Ready to supercharge your AI agents?

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

Auto Permissions Review - Enable · michaelboeding | DecimalAI

agent toolingby michaelboeding

Auto Permissions Review - Enable

michaelboeding/auto-permissions-review-enable

Source michaelboeding/skills ↗License MIT

Enable the auto permissions review hook for this session. Auto-approves read-only operations, sends ambiguous Bash to Haiku, and reviews edits only in accept-edits mode. Other terminal sessions are not affected.

SkillScore73Maintained

Automatic

Security & AppSec pack

Last verified 8/3/2026

What it changes

Passed 12 of 16 test cases with the skill, and 4 of 16 without it.

Without skill27%

With skill73%

Checks it passed that the model alone missed

Identifies string ai-review-enable
Instructs the user to press Shift+Tab
Identifies path ~/.claude/hooks/ai-review.sh

and 8 more in the full report

10 fixed6 passed either way6 still failing0 broke

Pass-rate lift: +45 pp
Tokens: -58%
Agent turns: 0%
Response time: -68%

Model gemini-3.6-flashMeasured 8/3/2026v116 of 22 cases passed with skill · 16 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/michaelboeding-auto-permissions-review-enable/SKILL.md https://app.decimal.ai/s/michaelboeding-auto-permissions-review-enable/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add michaelboeding-auto-permissions-review-enable, 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/michaelboeding-auto-permissions-review-enable/ and pins it in .decimal/skills.lock

decimalai skills add michaelboeding-auto-permissions-review-enable

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

curl -fsSL --create-dirs -o .claude/skills/michaelboeding-auto-permissions-review-enable/SKILL.md https://app.decimal.ai/s/michaelboeding-auto-permissions-review-enable/SKILL.md

Raw file: /s/michaelboeding-auto-permissions-review-enable/SKILL.md ↗ · machine-readable summary at /s/michaelboeding-auto-permissions-review-enable.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

What specific string keyword printed by bash allows the hook to detect that auto permission review is being enabled?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies string ai-review-enable	Missed	Passed

case-19 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md31 linessingle file

Auto Permissions Review - Enable

Turn on the auto permissions review hook for the current session.

Workflow

Step 1: Check if the hook is installed

[ -f ~/.claude/hooks/ai-review.sh ] && echo "installed" || echo "not installed"

If not installed, tell the user to run /auto-permissions-review-install first to install it.

Step 2: Enable for this session

The hook detects this command by the keyword and creates a session file automatically.

mkdir -p ~/.claude/ai-review-sessions && echo "ai-review-enable" && echo "Auto permissions review is now ON for this session."

Step 3: Confirm

Tell the user:

Auto permissions review is now enabled for this session
Read-only tools (Read, Glob, Grep, etc.) are auto-approved instantly
Ambiguous Bash commands are reviewed by Haiku
Edits only go through Haiku when accept-edits mode is on (Shift+Tab)
Other terminal sessions are not affected
Use /auto-permissions-review-disable to turn it off

Track record

Benchmark

12 / 16

test cases passed, vs 4 / 16 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 v4 — 8/1/2026

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

michaelboeding / skills

skills/auto-permissions-review-enable/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

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

Auto Permissions Review - Enable

Workflow

Step 1: Check if the hook is installed

Step 2: Enable for this session

Step 3: Confirm

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills