Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jnmetacode/self-evolve
Make the agent improve with every task — review the run, distill lessons into durable memory, and reinforce what worked. Use at the end of any non-trivial task, or when the user asks the agent to "learn from this".
Passed 16 of 21 test cases with the skill, and 10 of 21 without it.
and 5 more in the full report
7 fixed10 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
We successfully verified that the memory sourced from 'redis-cluster-timeout' fixed our socket timeout during load testing when querying 'redis connection drop'. Construct the exact parameters for reinforcing this memory.
| Checked | Without skill | With skill |
|---|---|---|
| Passes 'redis connection drop' as the query parameter | Passed | Passed |
| Passes 'redis-cluster-timeout' or 'redis' as the source parameter | Missed | Passed |
The instructions your model reads when the skill loads.
An agent that doesn't learn repeats its mistakes at full price. This skill is the improvement loop: observe the run → distill the lesson → store it → reinforce what worked → recall it next time. It uses local tools (engram for memory, tracelet for observation), so the learning stays on the user's machine.
Observe what actually happened. Don't trust your memory of the run —
check it. If tracing is on (npx @jnmetacode/tracelet), look at the trace:
which tool calls failed or were retried, where the time and tokens went,
which approach was abandoned. Without a trace, review your own steps: what
did you try first that didn't work?
Distill at most 1–3 lessons. A lesson is durable knowledge that would change how you act next time, not a diary entry:
npm ci runs before codegen")Store each lesson (one fact per memory, dated, with the why):
engram_remember: "2026-06-12: deploys to staging need SSL_MODE=require —
the pooler silently drops non-SSL connections (cost us 40 min)."
(CLI: npx @jnmetacode/engram remember … via the HTTP API, or the
engram_remember MCP tool.)
Reinforce retrievals that proved right. If you recalled a memory during the task and it turned out to be the correct answer, say so — recall gets measurably better with use:
engram_reinforce: { query: "staging deploy fails", source: "deploys" }
Future similar queries will rank that source higher. Only reinforce what was verified (the fix worked, the user confirmed) — reinforcing guesses
test cases passed, vs 10 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.