From project-toolkit
Generates evidence-based documentary reports by searching memory systems (Claude-Mem, Forgetful, Serena, DeepWiki), .agents/ artifacts, and GitHub issues with full citation chains. For pattern analysis and historical reviews.
npx claudepluginhub rjmurillo/ai-agents --plugin project-toolkitThis skill uses the workspace's default tool permissions.
Generate comprehensive documentary-style reports from your memory systems with full evidence chains.
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.
Generate comprehensive documentary-style reports from your memory systems with full evidence chains.
/memory-documentary [topic]
Example topics:
Use this skill when:
Search my memories for patterns about...What does my history say about...Generate a documentary on my [topic]Cross-reference all systems for...Evidence-based analysis of my [topic]Use this skill when:
Use memory skill instead when:
| Phase | Action | Output |
|---|---|---|
| 1 | Topic Comprehension | Search variants, scope boundaries |
| 2 | Investigation Planning | Explicit queries per system |
| 3 | Data Collection | Evidence with IDs, timestamps |
| 4 | Report Generation | Documentary with citations |
| 5 | Memory Updates | Store meta-pattern discovered |
The skill searches ALL available data sources systematically:
Memory Systems (4 MCP servers):
Project Artifacts:
.agents/retrospective/ - Learning extractions.agents/sessions/ - Session logs.agents/analysis/ - Research reports.agents/architecture/ - ADRs.agents/planning/ - Plans and PRDsGitHub Issues:
# Standard invocation
/memory-documentary "recurring frustrations"
# With explicit time range
/memory-documentary "testing patterns" --since 2025-12-01
Full citation for each finding:
Timeline showing how thinking changed:
YYYY-MM-DD: [Observation #ID] - Initial state
YYYY-MM-DD: [Memory #ID] - First iteration
YYYY-MM-DD: [Issue #NNN] - Technical response
Cross-system synthesis revealing:
| Standard | Requirement |
|---|---|
| Citation | Every claim has ID, timestamp, quote |
| Quotes | Direct quotes, not paraphrases |
| Verification | Retrieval commands for all evidence |
| Cross-links | Related evidence connected |
| Avoid | Why | Instead |
|---|---|---|
| Partial searches | Miss critical evidence | Search ALL systems |
| Paraphrasing | Loses verifiability | Direct quotes only |
| Single query | Miss variations | 3+ query variants per system |
| Skipping systems | Incomplete picture | Check all 4 MCP servers |
After execution:
.agents/analysis/[topic]-documentary-[date].mdReports saved to: .agents/analysis/[topic]-documentary-[date].md
| Skill | Relationship |
|---|---|
| memory | Operations (search, update) |
| exploring-knowledge-graph | Forgetful traversal |
| retrospective | Learning extraction |
| skillbook | Pattern → skill conversion |
Read: references/execution-protocol.md
This contains the full 5-phase execution protocol with detailed instructions for each data source.