When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
SkillScore96Maintained
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Coding pack
Last verified 8/14/2026
What it changes
Passed 22 of 23 test cases with the skill, and 21 of 23 without it.
Without skill91%
With skill96%
Checks it passed that the model alone missed
The response identifies the Helm values file count of 3 as outdated.
The response identifies the mapping documentation claim of `keyword` as outdated.
2 fixed20 passed either way0 still failing1 broke
Pass-rate lift
+4 pp
Tokens
-19%
Agent turns
0%
Response time
-51%
Model gemini-3.6-flashMeasured 8/14/2026v122 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
The helm values file says `replicaCount: 3`, but `kubectl get deployment` shows 5 replicas running in cluster. Document this discrepancy using the structured format.
What was checked, without and with the skill
Checked
Without skill
With skill
The response identifies 5 as the actual running replica count shown by `kubectl get deployment`.
Passed
Passed
The response identifies the Helm values file count of 3 as outdated.
Missed
Passed
case-15 · gemini-3.6-flash · 8/14/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md47 linessingle file
Map Territory
Docs, tests, diagrams, metrics, comments, and mental models are maps. Running code and actual data are the territory. When they disagree, verify territory and update the model — never force reality to match the description.
When to Use
Observed behavior contradicts a doc, test expectation, diagram, comment, dashboard, or prior assumption.
A claim about the system rests on a secondary source rather than current code or data.
Tests pass but production or manual behavior is wrong.
You are about to theorize why something happens before inspecting what happens.
A decision depends on whether a model, schema, or metric is still current.
When NOT to Use
The map is the artifact you are asked to edit (doc, diagram, spec) — that artifact is the task territory.
Same path already verified this session — reuse that observation.
Map is authoritative and generative (codegen types, derived schema) with no claimed drift.
The mismatch cannot change the decision — note and move on.
Competing causal hypotheses after territory is confirmed — switch to scientific-method.
Security exploit construction — use red-team; this skill only settles model-versus-observation.
Procedure
Name the map. State the exact representation trusted: which doc, test, metric, diagram, comment, or assumption. Quote the claim, not a paraphrase.
Name the territory check. Specify the observation that would prove or disprove the claim: code path, runtime value, query, reproduction, recent change, or live metric.
Verify source and freshness. Confirm origin of the map (author, generator, last update) and whether it could be stale relative to deploy, config, or data change. Prefer primary current sources over summaries.
Observe the territory. Read the real code path, run or instrument it, query real data, or reproduce the behavior. Do not predict from signatures or names alone.
Record the delta and update. If territory contradicts the map, territory wins for shipped behavior. Document the gap, revise the model, then decide the fix (code, map, or both). Note unmapped paths — likely next failure sites.
Stop when settled. Once the claim is confirmed or overturned with a concrete observation, stop re-checking the same path.
Use under time pressure when the situation is still changing and you must act before certainty — cycle Observe→Orient→Decide→Act on ~70% confidence, then re-observe.