Master controller and entry point for the skills tree. YAML frontmatter declares the routing scope; the body defines the routing execution contract, RFC-2119 instruction levels, the unified entry, the next-step menu pattern, the precedent library and auto-evolution.
Chinese edition of RULES.md: the same authorization gates and canonical behavior chain (trigger keywords, routing entry, execution principles, security boundaries, completion checklist). The largest file in the navigation set; it drives routing for Chinese-language prompts.
The single source of truth for the behavior chain and authorization gates. Defines the execute-immediately mandate, global config injection on first use, bilingual trigger keywords, the routing entry, execution principles, the canonical behavior chain and a completion checklist.
Root-level file that Claude Code auto-loads. Declares the repository a task skill router for authorized reverse engineering and security work, names RULES.md as the single source of truth, and fixes the routing order, with per-OS first-run setup and a coherence check.
Guide for adding a new skill module to the pack. Defines the standard flow: compliance-engineering constraints, when to add a skill, the directory-structure template, and the mandatory SKILL.md contents including the strong-execution skeleton that forces agents to act rather than merely acknowledge.
Keep a Changelog / SemVer changelog. Documents the 1.0.0 release (2026-07-18): the ops/combat-contract layer, PRIMARY routing and case tooling, core skills and localization, plus an Unreleased section with Fixed, Security, Added and Removed changes.
Navigation across the markdown files of zhaoxuya520/reverse-skill with measured metrics: 402 .md files, 83 SKILL.md, all in git mode 100644. Documentation is split by audience — 46 KB for humans, 157 KB for agents. Covers the routing chain and three license zones (MIT / GPL-3.0 / third-party MIT).
Master controller and entry point for the skills tree. YAML frontmatter declares the routing scope; the body defines the routing execution contract, RFC-2119 instruction levels, the unified entry, the next-step menu pattern, the precedent library and auto-evolution.
Chinese edition of RULES.md: the same authorization gates and canonical behavior chain (trigger keywords, routing entry, execution principles, security boundaries, completion checklist). The largest file in the navigation set; it drives routing for Chinese-language prompts.
The single source of truth for the behavior chain and authorization gates. Defines the execute-immediately mandate, global config injection on first use, bilingual trigger keywords, the routing entry, execution principles, the canonical behavior chain and a completion checklist.
Root-level file that Claude Code auto-loads. Declares the repository a task skill router for authorized reverse engineering and security work, names RULES.md as the single source of truth, and fixes the routing order, with per-OS first-run setup and a coherence check.
Guide for adding a new skill module to the pack. Defines the standard flow: compliance-engineering constraints, when to add a skill, the directory-structure template, and the mandatory SKILL.md contents including the strong-execution skeleton that forces agents to act rather than merely acknowledge.
Keep a Changelog / SemVer changelog. Documents the 1.0.0 release (2026-07-18): the ops/combat-contract layer, PRIMARY routing and case tooling, core skills and localization, plus an Unreleased section with Fixed, Security, Added and Removed changes.
Navigation across the markdown files of zhaoxuya520/reverse-skill with measured metrics: 402 .md files, 83 SKILL.md, all in git mode 100644. Documentation is split by audience — 46 KB for humans, 157 KB for agents. Covers the routing chain and three license zones (MIT / GPL-3.0 / third-party MIT).