agent-self-learning
Agent Self-Learning — Flight Recorder
Purpose
You are keeping a black-box flight recorder. Whenever you deviate from the straight path during a task — a retry, a workaround, a missing tool, an assumption, a question to the user — you silently append an entry to the log.
The log is not for you to read back. It is a deliverable for the developer. They will review it after the session, or feed it to another agent to improve workflows and instructions.
You are the recorder. The human is the analyst.
Activation
This skill is always active. You do not need to be asked to keep the log.
- Record silently as you work. Do not mention the log mid-task.
More from aivokone/ak-skills-core
agent-flight-recorder
Always-on flight recorder for agent runs. Recorder-only — does not change task execution, only records. Log append-only YAML entries only when the run deviates (retry, detour, workaround, blocker, missing context, quality rework). Buffer entries and flush at end/abort, before a blocking clarification, on major context switch, or after high severity. One run per file, no file if zero entries. Never mention logging mid-task. At end, output exactly one line only if entries exist. No analysis, no guidance, no recommendations.
11local-ref
Local docs cache for the project. Always check docs/reference/ before fetching externally. Use for init (set up cache), update (refresh docs), lookup (local-first search), and save (persist fetched docs). If external docs are fetched (Context7/web), save a tailored topic file to docs/reference/ and add a verbal pointer in AGENTS.md.
7pr-review
Use FIRST for any PR/code review work — checking feedback, reading CR comments, responding to reviewers, addressing review bot or human comments, or preparing commits on a PR. Collects feedback from ALL sources (conversation, inline, reviews) to prevent the common failure of missing inline feedback. Start with check-pr-feedback.sh, then reply inline where needed and summarize with one Fix Report.
6multi-agent-pr
Multi-agent PR and code review workflow for projects using multiple AI assistants (Claude, GitHub Copilot/Codex, Gemini Code Assist). Use when working with pull requests, code reviews, commits, or addressing review feedback. Teaches how to check all feedback sources (conversation, inline, reviews), respond to inline bot comments, create Fix Reports, and coordinate between agents that use different comment formats. Critical for ensuring no feedback is missed from external review bots.
3