olko-reflection

Plugin olko-reflection from marketplace olko-agent-skills in oleg-koval/agent-skills. Commands read from the repo's manifest — 5 days ago.

Skills (7)

• agent-ops-retro

  Retrospective on how the agents themselves are being operated, from local Claude Code transcripts plus the reports other jobs already produce. Answers what is going well, what is going wrong, what the human keeps having to repeat, and where delivery is leaking, then carries every unactioned finding

• crash-course

  Expert tutor that gets you from zero to working knowledge on any TOPIC fast, grounded in real sources rather than generic filler. Use this whenever the user wants to LEARN, understand, ramp up on, or get up to speed on something and has limited time: a new codebase or project they have been assigned

• retro-analysis

  Produce a recurring engineering retrospective from repository history, delivery evidence, work patterns, code-quality signals and prior snapshots, in repository, comparison or cross-project mode. Use when the user asks for a retro over shipped work: "run a retrospective", "how did this quarter go",

• review-past-performance

  Self-improvement loop for coding sessions. Pulls the last 24h of ICM memories, git history, and available transcripts; detects patterns like repeated mistakes, slow workflows, untested changes, or missing skills; then proposes 1-3 concrete improvements (new skills, prompt tweaks, eval criteria). Not

• self-critique

  Adversarially critique your own last answer: a blind critic agent re-derives and verifies every claim against live sources, the score is computed from a labelled claim ledger, you revise under a ratchet, restate the corrected answer, and turn each caught error into a durable rule with a fire counter

• team-retrospective

  Collect a factual retrospective from each task-owned agent and safely dismiss the team after successful work. Use during wrap-up of a completed, green multi-agent task or when explicitly requested.

• wrap-up

  Close out a small change or multi-step task by checking its original objective, running applicable quality gates, auditing the diff and task-owned artifacts, and preparing an evidence-backed handoff. Use when work is believed done, the user asks to wrap up or clean up, or before handing work off. Fo