Skip to content

simonepri/ifttt-lint / .agents/skills/research

research

Verified

Investigate a topic, library, or approach before planning. Combines user context, prior knowledge, and external sources.

FileKindSize
SKILL.mdskill md1.4 KB
---
name: research
description: Investigate a topic, library, or approach before planning. Combines user context, prior knowledge, and external sources.
allowed-tools: Bash, Read, Glob, Grep, AskUserQuestion, Agent
---

# Research

Structured exploration to ground decisions in evidence. Use before `/plan` or whenever facing unfamiliar territory. $ARGUMENTS is the topic or question to investigate.

1. **Scope**: what do we need to learn? Break the topic into specific questions. If the user gave a broad topic, narrow it down — "how does X work?" is better than "tell me about X".
2. **Prior knowledge**: start with what you already know. State it explicitly so the user can correct misconceptions early.
3. **External sources**: for each open question, gather evidence following the Research rule in `workflow.md` — Context7 for libraries/APIs, web search for patterns and recommendations, source code for internals.
4. **Synthesize**: write findings to a temp file (`/tmp/research-<timestamp>.md`). Structure:
   - **Topic**: what we investigated
   - **Key findings**: numbered list of concrete answers to the scoped questions
   - **Recommendations**: what approach to take and why, based on the evidence
   - **Open questions**: anything still unclear that needs user input or deeper investigation
5. **Present**: open the file in the IDE or print the path. Summarize the key findings and recommendations in conversation — keep it brief, the file has the details.
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall