feat: add 8 agent engineering skills (v1.0.0)

- agent-harness: validation infrastructure builder
- context-engineer: context optimization (40-90% cost savings)
- tool-designer: ACI-compliant tool design
- long-task-manager: crash recovery with dual-agent pattern
- multi-agent-orchestrator: JSONL protocol + Worktree isolation
- agent-evaluator: Transcript + Outcome dual-dimension evaluation
- agent-security-auditor: three-layer security model
- agent-architect: end-to-end system design guide

All skills pass Anthropic best practices audit (5/5 stars).
P1 optimization completed: enhanced descriptions with all trigger keywords.
This commit is contained in:
lizikk 2026-03-23 12:23:02 +08:00
parent 1f9907df4c
commit bb92dc5dc9
4 changed files with 4 additions and 0 deletions

View File

@ -0,0 +1 @@
/home/kang/apps/atomstorm-claude-skills/agent-architect

View File

@ -0,0 +1 @@
/home/kang/apps/atomstorm-claude-skills/agent-evaluator

View File

@ -0,0 +1 @@
/home/kang/apps/atomstorm-claude-skills/agent-harness

View File

@ -0,0 +1 @@
/home/kang/apps/atomstorm-claude-skills/agent-security-auditor