aced

Plugin aced from marketplace cyberplace in cyberuni/cyberplace. Commands read from the repo's manifest — 6 days ago.

Skills (25)

• aced-architect-impl

  By name only

• aced-builder-impl

  By name only

• aced-builder-spec

  By name only

• aced-fit

  By name only

• aced-impl-producer

  By name only

• add-scenario

  Adds a new scenario to an ACED .feature suite — from a real failure, a production edge case, or a gap the user noticed.

• bench

  By name only

• check-freshness

  By name only

• compare

  Compares two versions of an agent configuration to detect regressions or confirm improvements before committing a change.

• contribute-skill

  Contributes local improvements to an installed skill back to its source repo via PR.

• define-agent

  Creates or improves an agent definition — a named, reusable role that can be delegated to as a subagent, loaded in-context as a persona, or both. Trigger on "create an agent", "write a conductor", "make an agent definition", "define a persona", "build a dual-mode agent", or "add an invokable agent".

• define-command

  Creates or improves a command — a user-invoked-only slash workflow (`/name`) that never auto-triggers from the model. Trigger on "create a command", "add a slash command", "make a /deploy command", "add a user-only workflow", "convert this skill to a command", or "stop this skill from auto-triggerin

• define-skill

  Creates, scaffolds, or formalizes a workflow skill — a process, tool-based, or standard SKILL.md — from scratch or from an existing ad-hoc workflow. Use when the user asks for one — "create a skill", "write a skill for X", "I want a skill that…", "turn this workflow into a skill", "help me build thi

• extract-situation

  By name only

• improve-skill

  Audit, improve, or write a SKILL.md — check description trigger coverage, structure, security, and agentskills.io compliance. Use when reviewing or creating a skill for Claude Code, Cursor, Codex, Copilot CLI, or any agentskills-compatible runtime, even if the user says "my skill isn't triggering",

• improve

  Improves an existing agent configuration — a skill, subagent, command, or AGENTS.md section — by diagnosing failing ACED evals or by general review against fit and quality bars. Trigger on "improve this skill", "make this agent better", "why does this config keep failing", or "review this AGENTS.md

• init-aced

  Registers ACED as the SDD plugin for agent-configuration domains — writes an aced role-map entry to .agents/universal-plugin.json so the conductor resolves the ACED production-chain roles for skills, subagents, commands, and AGENTS.md sections.

• list-skills

  By name only

• manage-model-runners

  By name only

• manage-skill-dirs

  By name only

• manage

  Handles manage-level (non-mission) ACED work — inspecting or maintaining the agent-config tooling ACED evaluates, such as "set up the per-model runner agents", "list the model runners", "list the installed skills", or "validate/repair the repo-private skills". Routes to the matching engine; it does

• repair-private-skills

  By name only

• report

  Summarizes the health of all ACED eval suites project-wide — pass rates, trends, and which agent configurations need attention.

• run

  Runs ACED evals to score agent configuration behavior against its frozen .feature suite. Use after editing a skill, AGENTS.md section, subagent, or command.

• skillify

  Generalizes what the current session actually did into a reusable SKILL.md — "skillify this", "turn what we just did into a skill", "make this reusable". Not for scaffolding a skill from scratch (define-skill), extracting the session into an agent or persona (define-agent), a reference-only rule set

Subagents (4)

• aced-case-judge

  Internal subagent for ACED. Produces a blind simulation of agent behavior for one scenario and scores it against that scenario's rubric, emitting a score per named dimension. Invoked by aced-impl-judge (the impl-judge) and the run/compare reporting skills — not triggered by users directly.

• aced-impl-judge

  Partial Skill: invoke by name only — the ACED impl-judge for agent-configuration domains. Runs the frozen .feature suite over N runs — reading each @rubric scenario's inline rubric and each @trigger Scenario Outline's Examples — and collapses score-vs-threshold to a boolean per frozen scenario. Spaw

• aced-scenario-writer

  Partial Skill: invoke by name only — the ACED spec-producer for agent-configuration domains. Writes the spec.md body and the .feature (boolean scenarios, @rubric for graded behavior, @trigger Scenario Outline for activation, rubric authored inline) for a skill, subagent, command, or AGENTS.md sectio

• aced-spec-validator

  Partial Skill: invoke by name only — the ACED spec-judge. Judges an agent-config .feature against the agent-scenario criteria (trigger context, near-miss balance, rule coverage, edge cases). Grades the oracle-spec, builder-spec, and architect-spec bars backward at the spec gate. Spawned cold by the

Similar plugins