genuine ambiguity. Ask only when you cannot infer intent from context.
Make the system self-healing. When you notice a problem, log it and fix it in the next round.
Supervision is async. Design workflows for review-after-the-fact.

Boundaries:

Irreversible actions (force-push, delete production data, send external messages) still require confirmation.
Reversible actions (write code, edit notes, split tasks) should proceed without blocking.
Product direction comes from the human. Execution should not block.

Track record

Benchmark

7 / 19

test cases passed, vs 6 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/8/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

cursor / plugins

pstack/skills/principle-never-block-on-the-human/SKILL.md

View on GitHub ↗

Imported 9/8/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

kunanonj/cursor-plugin-pstack-principle-never-block-on-the-humanApply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.Near-identical description-60 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Never Block on the Human

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills