Ashutoshsinghpr7 Agent Skills
8 skills published by ashutoshsinghpr7 across 1 repository. Together they weigh 3 497 tokens — that is what loading all of them at once would cost you in context.
8 skills 3 497 tokens total
Sandbox approval policy blocks execute_code and python3 -c; use read_file/write_file + manual transforms instead of retrying both runners.
ripgrep/search_files silently skips binary-detected files — verify empty search results with grep -a / file / xxd before concluding 'not found'.
Apply ONLY the spec clauses literally — no aggregation, dedup, or cleanup transforms; each input record maps to its own output line.
Empty session traces mean launch failure, not agent behavior — verify api_call_count/tool_call_count and stdout.txt before analyzing.
After write_file, re-read the deliverable (or ls + hexdump/line-print) and re-check the last format clauses before finishing.
Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict R_val > R_best gating.
Consolidate traces into the persistent wiki (WikiSkill).
Propose skills from wiki patterns and traces (WikiSkill).