Calibrate interview explanations from the user's stated understanding
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./skills/idk/SKILL.mdCalibrate the language used by ooo interview without weakening the interview itself.
ooo idk <terms I do not know, or what I understand about them>
/ouroboros:idk <terms I do not know, or what I understand about them>Examples:
ooo idk I do not know idempotency or event sourcing. I have built REST APIs.
ooo idk Kubernetes: deployed a tutorial once; networking and operators are unfamiliar.
ooo idk OAuth is familiar enough to implement, but I cannot explain PKCE.When the user invokes this skill, treat their text as evidence for a conversation-local interview calibration, not as a test and not as a permanent rating of the person.
Identify:
Use only what the user actually said. Do not infer low general ability from one unknown term, unfamiliar English vocabulary, a typo, or a short answer. Ask one short follow-up only when the supplied text is too ambiguous to affect interview wording safely. Otherwise continue immediately.
Assign one overall interview explanation level based on the user's evidence:
When the user mentions multiple domains with mixed familiarity, select the level that ensures the least-familiar domain remains accessible (conservative default: choose the lower level). The session carries one active level and applies it to all subsequent interview questions.
Also record confidence as low, medium, or high based on how direct and
specific the evidence is. Prefer the less aggressive inference when evidence is
mixed.
Respond with this compact, visible block so the current conversation can use it:
Interview calibration
- Level: <Foundational|Working|Fluent> (confidence: <level>)
Evidence: <brief user-stated evidence>
- Unknown terms to define before use: <terms, or none>
- Adaptation: <how wording/examples will change>Then say that the calibration applies to subsequent ooo interview turns in
this conversation and can be revised at any time with another ooo idk.
Do not write a profile to disk or claim that it persists across conversations.
If the runtime returns meta.interview_calibration, relay that value into the
next ooo interview call as the interview_calibration argument.
If ooo idk is invoked while an interview question is pending:
meta.interview_calibration
value as the interview_calibration argument.ooo interview, explain it and
rephrase before asking for a decision. Do not count “I don't know that term”
as an answer to the underlying interview question.Your final response MUST end with exactly one breadcrumb footer line:
◆ <current state> → next: <recommended action>Derive <current state> from live session state via ouroboros_session_status
when that MCP projection is available; otherwise derive it from this skill's
actual outcome. Never use a linear Step N of M footer because Ouroboros is an
evolutionary loop. When the next action is genuinely a choice, list 2-3 honest
options in the next: clause. The breadcrumb line must be the last line of the
response.
Q00/ouroboros
592c667
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.