ito-research
Conducts systematic research and synthesis to inform technical decisions and feature development.
Install
mkdir -p .claude/skills/ito-research-withakay && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18897" && unzip -o skill.zip -d .claude/skills/ito-research-withakay && rm skill.zipInstalls to .claude/skills/ito-research-withakay
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Conduct structured research for feature development, technology evaluation, or problem investigation. Use when the user needs to explore options, analyze trade-offs, or investigate technical approaches.Key capabilities
- →Save source investigations under .ito/research/<topic>/
- →Change reviews under .ito/changes/<change-id>/reviews/
- →Read .ito/wiki/index.md when present
- →Use Ito's configured, provider-neutral memory operations
- →Finish with a concise recommendation containing evidence
- →Update wiki topic/query artifacts when the result has durable reuse value
How it works
The skill guides research through phases, saving investigations and change reviews in specified directories, and using memory operations for guidance.
Inputs & outputs
When to use ito-research
- →Evaluating new technology stacks
- →Analyzing architecture trade-offs
- →Investigating feature implementation approaches
About this skill
Research lifecycle
Use the phase resources in this directory for stack, feature, architecture, pitfalls, security, scale, edge-case, and synthesis work. Save source investigations under .ito/research/<topic>/ or change reviews under .ito/changes/<change-id>/reviews/.
Read .ito/wiki/index.md when present. Treat .ito/wiki/ as synthesized navigation: cite the underlying spec, change, research, code, or documentation and call out stale or contradictory coverage. Fall back to raw Ito artifacts rather than blocking.
Use Ito's configured, provider-neutral memory operations when helpful:
ito agent instruction memory-search --query "<terms>" --limit 10
ito agent instruction memory-query --query "<question>"
Memory is guidance, not the source of truth. Current specs, code, and rendered instructions win conflicts. Durable capture belongs to the archive phase.
Finish with a concise recommendation containing evidence, alternatives, trade-offs, risks, and confidence. Link the synthesis from the proposal/design when research informs a change, and update wiki topic/query artifacts only when the result has durable reuse value.
<!-- ITO:END -->Limitations
- →Memory is guidance, not the source of truth.
- →Current specs, code, and rendered instructions win conflicts.
How it compares
This skill structures research and documentation within a defined lifecycle, unlike ad-hoc information gathering.
Compared to similar skills
ito-research side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ito-research (this skill) | 0 | 13d | Review | Intermediate |
| repo-research-analyst | 1 | 6mo | Review | Intermediate |
| business-knowledge-workflow | 1 | 2mo | No flags | Intermediate |
| gathering-requirements | 3 | 8mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by withakay
View all by withakay →You might also like
repo-research-analyst
parcadei
Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase
business-knowledge-workflow
TencentBlueKing
业务知识获取与 Skill 文档编写工作流。当用户需要熟悉新业务模块、从 iWiki 获取文档、结合代码分析生成架构文档、或将业务知识沉淀为 Skill 时使用。
gathering-requirements
CaptainCrouton89
Systematically clarify user needs, preferences, and constraints before planning or implementation. Classifies work type, investigates existing systems, discovers edge cases and integration points, resolves assumptions, and creates detailed specifications. Use when building features, enhancements, or integrations where requirements need clarification.
rfc
jiangzhe
Design and resolve RFC documents through evidence-gated multi-round workflow. Use when planning large architectural/program-level changes in docs/rfcs, enforcing goal/scope/direction clarity, explicit first-principles/long-term/original-fit proposal lenses with rationale, draft-to-formal progression
spec
matteocervelli
>
trellis-brainstorm
mindfold-ai
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.