Claude Code plugin marketplace

Claude Second Brain

Most Claude Code skill repos are catalogs. This one is a system.

Every skill knows what comes after it. Judgment is protected from sycophancy by hard rules rather than good intentions. Ambiguous requests get decoded before a single file is touched. The graph that connects all of it is maintained by one of its own nodes.

Install
/plugin marketplace add NickAme03/claude-second-brain
/plugin install second-brain-skills@claude-second-brain

The difference is structural

A catalog is a folder you have to remember to open. A system routes you through itself. The distinction is not stylistic: it decides whether a session ends somewhere useful or ends nowhere.

A catalog
  • Isolated prompts you must remember to invoke
  • Nothing tells you what to do next
  • Quality depends on the model's mood that day
  • Grows by accumulation: more files, same structure
  • Dead entries are invisible until someone trips on one
A system
  • Every skill ends by naming 2 to 4 concrete next steps
  • Choices derive from what the run actually produced
  • Honesty enforced by prohibitions, not by tone
  • Grows by connection: new skills enter the graph
  • Missing links are tracked as a to-do list, by design

No session ends in a dead end

The rule every skill obeys: finish by offering choosable consequences derived from the actual output, condition first and tool second, with an explicit exit. When a destination does not exist yet, it is recorded rather than silently dropped.

01
Decode The request is classified before anything is touched. Action, judgment, thinking aloud, study, venting.
02
Act The chosen reading is declared out loud, so a wrong guess costs one sentence instead of an hour.
03
Hand off Two to four next steps, each tied to a condition the run actually met. Plus "or stop here".
04
Or record a gray link A handoff whose destination does not exist yet becomes a tracked gap. The system's natural backlog.

Three admission gates

Every skill in this repo was admitted only if it passed all three.

01

Self-management

The system works without constant intervention. Skills update themselves, registries track state, nothing depends on you remembering.

02

Biological organicity

Skills are organs. They are born, they connect, they specialize. An isolated skill is dead tissue.

03

Inertia

Every addition must increase the system's capacity to grow on its own, not just add one more file to a pile.

The 14 skills

They work independently. They work better together, because the handoff sections reference each other. Start with the first two: they are the immune system.

decodifica-intentostart here

Decodes every ambiguous request before acting. Classifies intent, decides whether to ask or infer, and always declares the reading it chose. The most expensive moment of a session is an action launched from a misread request.

anti-compiacimentostart here

Total ban on complacent lying. No unverified confirmations, no inflated praise, no minimized problems, no position changes under pressure without new facts. Every judgment split into what works and what does not, labeled as verified fact, opinion, or hypothesis.

verifica-artefattiartifact counterpart

Before any text reaches third parties, every named file, script, test or dataset is resolved against what the reader can reach. Three outcomes only: reachable, existing but unreachable (marked as a gray link, with the reason), or removed. Measures answer the other half of the rule: the command that regenerates them, or an explicit label saying they cannot be reproduced. A finished artifact that lives outside the repository is, for the reader, indistinguishable from one that never existed.

skill-linker

Turns every skill into a graph node: a standard "next skills" section, an edge registry, one skill per update. The reason this repo is a system and not a folder.

risparmio-token

Token economy in three modes: operating rules during work, setup audit across CLAUDE.md and MCP and skills, and design of token-efficient artifacts.

orchestratore-pianifica

Turns a concrete objective into an executable task sequence in PIANO.md.

orchestratore-esegui

Executes tasks from the plan, resuming exactly where the last session stopped.

orchestratore-ripianifica

Updates a plan incrementally when reality diverges. Never rewrites from scratch.

orchestratore-cruscotto

Read-only control tower over all active plans. Answers one question: where is the human actually needed?

percorsi-di-sviluppo

Turns vague ambitions into 2 to 4 comparable paths built on a real profile. Each with structural cons that do not disappear with effort, the first three steps, and an explicit abandonment signal.

analista-progetti

Reviews a project, or a whole portfolio read as a network, the way whoever judges it next would. Three lenses, seven scored dimensions, ruthless prioritization, every criticism shipped with a fix.

cacciatore-skill

The procurement organ. Hunts and evaluates new skills against the three gates. Reports only, never installs.

cacciatore-citazioni-apa

Finds real, verifiable academic citations through PubMed and Scholar, formats APA 7, extracts verbatim quotes. Absolute fabrication ban.

bussola

Cold-start dispatcher for the "I don't even know where to begin" moment. Returns one direction plus a first concrete move, then hands off. A compass, not a planner.

Four patterns worth stealing

Even if you never run a single skill from this repo, these transfer to any Claude Code setup. Take them and leave the rest.

Choosable consequences over dead ends

End every process with 2 to 4 options derived from actual outputs, not from a generic menu. "If the report reveals stalled projects, go to project management." Condition first, tool second, and always an explicit way to stop.

Decode before acting

A permanent memory rule points at the decoding skill, which guarantees the hook fires even when the ambiguous request resembles no skill description at all. Memory guarantees the trigger; the skill contains the method. Splitting those two is the whole trick.

Anti-sycophancy as architecture, not intention

"Be honest" does not survive contact with a user who insists. Hard prohibitions with a declared rationale do, and the rationale matters: insistence is data about mood, not about the object.

Skills that maintain skills

The graph maintainer is itself a skill, with non-negotiable rules: one skill at a time, diff before writing, registry updated in the same task. A system that cannot repair itself is documentation, not infrastructure.

Nota per chi legge in italiano. Le skill sono nate in italiano e in italiano restano: sono il sistema operativo reale di un vault Obsidian in uso quotidiano, non un esercizio. Il metodo è indipendente dalla lingua e sopravvive alla traduzione. Se lavori in italiano con Claude Code funzionano così come sono.