Results for “outcome-review”

Outcome Eval

Reviews closed trades, partial exits, and monthly trade aggregates for process adherence, risk discipline, execution quality, and evidence-based trading behavior patterns.

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

任意のリポジトリ（アプリ/ライブラリ/運用スクリプト/コンテンツ等）の種別を判定し、 種別に応じた評価軸（品質・テスト・依存、または検証ゲート等）で**実測ベース**評価して優先度付き改善案を出すスキル。 言語非依存（Python は AST 詳細・その他は近似と明記）。ベンダーコード混入・除外の空振り・偽の成功終了コードなど、 「黙って間違った数値を出す」失敗を構造的に封じる。 「リポジトリレビューして」「コード品質を評価して」「このプロジェクトを診断して」「包括レビュー」「repo-review」 「アーキテクチャ評価して」等で発火。/repo-review でも起動。

Facilitate structured post-incident reviews to identify root causes, document what worked and failed, and produce actionable recommendations to improve future incident response.

Turn interactive commit reviews back on for the current herdr workspace.

Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with structured-planning and debug-and-fix. Does not replace root-cause debugging — adds plan-level path selection.

Give a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a user-supplied approach set. Use for a solo POV, a mid-session second opinion, a named-peer cross-check, any request to consult other models or reconcile their opinions, an `oracle` panel, or a correction-cost-gated proactive cross-check offer. Not for findings review (use ce-doc-review), neutral explainers, or generating options (use ce-ideate or ce-brainstorm).

Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.

Skeptical pushback on the outline before drafting starts. Asks whether the outline is MECE, BLUF, problem-agitate-solution; whether it covers the topic better than the SERP top-5; whether sections duplicate; whether each section earns its visual. One revision pass on FAIL (BLOG_AGENT_OUTLINE_REVISION_BUDGET, default 1).

Validate whether an OSS tool is worth building through staged namespace, existing-solution, and feasibility review

Readability Review

当遭遇挫折、失败或结果不如预期时，用于将负面经验转化为成长燃料

Reviewer Role Session

OODA loop decision framework (Observe, Orient, Decide, Act). Use for complex decisions, problem-solving, unclear situations, or when someone is jumping to solutions without analysis.

Routes quality reviews to specialized critic agents based on file type or flags, covering peer review, code review, and manuscript polish.

Generates a post-release blameless retrospective from project signals — synthesizing DORA-like metrics, WorkItem outcomes, session timeline, and drift deltas into a structured Artifact + LogEntry. Use at the end of a release cycle when asked to run a retro, "post-release review", "retrospective", or "post-mortem".

Use to distil a CX dashboard into the three numbers a board or exec actually needs — volume/demand health, quality/outcome, and cost/efficiency — with commentary that drives decisions instead of forty tiles nobody acts on. Trigger for "board pack", "exec summary for support", "what should leadership see", "too many metrics on the dashboard", "three KPIs for the board", quarterly business review CX section, or when a leadership deck is mostly charts with no story.

Produce a plain-language manual test plan from the context supplied to it — an executive summary, a high-level list of named tests, and a detail section per test with the steps a person follows by hand and the outcomes they should expect. Use when you want to create, draft, generate, or outline a manual test plan, manual QA steps, hands-on verification steps, or an acceptance walkthrough for a feature, change, branch, plan, or PR. When the plan holds more than five tests and at least two natural categories emerge, both the test list and the detail sections are organized under plain-language categories. When nothing in the supplied context can be manually tested, it says so and asks for more context instead of producing a document. Does not analyze code for automated test coverage gaps — use automated-test-planning. Does not write test code — use tdd. Does not review code quality — use code-review. Does not stress-test an existing plan — use iterative-plan-review.