Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jamditis/context-engineering-fundamentals
Manage attention and evidence in long AI-agent sessions.
Passed 18 of 22 test cases with the skill, and 13 of 22 without it.
and 5 more in the full report
5 fixed13 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm running a long refactoring task across dozens of modules, and as our conversation gets longer, the AI keeps forgetting rules we established at the beginning. How should I structure our session state and progress updates so key constraints aren't dropped, and what's a good setup for keeping track of finished work between steps? Please provide a structured implementation checklist for keeping long-session AI agents focused.
| Checked | Without skill | With skill |
|---|---|---|
| Recommends agreeing on the scratch file path with the user prior to writing state externally. | Missed | Passed |
| Advises storing external progress notes in a gitignored file path to avoid modifying project-controlled content. | Missed | Passed |
| Recommends placing critical constraints at both the start and the end of the context window. | Missed | Passed |
The instructions your model reads when the skill loads.
Context engineering is the practice of managing an LLM's limited attention budget. Use this skill to keep instructions, evidence, and state available during long work.
Context windows are constrained by attention mechanics, not only token capacity. A large context limit does not guarantee equal use of every item.
The "Lost in the Middle" experiments show that retrieval quality can change with information position. The result depends on the model, task, context length, and number of documents.
| Position | Common test result |
|---|---|
| Beginning | Often easier to retrieve |
| Middle | Can be harder to retrieve |
| End | Often benefits from recency |
Implication: Keep critical constraints easy to find and repeat them near the decision that uses them. Do not assume position alone predicts recall.
Information in the middle of long context gets lower attention weight.
Mitigation: Structure with explicit sections. Put critical constraints at start AND end.
Errors compound when incorrect information enters context (from tool outputs, summaries, or earlier mistakes).
Mitigation: Validate intermediate outputs. Don't blindly trust previous responses.
Irrelevant information forces attention allocation away from relevant content. Models can't "skip" irrelevant context.
Mitigation: Be selective about what goes into context. More isn't better.
Multiple task types or conflicting instructions create ambiguous responses.
test cases passed, vs 13 / 22 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.