Skill Claude CodeCodex
Defines and validates standard communication protocols between agents (A2A).
not rated 23
+1 4d ago A 17 tokens
Skill Claude CodeCodex
Build LLM systems from composable workflow patterns (prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer) and decide workflow vs. autonomous agent.
not rated 23
+1 4d ago A 40 tokens
Skill Claude CodeCodex
Enforce architecture layer boundaries defined in AGENTS.md — detect and fix import violations.
not rated 23
+1 4d ago A 21 tokens
agentic-patterns
100Skill Claude CodeCodex
Implements advanced AI patterns like Reflection, ReAct, Planning, and Tool Use.
not rated 23
+1 4d ago A 22 tokens
meta-optimize
101Skill Claude CodeCodex
Self-refining engine — analyze repeated failures in other skills and rewrite their prompts/logic to improve future runs.
not rated 23
+1 4d ago A 26 tokens
meta-prompting
102Skill Claude CodeCodex
Agents optimizing prompts for other agents (Chain of Thought, Tree of Thoughts).
not rated 23
+1 4d ago A 20 tokens
multi-agent-orch
103Skill Claude CodeCodex
Plans and orchestrates multi-agent swarms, defining roles, topologies, and handoffs.
not rated 23
+1 4d ago A 24 tokens
persona-selector
104Skill Claude CodeCodex
Rank/select the best Loki persona(s) per task; persona delegation, consensus voting, bounded self-refinement — cost-gated.
not rated 23
+1 4d ago A 29 tokens
self-optimize
105Skill Claude CodeCodex
Tune skill/guide/persona/model selection to the project for quality+cost; gabbe.config.json + autonomy levels + alignment.
not rated 23
+1 4d ago A 30 tokens
swarm-consensus
106Skill Claude CodeCodex
Implement voting mechanisms (majority, weighted) to resolve inter-agent conflicts.
not rated 23
+1 4d ago A 20 tokens
agent-analytics
107Skill Claude CodeCodex
Tracks key performance indicators (KPIs) for AI Agents: Token Usage, Task Duration, Loop Cycles, and Success Rate.
not rated 23
+1 4d ago A 30 tokens
audit-trail
108Skill Claude CodeCodex
Maintain append-only structured audit log of all agent and human decisions and outcomes.
not rated 23
+1 4d ago A 18 tokens
clarify
109Skill Claude CodeCodex
Generate high-quality clarifying questions for any task/step, escalating when self-estimated uncertainty is high.
not rated 23
+1 4d ago A 24 tokens
emerging-tech
110Skill Claude CodeCodex
Architecture assistance for 2026-2030 technologies (6G, Matter IoT, Vector DBs).
not rated 23
+1 4d ago A 26 tokens
Skill Claude CodeCodex
Apply empirical and measurement methods to engineering decisions with sound experiment design, honest statistical interpretation, and root-cause analysis.
not rated 23
+1 4d ago A 28 tokens
final-review
112Skill Claude CodeCodex
Expert end-of-work review — catch errors/gaps/risks and propose optimizations before declaring done.
not rated 23
+1 4d ago A 24 tokens
integrity-check
113Skill Claude CodeCodex
End-to-end 8-dimension verification — requirements through delivery, all aligned and correct.
not rated 23
+1 4d ago A 21 tokens
Skill Claude CodeCodex
Manage knowledge integration via MCP, Vector DBs, and A2A connectors.
not rated 23
+1 4d ago C 20 tokens
knowledge-gap
115Skill Claude CodeCodex
Detect unknown territory before acting — a research gate forcing authoritative verification of unknown APIs/libraries.
not rated 23
+1 4d ago A 21 tokens
preflight
116Skill Claude CodeCodex
Mandated first action — auto-check, load index summaries + memory + cost, recommend the optimal set, then clarify.
not rated 23
+1 4d ago A 27 tokens
research
117Skill Claude CodeCodex
Find authoritative answers from official docs, RFCs, standards, and academic sources — never from blogs or opinions.
not rated 23
+1 4d ago A 23 tokens
retrospective
118Skill Claude CodeCodex
Run a blameless retrospective — gather a timeline, generate insights, decide a few owned dated actions, and feed lessons into CONTINUITY.md memory.
not rated 23
+1 4d ago A 35 tokens
sdlc-checkpoint
119Skill Claude CodeCodex
Save SDLC milestone snapshot, verify phase gates, advance tracking, and tag git commit.
not rated 23
+1 4d ago A 23 tokens
self-heal
120Skill Claude CodeCodex
Autonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation.
not rated 23
+1 4d ago A 23 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: