← all publishers

Kbediako

@kbediako source repo

Report this profile Claim this profile

• 10 skills
• 0 followers
• 12 hours ago last updated

1. ▌
   Long Poll Wait · kbediako bundle

   Await or monitor external long-running jobs, operating-system processes, CI pipelines, cloud runs, remote training, or release checks until terminal status. Select an authorized observation path separately from active-turn or scheduled continuation; poll only pull-only sources. Never use for native Codex child or app-task lifecycle.
   0
   installs
2. ▌
   Native Agent Evals · kbediako bundle

   Evaluate or audit Codex native Multi-Agent V2 behavior with small reproducible probes and structural rollout evidence. Use for V2 surface checks, direct-tool lifecycle behavior, bounded fanout, interruption semantics, resume behavior, or skill-invocation evidence.
   0
   installs
3. ▌
   Consult Chatgpt Pro · kbediako bundle

   Consult ChatGPT Pro or another ChatGPT extended-reasoning mode with a faithful task-relevant context packet, reconcile its advice against local evidence, and run focused follow-ups to closure. Use when the user explicitly asks for ChatGPT Pro, GPT Pro, or extended reasoning, or when a second opinion would materially improve a high-risk plan or architecture choice, difficult or repeated troubleshooting, post-implementation or code/work review, visual review, or synthesis of conflicting analyses. Skip implicit consultation for trivial tasks and questions already decided by authoritative local evidence.
   0
   installs
4. ▌
   Challenge Assumptions · kbediako bundle

   Falsify uncertain root-cause claims in ambiguous, repeated, disputed, or failed-repair investigations; do not use when current authoritative evidence already establishes a straightforward cause and one direct, safe, low-risk, non-state-changing validation is sufficient. Use for conflicting evidence, user-observed contradictions, policy-, permission-, network-, auth-, dependency-, upstream-, or runtime-shaped errors, or before a state-changing diagnostic or any high-impact diagnostic or remediation, or blaming another system without proof.
   0
   installs
5. ▌
   Native Subagents First · kbediako bundle

   Coordinate bounded native Multi-Agent V2 work when the user asks for subagents, parallel agents, multi-agent implementation or review, or when an active native-agent workflow has genuinely independent streams. Use for GPT-6 Astra role selection, context inheritance, ownership, fanout, progress gates, and parent synthesis.
   0
   installs
6. ▌
   Voice Delegate Guidance · kbediako bundle

   Use, even when not named, when this agent is the primary coordinator for an operative Codex Voice `realtime_delegation` handoff, including `source=transcript_tail_flush` after the live session ends, or when the user explicitly requests delegate-only Voice coordinator mode. Delegate work that materially advances the requested outcome; in explicit delegate-only mode, delegate all action work. Do not activate when a delegated worker receives Voice wrapper text only as forwarded task material, or for ordinary typed messages in which Voice, delegation, or wrapper text is merely discussed or quoted as data.
   0
   installs
7. ▌
   Native Agent Deliberation · kbediako bundle

   Frame consequential or ambiguous decisions through distinct evidence-backed viewpoints, tradeoffs, and dissent. Use for brainstorming among competing strategies, architecture choices, risk review, or a decision whose assumptions should be challenged before execution.
   0
   installs
8. ▌
   Native Codex Coordination · kbediako bundle

   Choose the smallest suitable Codex workflow among solo work, bounded native-agent execution, deliberation, native-agent evaluation, skill forward-testing, and waiting. Use when the main uncertainty is which of these coordination shapes fits the task.
   0
   installs
9. ▌
   Wait For Subagents Patiently · kbediako bundle

   Reconcile and wait for native Codex children when a child is quiet, appears hung, exceeds an estimate, or a wait window times out. Use before calling a child stalled, interrupting it, replacing it, or handing off without its final answer.
   0
   installs
10. ▌
    Native Agent Skill Validation · kbediako bundle

    Forward-test an existing or changed Codex skill with fresh, contamination-resistant native-agent trials. Use to test whether instructions trigger, generalize, and change behavior under a fixed Astra worker condition; do not use to create or update the skill itself.
    0
    installs