Ready to supercharge your AI agents?

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

Get Started Free →

Haolange/Skeptic — measured AI agent skill | DecimalAI

haolange/skeptic

SkillScore86Maintained

Internal specialist skill for Challenge weak claims and sign off only when proven.. Use when `rdc-debugger` dispatches skeptic work.

by haolange

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

Automatic

DevOps & SRE pack

decimalai skills pull haolange-skeptic

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/haolange-skeptic/SKILL.md

Raw file: /s/haolange-skeptic/SKILL.md ↗ · machine-readable summary at /s/haolange-skeptic.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 7d ago

—-39% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-44%	0%
case-08	✗→✓	▲ Improved	-58%	0%
case-09	✗→✓	▲ Improved	-48%	0%
case-10	✗→✓	▲ Improved	-33%	0%
case-11	✗→✓	▲ Improved	-53%	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 — 8/1/2026

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

haolange / rdc-agentcaps

debugger/platforms/code-buddy/skills/skeptic/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/1/2026Version v5

Skill contents

SKILL.md

角色技能包装说明

当前文件是 Codex 的 role skill 入口。

该角色默认是 internal/debug-only specialist。平台启动后不会自动进入该角色；只有用户手动召唤 rdc-debugger 并由它分派时，才进入当前 role。

Read first:

common/skills/rdc-debugger/SKILL.md
common/skills/skeptic/SKILL.md
common/config/platform_capabilities.json

Platform contract:

coordination_mode = staged_handoff
orchestration_mode = multi_agent
live_runtime_policy = single_runtime_single_context
live tools process is broker-owned; specialists operate through ownership_lease mediated broker actions

硬规则：

没有 passed artifacts/intake_gate.yaml 与完整 runtime broker artifacts 前，不得进入 live 调查。
只允许通过 broker action 请求访问 live runtime；不得直接调 live CLI，不得持有 tools process。
不得缓存并跨 handoff 复用 session_id / context_id / event_id 等 runtime handle。
不得临时写 Python、PowerShell 或 shell wrapper 批处理 live CLI。

Do not use this platform template before copying top-level debugger/common/ into the platform-local common/. Runtime case/run artifacts and reports are written under the platform-local workspace/.

Want to see if haolange/skeptic 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.