From wire
Proactive skill for saving and retrieving technical research findings across sessions. Auto-activates when performing technical research within a Wire engagement.
npx claudepluginhub rittmananalytics/wire-plugin --plugin wireThis skill uses the workspace's default tool permissions.
This skill activates automatically when you are about to perform technical research in the context of a Wire engagement — i.e., when the working directory contains a `.wire/` folder and you are about to:
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
This skill activates automatically when you are about to perform technical research in the context of a Wire engagement — i.e., when the working directory contains a .wire/ folder and you are about to:
Purpose: Research findings are time-consuming to re-derive. Persisting them at engagement level means future sessions (and other team members) can build on previous findings rather than starting from scratch.
Before starting any research task, check whether it has already been done:
.wire/research/sessions/*/summary.mdDo NOT block on this check — if .wire/research/ doesn't exist or is empty, proceed immediately.
After completing a significant research task, save findings to the engagement research store:
Save when the research:
Skip saving when:
Create the session directory (use current timestamp):
mkdir -p .wire/research/sessions/YYYY-MM-DD-HHMM
Write the summary file at .wire/research/sessions/YYYY-MM-DD-HHMM/summary.md:
# Research Session: YYYY-MM-DD-HHMM
**Engagement**: [client_name from engagement/context.md, or "unknown"]
**Release**: [current release folder, if applicable]
**Phase**: [current phase, if applicable]
**Topic**: [one-line topic description]
**Date**: [date]
## Summary
[2–4 paragraph summary of findings. Write for a consultant who is starting fresh — assume no context.]
## Key Facts
- [Specific, actionable finding 1]
- [Specific, actionable finding 2]
- [Specific, actionable finding 3]
## Implications for This Engagement
[How these findings affect the current work — what decisions they inform, what constraints they impose]
## Sources
- [URLs, file paths, or document names consulted]
## Caveats and Expiry
[Any caveats about reliability, version-specificity, or when these findings might become stale]
Optional: Save raw research material in the same session folder:
raw_api_response.jsonschema_extract.sqlcode_sample.pyAfter saving, briefly mention it:
Research saved to .wire/research/sessions/[timestamp]/summary.md
Keep this notification to one line — don't interrupt the flow of the main task.
When session:start is run, it automatically reads the 2–3 most recent research summaries and surfaces any that are relevant to the current release and phase. This skill does not need to do anything special for this — just ensure summaries are written clearly and include the release/phase metadata.
Research saved here may include client system details, API credentials context, or proprietary schema information. The .wire/research/ directory should be treated with the same confidentiality as all other Wire project artifacts:
.env.ACME_API_KEY") rather than valuesResearch is saved at engagement level (.wire/research/sessions/), not within a specific release folder. This is intentional: architectural decisions and system findings are relevant across all releases in an engagement. A finding from the discovery release about the client's BigQuery schema structure is equally relevant to a later dbt development release.