repo-native-alignment: Skill for Claude Code

/salvage

Extract learning from a session or piece of work before restarting. The insight: code is cheap now; learning is the asset.

Salvage is the bridge from Review back to Problem Space. When drift is detected, salvage captures what was learned so you can restart clean without losing understanding.

When to Use

Invoke /salvage when:

• Work is drifting - approach has changed direction multiple times
• Approach reversed 3+ times - you're oscillating, not converging
• Scope expanding while "done" keeps fuzzing - the finish line keeps moving
• You're protecting code you've invested in - afraid to throw it away
• Starting over feels right - but you don't want to lose what you learned

Do not use when: Work is on track and converging. Salvage is for extraction before restart, not routine reflection.

The Salvage Process

Step 1: Acknowledge the State

Before extracting, name what happened:

"This session/approach is being salvaged because [reason]. The original aim was [aim]. What actually happened was [reality]."

Be direct. No judgment—just clarity.

Step 2: Extract Five Things

Work through these extraction categories. Not everything will apply; extract what's present.

1. Model Shifts (What changed your understanding?)

• What assumptions were wrong?
• What did you learn about the problem that you didn't know before?
• What would you tell yourself at the start of this work?

"I thought X, but actually Y."

2. Guardrails (Constraints discovered the hard way)

• What boundaries should have been explicit from the start?
• What "don't do this" rules emerged?
• What edge cases bit you?

Format as explicit constraints:

Guardrail: [boundary]
Reason: [why this matters]
Trigger: [when to revisit this constraint]

3. Missing Context (What would have helped upfront?)

• What questions should have been asked at the start?
• What existing code/patterns should have been found first?
• What documentation was missing or would have prevented this?