research-types-explanatory
Explanatory research type sub-skill. Router-dispatched from research-agent parent on signals like "Why", "Root cause", "Caused by", "What led to", "Explain why". Loads the Causal Analysis pattern (Pattern C) with 5 Whys, Fishbone, and PECO framework. Not directly model-invocable.
What this skill does
# Explanatory Research Sub-Skill
Router-dispatched paradigm sub-skill for **Explanatory** research. Not directly model-invocable; the `research-agent` parent loads this sub-skill only when Phase 1 detection classifies the question as Explanatory.
## When This Sub-Skill Loads
The parent router dispatches here when the input question contains signals like:
- "Why does X happen"
- "Root cause of X"
- "What caused X" / "What led to X"
- "Explain why" / "Because"
- Post-incident investigations, defect investigations, "RCA on X"
## Framework Selection
| Framework | Use When |
|---|---|
| **PECO** | Population is exposed (not actively choosing) and effect is measured ("why did the population exposed to dependency X experience outcome Y") |
| **None** | Direct causal investigation; use 5 Whys + Fishbone instead of a formal framework |
PICO is rare for Explanatory — Explanatory looks backward at why something happened; PICO looks forward at whether an intervention works.
## Output Pattern: Causal Analysis
Use this pattern verbatim for the Findings section (parent skill's Phase 6 Synthesis output):
```
## Research Type: Explanatory
## Framework: [PECO / None]
## Symptom Definition
[Precise statement of observed effect - what, when, where, severity]
## 5 Whys Chain
Why 1: [Symptom] -> Because [Cause 1] [S1]
Why 2: [Cause 1] -> Because [Cause 2] [S2]
Why 3: [Cause 2] -> Because [Cause 3] [S3]
Why 4: [Cause 3] -> Because [Cause 4]
Why 5: [Cause 4] -> Because [Root Cause]
## Fishbone Categories (Ishikawa)
| Category | Contributing Factors |
|----------|---------------------|
| People | [...] |
| Process | [...] |
| Technology | [...] |
| Environment | [...] |
| Data/Materials | [...] |
## Hypothesis Evidence Map
| Hypothesis | Supporting [Sx] | Opposing [Sx] | GRADE |
|------------|-----------------|---------------|-------|
| H1: [...] | [S1], [S3] | [S2] | ⊕⊕⊕◯ |
## Most Probable Root Cause
[State with GRADE level]
## Counterfactual Test
[What would we expect if this cause were removed? Does evidence support that?]
## Validation Required
[What experiment or observation would confirm the root cause?]
```
## Phase Adaptations
The parent skill's 8-phase flow applies. Explanatory-specific notes:
- **Phase 3 (Scope)**: Symptom definition is the entry condition — precise what/when/where/severity statement required before Phase 4.
- **Phase 4 (Source Plan)**: Prioritize Primary sources tied to the incident (logs, code, telemetry, post-incident write-ups). Secondary sources used only for analogous cases.
- **Phase 5 (Gather)**: Drive each ReAct cycle toward a specific hypothesis confirmation or rejection. Avoid the "everything could be the cause" trap.
- **Phase 6 (Synthesis)**: 5 Whys is a discipline, not a checkbox — every step must cite evidence. Steps without `[Sx]` citations are invalid.
- **Phase 7 (Bias)**: Watch especially for **confirmation bias** — root-cause investigations naturally seek confirming evidence for the first plausible hypothesis. Counter by requiring opposing evidence in the Hypothesis Evidence Map.
## Integrity Constraints (Explanatory-Specific)
- **Correlation is not causation.** This is the cardinal rule. Every causal claim must include either an explicit causal mechanism or a `[INFERENCE]` label.
- **Counterfactual test is mandatory.** A root cause without a counterfactual ("if we removed X, the symptom would not occur because...") is a hypothesis, not a finding.
- **Validation step required.** Every Explanatory output ends with `Validation Required` — what experiment would confirm? Closed-loop validation distinguishes RCA from speculation.
- **Multiple-hypothesis discipline.** Do not collapse to a single root cause prematurely. The Hypothesis Evidence Map MUST list at least 2 alternatives unless a single-hypothesis is provably exhaustive.
## References
- Parent: `research-agent/SKILL.md` (Phase 1-8 flow, GRADE system, integrity constraints)
- `research-agent/references/research-type-patterns.md` § "Explanatory" - identification matrix, disambiguation rules
- `research-agent/references/systematic-review.md` § "Risk of bias" - bias categories that contaminate causal investigations
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.