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/SKILLS.md
View on GitHub## Skill Memory Router
This file routes durable skill and capability knowledge for the repository.
It summarizes what skills were available, what was attempted, what worked, what failed, and how future runs should use those skills.
Use the subfolders for durable Markdown-only skill memory:
- `availability/` - environment-specific skill availability and capability probe notes
- `usage/` - stable usage guidance and fit for specific skills
- `issues/` - recurring skill failures, limitations, or confusing behavior
- `patterns/` - reusable multi-skill operating patterns and delegation playbooks
Keep this file concise. Link to child docs instead of duplicating them.
## Retrieval Hints
- If the run may use delegated review, subagents, or review bundles:
- read this router
- read only the most relevant skill-memory docs that are actually present for the current environment and workflow
- If the run may need specialized external capability:
- prefer the `find-skills` skill when available
- otherwise use the Skills CLI directly and treat discovered packages as candidates until quality is checked
- If the run changes the smoke harness or cross-toolchain behavior:
- read the most relevant availability/usage notes if any have been intentionally promoted into skill memory
- In Phase 8, promote durable skill lessons into one of these shards:
- `availability/` for capability probes and environment constraints
- `usage/` for stable fit/use guidance
- `issues/` for recurring failure modes
- `patterns/` for reusable operating playbooks
- Before promoting anything durable, capture run-local skill usage in the Phase 8 artifact:
- what skills were available
- what skills were sought
- what skills were attempted or used
- what worked well or poorly
- what future guidance should change
## Current Docs
- `/.recursive/memory/skills/usage/skill-discovery-and-evaluation.md`
- `/.recursive/memory/skills/patterns/delegated-verification-and-refresh.md`
- `/.recursive/memory/skills/patterns/phase8-skill-memory-promotion.md`
- Add child docs here only when they are intentionally promoted as reusable repository guidance.
<!-- RECURSIVE-MODE-MEMORY:START -->
## Skill Memory Router
This file routes durable skill and capability knowledge for the repository.
It summarizes what skills were available, what was attempted, what worked, what failed, and how future runs should use those skills.
Use the subfolders for durable Markdown-only skill memory:
- `availability/` - environment-specific skill availability and capability probe notes
- `usage/` - stable usage guidance and fit for specific skills
- `issues/` - recurring skill failures, limitations, or confusing behavior
- `patterns/` - reusable multi-skill operating patterns and delegation playbooks
Keep this file concise. Link to child docs instead of duplicating them.
## Retrieval Hints
- If the run may use delegated review, subagents, or review bundles:
- read this router
- read only the most relevant skill-memory docs that are actually present for the current environment and workflow
- If the run may need specialized external capability:
- prefer the `find-skills` skill when available
- otherwise use the Skills CLI directly and treat discovered packages as candidates until quality is checked
- If the run changes the smoke harness or cross-toolchain behavior:
- read the most relevant availability/usage notes if any have been intentionally promoted into skill memory
- In Phase 8, promote durable skill lessons into one of these shards:
- `availability/` for capability probes and environment constraints
- `usage/` for stable fit/use guidance
- `issues/` for recurring failure modes
- `patterns/` for reusable operating playbooks
- Before promoting anything durable, capture run-local skill usage in the Phase 8 artifact:
- what skills were available
- what skills were sought
- what skills were attempted or used
- what worked well or poorly
- what future guidance should change
## Current Docs
- `/.recursive/memory/skills/usage/skill-discovery-and-evaluation.md`
- `/.recursive/memory/skills/patterns/delegated-verification-and-refresh.md`
- `/.recursive/memory/skills/patterns/phase8-skill-memory-promotion.md`
- Add child docs here only when they are intentionally promoted as reusable repository guidance.
<!-- RECURSIVE-MODE-MEMORY:END -->
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 | 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: 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 |