GPTsApp SkillsCodex Reset
Menu
Codex Reset

Find a skill for the job.

Compare the method, check the prerequisites, then go to the exact source.

Refine by task, source or prerequisites

Technology mentions are not dependencies. Client filters require scoped documentation, not a runtime compatibility claim. Detailed guides summarize files read at a fixed commit; they are not runtime tests.

8364 matches

Pinned source methods · Setup may be unknown
Choose 2–3 sharing a task.Selection guidance uses this directory’s task labels only. It is not runtime compatibility.

  1. eval-config

    skill collectionNo comparison task assigned

    byhartvig/agent-skills-collectionmarketing-and-advertising/digital-marketing-pro/eval-config/SKILL.md

    Configure content eval settings. Use when: adjusting score thresholds, dimension weights, or auto-reject rules. (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  2. eval-content

    skill collectionNo comparison task assigned

    byhartvig/agent-skills-collectionmarketing-and-advertising/digital-marketing-pro/eval-content/SKILL.md

    Evaluate content quality. Use when: scoring drafts, checking hallucinations, or assessing brand voice compliance. (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  3. eval-driven-dev

    community example

    github/awesome-copilotskills/eval-driven-dev/SKILL.md

    Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate (Publisher-index excerpt; file read separately)

    Setup not establishedSource observation · Source example · File tree not reviewedRead SKILL.md ↗Study method & source

  4. eval-harness-first

    plugin directoryNo comparison task assigned

    wshobson/agentsplugins/llm-finetuning/skills/eval-harness-first/SKILL.md

    Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  5. eval-suite

    skill collectionNo comparison task assigned

    byhartvig/agent-skills-collectionmarketing-and-advertising/digital-marketing-pro/eval-suite/SKILL.md

    Batch evaluate multiple content pieces. Use when: scoring a content library, campaign assets, or deliverable set. (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  6. evals-context

    skill collection

    foryourhealth111-pixel/vibe-skillsbundled/skills/evals-context/SKILL.md

    Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  7. evaluating-code-models

    skill collectionNo comparison task assigned

    foryourhealth111-pixel/vibe-skillsbundled/skills/evaluating-code-models/SKILL.md

    Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  8. evaluating-llms-harness

    skill collectionNo comparison task assigned

    foryourhealth111-pixel/vibe-skillsbundled/skills/evaluating-llms-harness/SKILL.md

    Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  9. evaluating-machine-learning-models

    skill collectionNo comparison task assigned

    foryourhealth111-pixel/vibe-skillsbundled/skills/evaluating-machine-learning-models/SKILL.md

    Evaluate trained machine learning models with the right metrics and comparison logic. Use for benchmark review, threshold selection, calibration, validation, and model (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  10. evaluating-threat-intelligence-platforms

    skill collectionNo comparison task assigned

    byhartvig/agent-skills-collectiondevelopment-and-testing/cybersecurity-skills/evaluating-threat-intelligence-platforms/SKILL.md

    Evaluates and selects Threat Intelligence Platform (TIP) products based on organizational requirements including feed integration capability, STIX/TAXII support, workflow automation, analyst interface, (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  11. evaluating-threat-intelligence-platforms

    skill collectionNo comparison task assigned

    mukul975/anthropic-cybersecurity-skillsskills/evaluating-threat-intelligence-platforms/SKILL.md

    Evaluates and selects Threat Intelligence Platform (TIP) products based on organizational requirements including feed integration capability, STIX/TAXII support, workflow automation, analyst interface, (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

  12. evaluation

    skill collection

    byhartvig/agent-skills-collectioncontext-engineering/context-engineering/evaluation/SKILL.md

    This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, (SKILL.md metadata excerpt)

    Setup not establishedSource observation · Source example · File structure observedRead SKILL.md ↗Study method & source

Snapshot w7-discovery-20260912 · 8364 file observations across 30 repositories. Source collection is not a quality or safety assessment.