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.
.recursive/memory/skills/patterns/phase8-skill-memory-promotion.md
View on GitHubType: `pattern`
Status: `CURRENT`
Scope: `How Phase 8 captures run-local skill usage and promotes only durable lessons into skill memory.`
Owns-Paths:
Watch-Paths:
- `/.recursive/RECURSIVE.md`
- `/.recursive/memory/MEMORY.md`
- `/.recursive/memory/skills/SKILLS.md`
- `/.recursive/run/`
Source-Runs:
- `none (generic repository guidance)`
Validated-At-Commit: `generic-repository-guidance`
Last-Validated: `2026-04-09T00:00:00Z`
Tags:
- `skills`
- `memory`
- `phase8`
- `promotion`
# Phase 8 Skill Memory Promotion
Skill memory should be operational, not accidental.
## First Capture It Run-Locally
Before promoting durable guidance, record run-local skill usage in `08-memory-impact.md`:
- what skills were available
- what skills were sought
- what skills were attempted or used
- what worked well
- what issues were encountered
- what future guidance changed
- what promotion candidates exist
## Then Decide What Becomes Durable
Promote only lessons that are:
- reusable across runs
- specific enough to change future planning or verification behavior
- not merely one-off environmental noise
## Keep The Boundary Honest
- Run-local observations belong in the run artifact first.
- Durable memory should contain generalized guidance, not session history.
- In reusable skill/workflow repos, do not turn current-session implementation residue into durable memory unless it has been rewritten as generic repository guidance.
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: 471k | Updated | Claude CodeCodex | Unverified | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |