Results for “eval”

Design task-local harnesses, eval gates, and reusable skill extraction for adaptive agent workflows.

Automatically evaluates Claude Code sessions to extract reusable patterns and save them as learned skills.

Create new skills, modify and improve existing skills, and measure skill performance through iterative evaluation and benchmarking.

Manages career workflows: resume review and scoring, job evaluation with apply recommendations, rubric development, content extraction from conversations, and pipeline quality audits.

Rates an agent's own output on five axes — accuracy, completeness, clarity, actionability, conciseness — producing a structured scorecard with evidence and improvement suggestions.

Provides structured goal-setting and strategic guidance in the style of John Doerr, focusing on OKRs, execution, and team evaluation.

Evaluates whether a lawsuit is worth pursuing, explains the litigation process from filing to resolution, and guides case preparation, settlement negotiations, and small claims alternatives.

Helps software engineers with discrete job search tasks: job description analysis, CV tailoring, cover letter writing, offer evaluation, and follow-up emails.

Audits AGENTS.md and CLAUDE.md files for bloat, redundancy, and ineffective rules, then runs A/B evals to prove which instructions are dead weight.

Use when planning an HPCA project timeline from venue fit through the two-step July registration and paper gate, the autumn review wait, the single rebuttal/revision window, notification, IEEE camera-ready, artifact evaluation, and the February/March talk, with backward-planning offsets for a hardware-evaluated paper.

Use when planning a USENIX FAST project timeline from venue fit through choosing a Spring or Fall deadline, double-blind submission, the author-response period, shepherding or a one-shot revision, artifact evaluation, and the open-access camera-ready, with backward-planning offsets tuned to storage evaluation and honest handling of the two-deadline cycle.

Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds). Use when asked to: "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "which version is better", "expert score", "evaluate this copy/strategy/page", or when another skill needs a quality gate on its output. Also triggers on: "score this landing page", "expert panel these email variants", "rate this headline", "panel these charts".

Evaluate business decisions through the lens of sustainable, profitable growth, covering spending, hiring, fundraising, and scaling.

Evaluates whether suing is worthwhile, explains the litigation process from filing to resolution, and guides case preparation and settlement negotiations.

Analyzes email sequence performance metrics. Evaluates open rates, click rates, reply rates, and conversion by step. Identifies drop-off points, benchmarks against industry averages, and recommends optimizations.

Identify skill coverage gaps and improvement opportunities. Use when analyzing missing skills for a task, creating skill gap issues, evaluating skill effectiveness, or refining skill progressive disclosure.

Evaluate and improve interface usability using heuristic analysis based on Nielsen's 10 heuristics, Krug's laws, and severity ratings.

Use when a val sends email, receives email, or is triggered by an incoming email. Covers email-type vals (the Email handler shape, attachment limits, the assigned val email address) and sending mail via std/email.

Systematically evaluates alternatives against weighted criteria, builds a comparison matrix, and recommends the best option with documented rationale and trade-offs.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Discovers VC, accelerator, angel, and CVC investors via web search, evaluates thesis fit across four dimensions, and maps approach pathways for outreach.

Collects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.

Evaluate a paper's contribution novelty, identify best-fit SSCI journal fields and ABS star rating, and recommend 20 target journals. Trigger when user says "paper submission" / "paper-submission" / "投稿评估" / "期刊推荐" / "target journal" / "选刊".

Displays HTML content on connected OpenClaw nodes (Mac, iOS, Android) via a local HTTP server and node bridge, with actions for presenting, navigating, evaluating, and capturing snapshots.

Transforms fuzzy problems into structured briefs that AI agents can reason about, critique, and act upon, while evaluating how much of the problem can be automated.

Discovers and evaluates community skills from skills.sh and awesome-openclaw-skills when local skills don't cover a need, scoring credibility and installing top recommendations with permission.

Ruthless product and app critique for Nick's workflow. Use when evaluating an app, landing page, flow, or product experience to identify why users may bounce, distrust it, fail to activate, or never come back. Focus on practical weaknesses, not polite fluff.

Use when about to claim work is complete, fixed, or passing, before committing, before reporting a task done, or before telling the evaluator the batch is ready. Requires running the verification command and reading its output in this turn before any success claim; evidence before assertions always.

Use when planning an ESEC/FSE project timeline from venue fit through paper registration, submission, the journal-style Major Revision round, artifact evaluation, PACMSE camera-ready, and presentation, with backward-planning offsets for an empirical-SE paper and honest handling of the single-annual-deadline cycle and cycle-hopping.

Perform survival analysis and time-to-event modeling in Python using scikit-survival, including Cox models, random survival forests, gradient boosting, survival SVMs, and evaluation metrics like concordance index and Brier score.