Stats
Actions
Tags
From dstoic
Conducts deep proactive analysis for complex technical problems using workflows for scoping, decomposition, research, design, and weighted decision matrices. For technical spikes, design strategies, and multi-constraint issues.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dstoic:investigateopusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Deep analysis for complex technical problems. Proactive (design-first), not reactive (error-first).
Deep analysis for complex technical problems. Proactive (design-first), not reactive (error-first).
You are investigating: $ARGUMENTS
CRITICAL: After EVERY AskUserQuestion call, check if answers are empty/blank. Known Claude Code bug: outside Plan Mode, AskUserQuestion silently returns empty answers without showing UI.
If answers are empty: DO NOT proceed with assumptions. Instead:
0.Scope → 1.Decompose → 2.Research → 3.Design → 4.Decide → 5.Persist → 6.Bridge
AskUserQuestion to qualify:
Skip if $ARGUMENTS already covers these.
Break problem into sub-problems. See protocols/decompose.md.
Output: Mermaid diagram of sub-problems + dependencies.
For each sub-problem, multi-angle investigation. See protocols/research.md.
Output: Findings matrix — sub-problem × approach × evidence.
Generate 2-3 alternative approaches. See protocols/design.md.
Output: Alternatives table with trade-offs.
Output: Recommended approach + explicit risks.
MUST execute before finishing. DO NOT skip. DO NOT wait for user to ask.
Write investigation to $THINKING_DIR/investigations/{project}/{date}-{slug}-llm.md.
{project} = current project folder name (e.g., agent-skills, gtd-pcm). {slug} = lowercase hyphenated from problem statement. Create directory if missing.
Collision handling: If filename exists, append sequence: {date}-{slug}-2-llm.md, {date}-{slug}-3-llm.md. First write gets clean name.
Guard: If $THINKING_DIR is unset, warn user and skip artifact persistence: ⚠️ $THINKING_DIR not set — artifact not persisted. Set via: export THINKING_DIR="$HOME/dev/praxis/thinking"
Content (required sections):
Handoff to execution:
/openspec-plan)Before responding to user, verify:
$THINKING_DIR (or guard triggered if unset)protocols/decompose.md — Issue Trees, MECE, Constraint Mappingprotocols/research.md — Kepner-Tregoe IS/IS NOT, multi-angle probingprotocols/design.md — Morphological Analysis, trade-off frameworksnpx claudepluginhub digital-stoic-org/agent-skills --plugin dstoicGuides users through structured questioning to clarify ill-defined problems, then produces a problem statement, map, and solution routes before handing off to solution skills.
Facilitates structured brainstorming for problem exploration, design decisions, approach comparisons, and trade-off evaluations using 8 LLM bias-counteracting methods with parallel subagent deep dives.
Applies structured reasoning to complex coding problems using 19 analytical frameworks, 12 bias detectors, 10 decomposition methods, 10 mental models, Cynefin classification, ethical checks, and communication patterns.