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/usage/skill-discovery-and-evaluation.md
View on GitHubType: `pattern`
Status: `CURRENT`
Scope: `How recursive-mode runs should discover, evaluate, and record external skills or missing capabilities.`
Owns-Paths:
Watch-Paths:
- `/.recursive/RECURSIVE.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`
- `discovery`
- `find-skills`
- `capability`
# Skill Discovery And Evaluation
Use this guidance when a run needs a specialized capability that is not already available.
## Preferred Order
1. Use the `find-skills` skill if it is already installed.
2. Otherwise use the Skills CLI directly.
3. If nothing suitable exists, proceed with built-in capability and record that no suitable external skill was available.
## Useful Commands
- `npx skills find <query>`
- `npx skills add <package-or-repo>`
- `npx skills add <package-or-repo> --skill <skill-name>`
- `npx skills check`
- `npx skills update`
## Evaluation Rules
- Prefer skills from reputable publishers or organizations.
- Prefer higher install counts when the skills are otherwise comparable.
- Check upstream repository quality before recommending or installing a skill.
- Do not treat search results as proof of quality; verify source and documentation first.
## Phase 8 Recording
If a run materially used skill discovery, capture it in `08-memory-impact.md` under:
- `## Run-Local Skill Usage Capture`
- `## Skill Memory Promotion Review`
Promote only durable, reusable conclusions into skill memory. Leave one-off session notes in the run artifact instead of turning them into durable 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 | 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 |