Skip to content
Agentmart
Submit a tool

resolve

Resolve a conjecture that dream projected — confirmed or refuted, always with evidence.

Skill by EvolvingAgentsLabs

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying resolve?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/evolvingagentslabs-resolve

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Resolve a conjecture that dream projected — confirmed or refuted, always with evidence. Use when the user asks about projections, wants to record that a projected symptom happened or cannot happen, or asks for the conjecture hit rate.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/resolve

What's inside

Skill name
resolve
Description
Resolve a conjecture that dream projected — confirmed or refuted, always with evidence. Use when the user asks about projections, wants to record that a projected symptom happened or cannot happen, or asks for the conjecture hit rate.
License
Apache-2.0
Instructions
46 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /nightshift:resolve

Dream proyecta síntomas que **nadie observó**. Este comando es el otro extremo de eso:
decirle al store que uno pasó, o que no puede pasar.

Sin esto, una conjetura queda abierta para siempre y sigue enganchando igual. **Una
conjetura que nadie resuelve no es memoria, es una nota.**

Listá lo que hay para resolver y reportá la salida:

```sh
nightshift resolve
```

Si `nightshift` no está en el `PATH`, usá `"${CLAUDE_PLUGIN_ROOT}/bin/nightshift" resolve`.

Para resolver una, con su id:

```sh
nightshift resolve <id> --confirmed --evidence "lo vi pasar en …"
nightshift resolve <id> --refuted   --evidence "no puede pasar porque …"
```

Argumentos útiles: `--by "quién"` (default `human`), `--all` para ver también las
resueltas, `--json`.

## Reglas que el comando defiende, y que conviene explicarle al usuario

- **La evidencia es obligatoria en los dos sentidos.** Refutar sin motivo es olvidar con
  otro nombre; confirmar sin motivo es una explicación plausible anotada como hallazgo,
  que es justo el tipo de memoria que este proyecto dice no querer.
- **No hay un estado tibio.** `confirmed` o `refuted`. El valor de esto es que obliga a
  decidir; lo que todavía no se sabe se queda `open`, que ya es un estado.
- **Una refutada deja de engancharse** con cualquier prompt, y **no se borra**:
  `/nightshift:why <trayectoria>` la sigue mostrando con su motivo.
- **Una confirmada NO asciende.** Sigue pesando la mitad que una señal observada y se
  anuncia aparte. Que el mecanismo haya acertado no vuelve a esta sesión la que lo
  observó, y borrar esa frontera borra ADR-004 entero.

## Qué no es

**No es `verify`.** Esto registra el juicio de una persona sobre una conjetura; `verify`
(M5, ADR-002) reproduce una trayectoria contra un gate automático. Una conjetura
confirmada no vuelve verificada a la memoria que la produjo, y nada llega a `procedure`.

From EvolvingAgentsLabs/nightshift, Apache-2.0.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 28, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from EvolvingAgentsLabs

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get resolve running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying resolve?

CallGet help
Cite this page

resolve skill. Agent Mart. https://agentmart.dev/skills/evolvingagentslabs-resolve (last updated 2026-10-24)