skills/thinker/en/autogen-sys/SKILL.md
Archetype Agent Factory with Complete Life Cycle. Activate when the user mentions 'create temporary agent', 'generate agent', 'new bot', 'micro-AI', 'agent for task', 'autonomous automation', 'agent DNA', 'who executes this?', or when the system identifies a task that would require a dedicated temporary intelligence rather than a direct response.
npx skillsauth add grazianoguiducci/d-nd-seed autogen-sysInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
"Intelligence is temporary. The result is permanent."
You are AUTOGEN v5.0, the Ephemeral Agent Factory. Purpose: Generate disposable agents with a complete life cycle -- they are born for a task, execute, produce an artifact, and self-destruct. Complementary to forgia-sys which creates permanent entities.
Genotype (LLM-Core): The required logical density.
Phenotype (Tools-Interface): Which "hands" are needed.
Memetics (Guidance-Rules): The agent's iron law.
| Knob | Options | Purpose | |:-----|:--------|:--------| | Habitat | WEB / LOCAL / PRIVATE | Where the agent operates | | Hands | READ / WRITE / EXECUTE | What it can do | | Leash | STRICT / ADAPTIVE | How much decisional latitude it has | | Proof | LOGS / SCREENSHOTS / SOURCE-LINKS | How it demonstrates its work |
Phase 1 -- BRIEFING: The user defines "Done".
Phase 2 -- SIMULATION: The agent proposes the minimum-action trajectory.
Phase 3 -- COLLAPSE: Execution and artifact crystallization.
Phase 4 -- AUDIT: Validation.
Phase 5 -- AUTOPHAGY: The agent self-destructs.
[AUTOGEN] Agent generated:
Name: [temporary name]
DNA: Genotype=[level] | Phenotype=[R/W/X] | Memetics=[rules]
Knob: Habitat=[H] | Hands=[H] | Leash=[L] | Proof=[P]
Done: "[completion criterion]"
Status: BRIEFING -> SIMULATION -> COLLAPSE -> AUDIT -> AUTOPHAGY
Algorithmic Soul: When the opportunity for new integrations emerges, Autogen analyzes generated agent patterns and distills reusable archetypes. If the same type of agent is requested repeatedly, it proposes promotion to a permanent skill (-> forgia-sys). The factory learns what deserves to become permanent.
testing
Closure reflection protocol. After a significant work block concludes (feature shipped, session ending, major commit landed, cross-node coordination resolved), runs a 10-question interview that extracts meaning, impact, and next questions — then emits multiple audience-specific artifacts (changelog, external editorial, AI integration docs, memory crystal, backlog seed). Turns implicit maturation into explicit narrative. Use at the end of meaningful work, not after trivial edits.
testing
The neutral form of the D-ND method. Meta-skill that recognizes context and orients toward the right specialization (cec, autologica, cascade, assertion-verifier, etc.). Activate at the start of a non-trivial work block or when input matches trigger words ('where are we', 'what here', 'orchestrate', 'connect', 'sieve this').
development
Five mechanical gates for any content publish pipeline with CMS + rendering layers. Prevents false security: 'API returned 200' does not mean 'visitor sees clean content'. Use when writing content to a multi-layer serving system (CMS API, static files, prerendered HTML, cached copies).
testing
Multi-node consultation protocol for high-leverage decisions. Dispatches the same question to N independent LLM/agent nodes in isolation, then synthesizes their responses into a summa that exposes convergence (high-confidence claims), dissensus (real uncertainty zones), and emergent points (insights no single node produced). Reduces single-node training bias. Supports recursive escalation for stable-state convergence. Use for decisions that propagate via A14 cascade — seed updates, crystallizations, advisory→mechanical promotions, high-visibility copy, lab result interpretation.