Ready to supercharge your AI agents?

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

AC Stop Hook Analyzer — measured AI agent skill | DecimalAI

majiayu000/ac-stop-hook-analyzer

NewSkillScoreMaintained

Analyze context and decide on continuation via Stop hook. Use when determining if work should continue, analyzing completion status, making continuation decisions, or implementing the Two-Claude pattern.

agent-toolingby majiayu000

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/majiayu000-ac-stop-hook-analyzer/SKILL.md

decimalai skills pull majiayu000-ac-stop-hook-analyzer --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/majiayu000-ac-stop-hook-analyzer/SKILL.md https://app.decimal.ai/s/majiayu000-ac-stop-hook-analyzer/SKILL.md

Raw file: /s/majiayu000-ac-stop-hook-analyzer/SKILL.md ↗ · machine-readable summary at /s/majiayu000-ac-stop-hook-analyzer.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

Yes — +50% lift-54% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-61%	0%
case-02	✗→✓	▲ Improved	-69%	0%
case-03	✗→✓	▲ Improved	-44%	0%
case-04	✗→✓	▲ Improved	-75%	0%
case-05	✗→✓	▲ Improved	-74%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

majiayu000 / claude-skill-registry

skills/agent/ac-stop-hook-analyzer-adaptationio-skrillz-3/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

AC Stop Hook Analyzer

Analyze context to decide on continuation (Two-Claude Pattern).

Purpose

Implements the Analyzer role in the Two-Claude Pattern, using Opus 4.5 to intelligently decide whether to continue autonomous operation.

Quick Start

python
from scripts.stop_hook_analyzer import StopHookAnalyzer

analyzer = StopHookAnalyzer(project_dir)
decision = await analyzer.should_continue()
# Returns: {"decision": "block", "reason": "Continue with api-003"}

Decision Logic

Check completion against objective
Analyze remaining features
Validate safety limits
Return continue/stop decision

API Reference

See scripts/stop_hook_analyzer.py for full implementation.

Want to see if majiayu000/ac-stop-hook-analyzer would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.