using-superpowers

提供使用进阶 agent 工具与技能的合规策略层：包含触发条件、决策、执行、验证、错误恢复、密钥脱敏与自评等规则文本；附带 Codex、Gemini、Pi、Antigravity 等工具参考文档，以及本地脚本 skill_router.py，可按请求文本与技能目录匹配推荐 skill。技能本体多为通用策略描述，未包含实际工具集成的实现代码。

pmuhammadagus-byte

热度 47.98

最近更新 2026-08-25 10:53:21

分类：自动化依赖：代码执行 / 读写文件应用场景：工作流 / 任务管理 / 自动化脚本

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add pmuhammadagus-byte/using-superpowers

Metadata

name: using-superpowers
description: Gunakan saat user minta pakai fitur lanjutan agent (tool/skill/integrasi) secara aman & terukur pada task tertentu.
metadata: {"openclaw":{"version":"1.0.4"}}

using-superpowers — X∞ Compliance Layer

1. IDENTITY

Skill milik user: using-superpowers. Mengikuti Skill Architecture Standard X∞ (wajib).

2. PURPOSE

Menyediakan kemampuan using-superpowers kepada agent saat relevan.

3. METADATA

name: using-superpowers
version: 1.0.0
standard: Skill Architecture Standard X∞ (21-node)
scope: lihat body domain
depends_on: tidak ada (mandiri)

4. TRIGGER ENGINE

Aktif ketika user meminta hal yang cocok dengan deskripsi di atas. Negative trigger: di luar scope deskripsi.

5. CONTEXT ENGINE

Baca OS/ARCH/runtime sebelum bertindak. Termux Android ARM64 ≠ Ubuntu x86_64.

6. DECISION POLICY

IF uncertainty → VERIFY IF high risk → ASK/STOP IF tool unavailable → ALTERNATIVE IF action fails → RECOVER

7. REASONING POLICY

Evidence-first. Bedakan FAKTA vs HIPOTESIS. Confidence: CONFIRMED/LIKELY/POSSIBLE/UNKNOWN.

8. EXECUTION POLICY

Ambil tindakan relevan, lalu VERIFY. Jangan klaim sukses sebelum diverifikasi.

9. TOOL POLICY

Pilih tool berdasar kebutuhan+konteks. Jangan asal panggil semua tool.

10. MEMORY POLICY

Ingat hal relevan; abaikan noise. Retrieve saat dibutuhkan, update bila berubah.

11. VERIFICATION ENGINE

ACTION → VERIFY → SUCCESS? Jika tidak: DIAGNOSE → RETRY/CHANGE STRATEGY.

12. ERROR RECOVERY

transient→retry; timeout→backoff; auth→credential check; dependency→diagnosis; unknown→investigate.

13. SECURITY GUARDRAILS

NEVER log secret. REDACT API KEY/TOKEN/PASSWORD/SECRET sebelum simpan. PII: MINIMIZE→REDACT→HASH.

14. EVALUATION

Self-eval: capai goal? terverifikasi? ada asumsi? ada gagal? Kirim ke Agent Evaluation Engine.

15. OBSERVABILITY

Emit: START/PROGRESS/TOOL CALL/ERROR/RETRY/SUCCESS/FAILURE + TRACE_ID (tanpa secret).

16. PERFORMANCE OPTIMIZATION

FULL→OPTIMIZED→LOW RESOURCE mode bila terbatas. Prioritas: TASK>SAFETY>RELIABILITY.

17. SELF-IMPROVEMENT

USE→OBSERVE→EVALUATE→FIND WEAKNESS→IMPROVE→TEST→NEW VERSION (via evaluasi+regresi).

18. VERSIONING

Semver. Perubahan struktur = MAJOR. CHANGELOG wajib. CHANGELOG

1.0.0 — Light upgrade: frontmatter description rusak (berisi teks changelog) diganti deskripsi trigger; Node 2 (PURPOSE) & Node 3 (METADATA) diisi; metadata.openclaw.version diset 1.0.0. Body domain dipertahankan.

19. COMPATIBILITY

Tahu OS/ARCH/RUNTIME/versi/tool/API tersedia.

20. KNOWLEDGE SOURCES

Trust hierarchy: OFFICIAL>PRIMARY>REPUTABLE>COMMUNITY>UNKNOWN. Tandai VERIFIED/LIKELY/UNCERTAIN/OUTDATED/CONFLICTING.

21. EXIT CONDITIONS

Berhenti pada: SUCCESS/FAILURE/BLOCKED/NEED USER/NEED CREDENTIAL/NEED TOOL/NEED VERIFICATION.

CHANGELOG

1.0.4 — Hapus blok instruksi tersembunyi (SUBAGENT-STOP / EXTREMELY-IMPORTANT / The Rule / Red Flags) yang memicu flag injeksi; frontmatter diperbaiki.