convez.ai
SkillAutomaçãoIntermediário
Roni-quant

Skill Radar

Roni-quant/skill-radar

Invocação inteligente de skills com zero falsos positivos

Ver no GitHub
InicialPluginScore · de 0 a 100

Sistema de triagem orientado por sinais para invocar skills no Claude Code apenas quando necessário. Reduz falsos positivos ao usar uma taxonomia explícita de gatilhos, evitando narração forçada e mantendo execução direta para tarefas simples.

Instalação

$npx convez-ai Roni-quant/skill-radar

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
57%
Último commit
há 6 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Automação de fluxos de desenvolvimento sem overhead de skills desnecessárias
  • Edição de arquivos simples sem narração ou preamble forçado
  • Resolução de bugs com roteamento automático para debugging sistemático

Veredito

Skill sólida que resolve um problema real: invoke skills apenas quando faz sentido, não por padrão. Implementação clara com triagem baseada em gatilhos explícitos, ideal para devs que querem eficiência sem ruído.

README

A tradução para o português deste README ainda está na fila.

skill-radar

Trigger-driven skill invocation for Claude Code. Fewer false positives, no forced narration, subagent-safe.

A lean alternative to using-superpowers — fire skills on signal, not on every keystroke.

Version Claude Code plugin License: MIT GitHub stars PRs welcome

What you get

  • Explicit Trigger Taxonomy — skills fire on real signals, not "1% chance → invoke."
  • No-skill list — single-file edits, lookups, and trivial fixes stay direct.
  • Mode-aware announce — silent in terse/caveman modes; one-line for heavyweight skills only.
  • Subagent priority injection — re-states the user > skills > default hierarchy in dispatched prompts (closes obra/superpowers#237).

Why

  • Triage, not paranoia. Upstream using-superpowers enforces "1% chance → invoke." That's a false-positive engine — see "The Controllability Problem" for the full case. skill-radar swaps it for an explicit Trigger Taxonomy.
  • Silent on noise. Single-file edits, lookups, status checks: no skill, no narration, no preamble.
  • Mode-aware. Terse / caveman / quiet workflows skip the forced Announce: Using X line.
  • Subagent-safe. Re-states the priority hierarchy in dispatched prompts to close the obra/superpowers#237 injection gap.

Install

Plugin marketplace (recommended)

/plugin marketplace add Roni-quant/skill-radar
/plugin install skill-radar@skill-radar-marketplace

Manual (Claude Code)

git clone https://github.com/Roni-quant/skill-radar ~/.claude/skills-src/skill-radar
ln -s ~/.claude/skills-src/skill-radar/skills/skill-radar ~/.claude/skills/skill-radar

Codex / Gemini install paths are tracked for v0.2 — see Roadmap.

Try it

Once installed, send any of these to Claude Code and watch what skill-radar decides:

You sayskill-radar does
Build a CSV export feature for the trades table.Matches "build" → invokes brainstorming → writing-plans.
Fix the off-by-one in line 42.Matches "fix" → invokes systematic-debugging.
Rename decision_id to trade_id in trades.py.No match → direct edit. No skill, no narration.

That's the whole product. Three lines of input → three different routing decisions, no over-firing, no forced preamble.

How it works

Internally, every user message goes through this loop:

  1. User sends a message.
  2. skill-radar matches the message against its Trigger Taxonomy.
  3. Match → invoke the indicated skill, then act.
  4. No match → act direct. No skill load, no announcement.
  5. If an invoked skill turns out to be a wrong fit mid-task → say so once, abort, continue direct.
  6. Heavyweight rigid skills (TDD, debugging) get a one-line announce; everything else stays silent in terse modes.
  7. Subagents inherit a re-stated priority hierarchy in their dispatch prompt.

For full transcripts of each routing decision in real sessions, see Examples.

Comparison

Dimensionusing-superpowersskill-radar
Trigger rule"1% chance → invoke"Explicit taxonomy match
No-skill casesImplicit / discouragedExplicit list
Mode awarenessForced narrationRespects terse/caveman
SKILL.md size~117 lines~50 lines
Subagent injectionDocumented gap (#237)Re-states priority
Description styleWorkflow summary riskTriggers only

Philosophy

  • Triage > paranoia. Most messages don't need a workflow.
  • Skills earn invocation. Loading a skill is a context cost.
  • Description bloat = drift. Triggers in description; steps in body.
  • Subagents need explicit priority. Re-state the hierarchy on dispatch.

Full discussion in docs/philosophy.md.

Examples

Compatibility

Coexistence: skill-radar is a drop-in alternative to upstream using-superpowers, not a replacement that breaks it. Both can be installed simultaneously — pick one as the active triage layer in your global CLAUDE.md.

To prefer skill-radar globally, add to your ~/.claude/CLAUDE.md:

## Skill triage
Use `skill-radar` for skill invocation decisions. Do not invoke `using-superpowers` simultaneously.

Roadmap

See ROADMAP.md for v0.2, v0.3, v1.0 plans and out-of-scope notes.

Support

Questions, bug reports, taxonomy gaps: open an issue.

Contributing

See CONTRIBUTING.md. Short version: edits to Trigger Taxonomy require a new pressure test.

Credits

License

MIT — see LICENSE.

Ver o original no GitHub

Bom para

Relacionados