try-works/role-model / .agents/skills/recursive-mode
recursive-mode
UnverifiedRepository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.
scripts/recursive-training-phase8-trigger.ps1
View on GitHub#Requires -Version 5.1
<#
.SYNOPSIS
Post-Phase 8 training trigger for recursive-mode.
.DESCRIPTION
Called by the harness immediately after Phase 8 (08-memory-impact.md) is locked.
Checks whether training should run, constructs the appropriate command, and
executes it.
.PARAMETER RepoRoot
Path to the git repository root.
.PARAMETER RunId
The run that just completed Phase 8.
.PARAMETER LlmProvider
LLM provider for extraction (default: kimi).
.PARAMETER Auto
Skip user confirmation and run training immediately.
.PARAMETER WinnerOnlyThreshold
Minimum winners for winner-only mode (default: 2).
.PARAMETER Quiet
Suppress non-error output.
.EXAMPLE
.\recursive-training-phase8-trigger.ps1 -RepoRoot . -RunId phase25 -Auto
#
>
param(
[Parameter(Mandatory)]
[string]$RepoRoot,
[Parameter(Mandatory)]
[string]$RunId,
[string]$LlmProvider = "kimi",
[switch]$Auto,
[int]$WinnerOnlyThreshold = 2,
[switch]$Quiet
)
$scriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
$pyScript = Join-Path $scriptDir "recursive-training-phase8-trigger.py"
$argsList = @("--repo-root", $RepoRoot, "--run-id", $RunId, "--llm-provider", $LlmProvider)
if ($Auto) { $argsList += "--auto" }
if ($WinnerOnlyThreshold -ne 2) { $argsList += @("--winner-only-threshold", $WinnerOnlyThreshold) }
if ($Quiet) { $argsList += "--quiet" }
& python $pyScript @argsList
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |