assess-obstacle-severity
This skill evaluates the practical difficulty of identified obstacles for a specific user by rating each on overcomability, time investment, and available workarounds. Use it after obstacles have been identified to determine which barriers are surmountable versus prohibitive, optionally validating assessments through web or literature search before generating structured severity ratings.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/assess-obstacle-severity && cp -r /tmp/assess-obstacle-severity/skills/assess-obstacle-severity ~/.claude/skills/assess-obstacle-severitySKILL.md
# Assess Obstacle Severity Assess how severe each obstacle actually is for this specific user. ## Execution Subagent — spawned via `subagent-spawning/spawn-agent` skill. ## Input - Identified obstacles list - ActorProfile ## Search Optional — may use web-search, web-research, literature-overview, literature-search, literature-research to validate assessments. ## Output Each obstacle rated on: - Overcomability: 1-week learnable / 1-month effort / 6-month investment / fundamental blocker - Time cost estimate - Workaround existence (yes/no + description)
Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.
Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.
loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.
loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.
Strategy: 面对异常的最佳解释推理
Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems