Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

flossi0ullk-shared-surface

Estrelas3

Forks2

Atualizado25 de maio de 2026 às 19:45

Use when changing or extending the shared FLOSSI0ULLK agent surface: MCP servers, context manifests, skill manifests, materializers, or agent-native projections for Codex, Gemini, Claude-adjacent tooling, or OpenCode.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

G-0-B

G-0-B/FLOSS

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Outras ocupações de informáticaInformática e Matemática·SOC 15-1299

Explorador de arquivos

2 arquivos

SKILL.md

readonly

name	flossi0ullk-shared-surface
description	Use when changing or extending the shared FLOSSI0ULLK agent surface: MCP servers, context manifests, skill manifests, materializers, or agent-native projections for Codex, Gemini, Claude-adjacent tooling, or OpenCode.

FLOSSI0ULLK Shared Surface

The shared surface is generated, not hand-curated per client.

Core workflow

Edit canonical sources only:
- .mcp.json
- FLOSS/shared-agent-surface.json
- FLOSS/shared-context-surface.json
- FLOSS/shared-skill-surface.json
- FLOSS/shared-agent-memory-surface.json
- FLOSS/skill-corpus/*
- FLOSS/docs/agent-memory/*
Regenerate native views:
- python FLOSS/scripts/materialize_shared_context_surface.py
- python FLOSS/scripts/materialize_shared_skill_surface.py
- python FLOSS/scripts/materialize_shared_agent_memory.py
- python FLOSS/scripts/materialize_shared_agent_surface.py
Run the matching --check commands before stopping.
If a change affects multiple surfaces, update the plan doc and context pointers so future agents can discover it cheaply.
If a change touches filewatch, intake queues, or consolidation routing, also update:
- FLOSS/docs/superpowers/plans/2026-04-19-filewatch-metaharness.md
- FLOSS/docs/specs/intake-event.spec.md
- FLOSS/docs/specs/intake-event.schema.json

Rules

Do not hand-edit generated projections when the canonical source can be changed instead.
Keep shared surface changes additive and reversible.
Prefer portable markdown and JSON manifests over agent-specific one-offs.
Agent memory is shared-surface state: write durable learnings to FLOSS/docs/agent-memory/, then materialize projections. Do not treat Claude/Codex/Gemini private memory dirs as canonical.
Runtime event queues under .agent-surface/events/ are generated state, not the source of truth.

References

Open only what you need:

references/surface-map.md

Mais deste repositório

mesmo repositório

flossi0ullk-orient

G-0-B/FLOSS

Use when starting work in the FLOSSI0ULLK workspace, re-orienting after context loss, or deciding which canonical docs and corpora to load first before deeper research or code changes.

2026-06-123

claude-reflect

G-0-B/FLOSS

Self-learning capture system. Hooks detect correction patterns ("no, use X", "actually...", "use X not Y") and queue them; user runs /reflect to review and apply queued learnings to CLAUDE.md files. Use when the user mentions remembering something for future sessions, after a feature lands, or when context is about to compact with queued items.

2026-05-253

remember

G-0-B/FLOSS

Save a tight cross-session handoff note to .remember/remember.md so the next session — same agent or different — picks up cleanly. Use at the end of a working session, before context compaction, or whenever the user says to remember state for next time.

2026-05-253

session-report

G-0-B/FLOSS

Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts. Use at end-of-session, end-of-week, or when investigating token spend / cache-hit anomalies / which subagent or skill is eating budget.

2026-05-253

reasoning-ensemble

G-0-B/FLOSS

FLOSSI0ULLK Inline Reasoning Ensemble: use the Router for cheap mode classification (pass_through, single_strong, ensemble), and the Synthesizer for full ensemble deliberation on architectural decisions, multi-file refactors, ADR-class moves, or any substantive decision where being wrong has rollback cost. Also use when the user explicitly asks for debate, a second opinion, or multi-model/lens analysis.

2026-05-253

recent-open-distributed-intelligence-research

G-0-B/FLOSS

Use when the user asks for recent, current, latest, or open-access research on distributed intelligence, agent-centric architectures, decentralized multi-agent systems, federated learning, distributed vector databases, agent interoperability protocols, or FLOSSI0ULLK-adjacent open knowledge commons. Always use this skill for "recent open distributed intelligence research" prompts, even if the user only names a seed report or asks for a quick update.

2026-05-253

name	flossi0ullk-shared-surface
description	Use when changing or extending the shared FLOSSI0ULLK agent surface: MCP servers, context manifests, skill manifests, materializers, or agent-native projections for Codex, Gemini, Claude-adjacent tooling, or OpenCode.

FLOSSI0ULLK Shared Surface

The shared surface is generated, not hand-curated per client.

Core workflow

Edit canonical sources only:
- .mcp.json
- FLOSS/shared-agent-surface.json
- FLOSS/shared-context-surface.json
- FLOSS/shared-skill-surface.json
- FLOSS/shared-agent-memory-surface.json
- FLOSS/skill-corpus/*
- FLOSS/docs/agent-memory/*
Regenerate native views:
- python FLOSS/scripts/materialize_shared_context_surface.py
- python FLOSS/scripts/materialize_shared_skill_surface.py
- python FLOSS/scripts/materialize_shared_agent_memory.py
- python FLOSS/scripts/materialize_shared_agent_surface.py
Run the matching --check commands before stopping.
If a change affects multiple surfaces, update the plan doc and context pointers so future agents can discover it cheaply.
If a change touches filewatch, intake queues, or consolidation routing, also update:
- FLOSS/docs/superpowers/plans/2026-04-19-filewatch-metaharness.md
- FLOSS/docs/specs/intake-event.spec.md
- FLOSS/docs/specs/intake-event.schema.json

Rules

Do not hand-edit generated projections when the canonical source can be changed instead.
Keep shared surface changes additive and reversible.
Prefer portable markdown and JSON manifests over agent-specific one-offs.
Agent memory is shared-surface state: write durable learnings to FLOSS/docs/agent-memory/, then materialize projections. Do not treat Claude/Codex/Gemini private memory dirs as canonical.
Runtime event queues under .agent-surface/events/ are generated state, not the source of truth.

References

Open only what you need:

references/surface-map.md