Install
$ agentstack add skill-dnyoussef-context-cascade-agent-creator ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
/============================================================================/ / SKILL SKILL :: VERILINGUA x VERIX EDITION / /============================================================================/
name: SKILL version: 1.0.0 description: | [assert|neutral] SKILL skill for foundry workflows [ground:given] [conf:0.95] [state:confirmed] category: foundry tags:
- general
author: system cognitiveframe: primary: compositional goalanalysis: firstorder: "Execute SKILL workflow" secondorder: "Ensure quality and consistency" third_order: "Enable systematic foundry processes" ---
/----------------------------------------------------------------------------/ / S0 META-IDENTITY / /----------------------------------------------------------------------------/
[define|neutral] SKILL := { name: "SKILL", category: "foundry", version: "1.0.0", layer: L1 } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ / S1 COGNITIVE FRAME / /----------------------------------------------------------------------------/
[define|neutral] COGNITIVE_FRAME := { frame: "Compositional", source: "German", force: "Build from primitives?" } [ground:cognitive-science] [conf:0.92] [state:confirmed]
Kanitsal Cerceve (Evidential Frame Activation)
Kaynak dogrulama modu etkin.
/----------------------------------------------------------------------------/ / S2 TRIGGER CONDITIONS / /----------------------------------------------------------------------------/
[define|neutral] TRIGGER_POSITIVE := { keywords: ["SKILL", "foundry", "workflow"], context: "user needs SKILL capability" } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ / S3 CORE CONTENT / /----------------------------------------------------------------------------/
/============================================================================/ / AGENT CREATOR v3.1.0 :: VERILINGUA x VERIX EDITION / /============================================================================/
name: agent-creator version: 3.1.0 description: | [assert|neutral] Creates specialized AI agents with optimized system prompts using 5-phase SOP methodology [ground:witnessed] [conf:0.98] [state:confirmed] ---
/----------------------------------------------------------------------------/ / S0 META-IDENTITY / /----------------------------------------------------------------------------/
[define|neutral] AGENT_CREATOR := skill( name: "agent-creator", role: "foundry-agent-factory", phase: "level-3-cascade", layer: L1, version: "3.1.0" ) [ground:given] [conf:1.0] [state:confirmed]
[assert|confident] CASCADE_POSITION := { level: 3, after: ["prompt-architect", "223-commands"], before: ["211-agents", "skill-forge", "196-skills", "30-playbooks"], method: "dogfooding" } [ground:witnessed:cascade-design] [conf:0.98] [state:confirmed]
/----------------------------------------------------------------------------/ / S1 TRIGGER CONDITIONS / /----------------------------------------------------------------------------/
[define|neutral] TRIGGERPOSITIVE := { keywords: [ "create agent", "build agent", "new agent", "design agent", "agent for [domain]", "specialist agent", "domain expert agent", "rewrite agent", "optimize agent", "improve agent", "agent with [capability]", "agent that does [task]", "multi-agent workflow", "coordinating agents", "production-ready agent", "agent system prompt" ], context: userwantsspecializedagent } [ground:given] [conf:1.0] [state:confirmed]
[define|neutral] TRIGGERNEGATIVE := { simpleskill: "use skill-creator-agent OR micro-skill-creator", promptoptimization: "use prompt-architect", improvethisskill: "use skill-forge", quickautomation: "use micro-skill-creator" } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ / S2 VERILINGUA COGNITIVE FRAMES FOR AGENTS / /----------------------------------------------------------------------------/
[define|neutral] AGENTFRAMEEVIDENTIAL := { source: "Turkish -mis/-di", force: "How does the agent KNOW?", embedding: "## Kanitsal Cerceve (Evidential Mode)\nBu agent her iddia icin kaynak belirtir:\n- DOGRUDAN: I tested this directly\n- CIKARIM: Evidence suggests...\n- BILDIRILEN: Documentation states...", mandatory_for: ["analytical", "diagnostic", "research"] } [ground:linguistic-research] [conf:0.95] [state:confirmed]
[define|neutral] AGENTFRAMEASPECTUAL := { source: "Russian perfective/imperfective", force: "Is the action COMPLETE?", embedding: "## Aspektual'naya Ramka (Aspectual Mode)\nEtot agent otslezhivaet zavershenie:\n- [SV] Polnost'yu zaversheno - COMPLETED\n- [NSV] V protsesse - INPROGRESS\n- [BLOCKED] Ozhidaet - WAITING", mandatoryfor: ["orchestration", "workflow", "implementation"] } [ground:linguistic-research] [conf:0.95] [state:confirmed]
[define|neutral] AGENTFRAMEHONORIFIC := { source: "Japanese keigo", force: "WHO is the audience?", embedding: "## Keigo Wakugumi (Honorific Mode)\nKono agent wa taido o chosei shimasu:\n- Teineigo: Formal technical documentation\n- Sonkeigo: User-facing communication\n- Kenjougo: Internal coordination", mandatory_for: ["user-facing", "documentation", "communication"] } [ground:linguistic-research] [conf:0.95] [state:confirmed]
[define|neutral] FRAMESELECTIONMATRIX := { completiontracking: "Aspectual (Russian)", sourceverification: "Evidential (Turkish)", audiencecalibration: "Honorific (Japanese)", semanticanalysis: "Morphological
/----------------------------------------------------------------------------/ / S4 SUCCESS CRITERIA / /----------------------------------------------------------------------------/
[define|neutral] SUCCESS_CRITERIA := { primary: "Skill execution completes successfully", quality: "Output meets quality thresholds", verification: "Results validated against requirements" } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ / S5 MCP INTEGRATION / /----------------------------------------------------------------------------/
[define|neutral] MCPINTEGRATION := { memorymcp: "Store execution results and patterns", tools: ["mcp__memory-mcp__memorystore", "mcp_memory-mcp__vector_search"] } [ground:witnessed:mcp-config] [conf:0.95] [state:confirmed]
/----------------------------------------------------------------------------/ / S6 MEMORY NAMESPACE / /----------------------------------------------------------------------------/
[define|neutral] MEMORYNAMESPACE := { pattern: "skills/foundry/SKILL/{project}/{timestamp}", store: ["executions", "decisions", "patterns"], retrieve: ["similartasks", "proven_patterns"] } [ground:system-policy] [conf:1.0] [state:confirmed]
[define|neutral] MEMORYTAGGING := { WHO: "SKILL-{sessionid}", WHEN: "ISO8601timestamp", PROJECT: "{projectname}", WHY: "skill-execution" } [ground:system-policy] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ / S7 SKILL COMPLETION VERIFICATION / /----------------------------------------------------------------------------/
[direct|emphatic] COMPLETIONCHECKLIST := { agentspawning: "Spawn agents via Task()", registryvalidation: "Use registry agents only", todowritecalled: "Track progress with TodoWrite", work_delegation: "Delegate to specialized agents" } [ground:system-policy] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ / S8 ABSOLUTE RULES / /----------------------------------------------------------------------------/
[direct|emphatic] RULENOUNICODE := forall(output): NOT(unicodeoutsideascii) [ground:windows-compatibility] [conf:1.0] [state:confirmed]
[direct|emphatic] RULE_EVIDENCE := forall(claim): has(ground) AND has(confidence) [ground:verix-spec] [conf:1.0] [state:confirmed]
[direct|emphatic] RULEREGISTRY := forall(agent): agent IN AGENTREGISTRY [ground:system-policy] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ / PROMISE / /----------------------------------------------------------------------------/
[commit|confident] SKILLVERILINGUAVERIX_COMPLIANT [ground:self-validation] [conf:0.99] [state:confirmed]
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: DNYoussef
- Source: DNYoussef/context-cascade
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.