mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-21 00:26:23 +03:00
Magnus HedemarkandGitHub
051bf2a9c6
* fix: SkillOpt Epoch 1 — neckbeard description trigger-verb-first Move trigger verbs (fix/build/refactor/review/verify/release) to the front of the description for better discoverability. Negative case (non-software questions) now correctly rejected. Validation: 4/6 held-out tasks correct. * fix: SkillOpt Epoch 2 — wire overlooked catalog specialists into routing Add 6 stage-owning methodology skills to the routing table and SKILL.md summary: secure-software-engineering, web-accessibility, qa-methodology, product-design-and-ux, api-design-and-evolution, site-reliability-engineering. Note product-methodology and c4-diagramming as narrower composers. Baseline rollout showed security reviews, UI features, and regression-safety questions all routed without their natural specialist. Validation: 6/6 held-out routing tasks now route correctly (baseline 3/6). All additions are agent-agnostic methodology skills; no Hermes/deployment/personal content. * fix: SkillOpt Epoch 3 — align stages.md Stage 4 with expanded routing Stage 4 execution flow now names the same specialists added to the routing table in Epoch 2: secure-software-engineering and web-accessibility for implementation, qa-methodology for verification, product-design-and-ux and api-design-and-evolution for design, site-reliability-engineering for delivery. Rollout confirmed the gap: an agent following stages.md alone would route a security-sensitive change (untrusted input, trust-boundary crossing) with no security specialist. Validation: PASS — stages.md now names the specialist. * fix: SkillOpt final validation — remove Hermes-specific skill_view reference Replace skill_view(name="neckbeard") with agent-agnostic "read SKILL.md" in Quick Start. Public skill must not reference Hermes-specific APIs. * chore: regenerate Claude marketplace for neckbeard description update