surendranb Your Skill Name
State the outcome this skill produces and the method it follows — in one paragraph. A skill is a drilled capability, not a prompt: same disciplined behavior every run.
Method
- Measure first. Gather the real state before deciding anything.
- Find the constraint. Diagnose the one binding bottleneck; ignore symptoms.
- Rank fixes by impact divided by (cost plus risk). Cheapest reversible win first.
- Propose, get approval, act. Never take a destructive step without a shown, approved list.
- Re-measure and stop when the objective is met.
Thresholds / rules
List the concrete numbers or rules the agent applies, and why each is the threshold (rationale, not just the rule).
Safety contract
- Read-only by default; name exactly what (if anything) changes state.
- No deletion/uninstall/reconfig without the user approving a specific list.
- Never touch the user's own work or managed configuration without explicit confirmation.
- Make changes reversible where possible; report outcomes faithfully.