Menu
O SkillsMP coletou 10 skills de Darwin-Agent/HarnessX. Abra uma skill para revisar a origem e os detalhes.
Mostrando 10 de 10 skills coletadas.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of…
Idioma do texto original: inglês
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used…
Idioma do texto original: inglês
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting,…
Idioma do texto original: inglês
How to read trajectories and extract useful experience — from successes and failures alike — into candidates for the 4 HarnessConfig levers. Covers the trajectory frontmatter schema (behaviour / eval / judge), the two axes of reflection (lens × lever), the…
Idioma do texto original: inglês
Cross-round journal format — the multi-round memory that tells the next meta-agent what's been tried, what landed, and what got reverted. One `## Round N` section per evolve, with machine-parseable YAML frontmatter + free prose body. Read at the start of…
Idioma do texto original: inglês
Component-authoring reference for HarnessX evolve rounds. Covers the @tool signature and TOOL_SPEC workflow, MultiHookProcessor (hook dispatch table, event fields, messages-mutation contract), system-prompt template editing (Cases A/B/C), config.yaml shape,…
Idioma do texto original: inglês
Self-validation CLIs for the artifacts you write, plus the post-flight workflow the orchestrator runs after `end_turn`. Three categories — validity (canonicalize / dry_fire / contract / synthetic replay) blocks; policy (novelty / evidence) blocks on non-noop…
Idioma do texto original: inglês
GAIA-specific benchmark guidance. Public-writeup-sourced techniques (markdown browser, file inspector, code-action agent, planning, multi-agent decomposition, query refinement, answer-format guard, early-commit nudge, prompt caching, majority voting) mapped…
Idioma do texto original: inglês
τ²-bench-specific benchmark guidance (Sierra Research; retail / airline / telecom). Multi-turn dialogue eval with multiplicative reward (DB × action × NL-assertion) and pass^k reliability metric. Catalogues tau2 failure modes and techniques from public…
Idioma do texto original: inglês
Terminal-Bench 2 benchmark-specific structural facts for meta-agent evolution rounds. Covers sandbox topology, tool constraints, evolvable config surface, and trajectory signal layout. Read before authoring any candidate that touches the system prompt,…
Idioma do texto original: inglês