Skip to content

oliver-kriska/claude-elixir-phoenix / targets/dsh/skills/phx-research

phx-research

Verified

Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library). Use when learning about libraries, patterns, or comparing approaches. Searches HexDocs, ElixirForum, GitHub.

FileKindSize
SKILL.mdskill md3.3 KB
references/library-evaluation.mdmarkdown1.9 KB

references/library-evaluation.md

View on GitHub
# Library Evaluation Template

When `/phx-research --library` or evaluating a Hex dependency,
use this structured template instead of free-form research.

## Workflow

1. Check hex.pm stats (downloads, recent releases, maintenance)
2. Read GitHub repo (issues, PRs, test quality, deps)
3. Analyze architecture fit with current project
4. Produce ONE structured document (not multiple files)

## Output Template

Write to `.claude/research/{library-name}-evaluation.md`:

```markdown
# Library Evaluation: {name}

## Quick Facts

| Metric | Value |
|--------|-------|
| Hex.pm | {url} |
| Latest version | {version} ({date}) |
| Weekly downloads | {count} |
| License | {license} |
| Elixir version | {requirement} |
| Dependencies | {list} |

## What It Does

{2-3 sentences — what problem it solves}

## Maintenance Assessment

- Last release: {date}
- Open issues: {count} (oldest: {date})
- Recent commits: {count in last 3 months}
- Test coverage: {yes/no/unknown}
- CI: {passing/failing/unknown}
- Rating: Active / Maintained / Stale / Abandoned

## Architecture Fit

### Current Project Patterns

{What patterns the project uses today for this concern}

### Library Approach

{How the library handles it — key design decisions}

### Integration Points

{Where the library connects to your code}

### Breaking Changes Risk

{What would need to change in your codebase}

## Recommendation

**Adopt / Wait / Skip**

Reason: {1-2 sentences}

If adopting:
1. {First integration step}
2. {Key configuration}
3. {Migration path from current approach}

## Watch Out For

- {Gotcha 1}
- {Gotcha 2}
```

## Size Target

One document, ~5KB max. No separate summary, index, or
integration guide files — everything in one evaluation doc.

## After Evaluation — STOP

Present the recommendation and ask user what to do next:

- "Plan the integration" -> `/phx-plan`
- "Research more" -> continue
- "Skip it" -> end
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