.build/claude/skills/source-evaluation-bibliography/SKILL.md
Evaluate source quality, build annotated bibliographies, and maintain curated reference collections. Covers the CRAAP test, source classification, citation management, and research documentation patterns. Triggers on source evaluation, bibliography creation, or research documentation requests.
npx skillsauth add organvm-iv-taxis/a-i--skills source-evaluation-bibliographyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Evaluate, document, and maintain curated collections of references and sources.
| Criterion | Questions | Weight | |-----------|-----------|--------| | Currency | When was it published/updated? Is the information still valid? | Medium | | Relevance | Does it address the specific question? Who is the intended audience? | High | | Authority | Who is the author? What credentials/affiliations? | High | | Accuracy | Is it evidence-based? Can claims be verified? Peer-reviewed? | Critical | | Purpose | Is it informative, persuasive, or commercial? Any bias? | Medium |
| Tier | Source Type | Reliability | Example | |------|-----------|-------------|---------| | S | Primary research, official specs | Highest | Peer-reviewed papers, RFC documents, official API docs | | A | Authoritative secondary | High | Textbooks, reputable technical blogs, conference proceedings | | B | Community knowledge | Moderate | Stack Overflow answers (high-vote), well-maintained wikis | | C | Informal | Variable | Blog posts, tutorials, forum discussions | | D | Unverified | Low | Social media, anonymous posts, undated content |
source:
title: "Designing Data-Intensive Applications"
author: "Martin Kleppmann"
type: book
year: 2017
url: "https://dataintensive.net/"
tier: A
evaluation:
currency: Good (concepts still current despite 2017 publication)
relevance: High (directly addresses distributed systems patterns)
authority: Strong (researcher at Cambridge, industry experience)
accuracy: Peer-reviewed content, extensively cited
purpose: Educational, no commercial bias
notes: "Definitive reference for distributed data systems. Chapter 5-9 most relevant."
tags: [distributed-systems, databases, architecture]
last_verified: 2026-03-20
## {Author Last}, {First}. "{Title}." *{Publication}*, {Year}. {URL}
**Tier:** {S/A/B/C/D} | **Relevance:** {High/Medium/Low} | **Last verified:** {Date}
**Summary:** {2-3 sentences describing the content and main argument}
**Key contributions:**
- {Specific idea, framework, or finding #1}
- {Specific idea, framework, or finding #2}
**Limitations:** {Any caveats, biases, or gaps}
**Connection:** {How this source relates to other sources or the project}
## Kleppmann, Martin. "Designing Data-Intensive Applications." O'Reilly, 2017.
**Tier:** A | **Relevance:** High | **Last verified:** 2026-03-20
**Summary:** Comprehensive guide to distributed data systems covering replication,
partitioning, transactions, and stream processing. Bridges theoretical CS concepts
with practical engineering tradeoffs.
**Key contributions:**
- Clear taxonomy of consistency models (linearizability, causal, eventual)
- Practical comparison of batch vs. stream processing architectures
- The "unbundling the database" framing for microservice data patterns
**Limitations:** Pre-dates serverless and edge computing patterns. Some implementation
details are framework-specific and may be dated.
**Connection:** Foundation for resilience-patterns and data-pipeline-architect skills.
Complements the CAP theorem discussion in redis-patterns.
references/
├── bibliography.yaml # Machine-readable catalog
├── by-topic/
│ ├── distributed-systems.md # Topic-organized annotations
│ ├── security.md
│ └── ai-agents.md
├── by-tier/
│ ├── tier-s.md # Primary sources only
│ └── tier-a.md # Authoritative secondary
└── reading-log.md # Chronological reading notes
bibliography:
- id: kleppmann2017
title: "Designing Data-Intensive Applications"
author: "Martin Kleppmann"
year: 2017
type: book
tier: A
topics: [distributed-systems, databases]
cited_by: [resilience-patterns, data-pipeline-architect]
- id: fowler2002
title: "Patterns of Enterprise Application Architecture"
author: "Martin Fowler"
year: 2002
type: book
tier: A
topics: [architecture, patterns]
cited_by: [backend-implementation-patterns]
The circuit breaker pattern [kleppmann2017, ch.8] provides fault isolation
between services. This aligns with the bulkhead pattern described in
[nygard2018, ch.5], which isolates failure domains at the resource level.
## Quarterly Review Checklist
- [ ] Verify URLs still resolve (automated: link-checker script)
- [ ] Check for updated editions or superseding publications
- [ ] Re-evaluate tier for sources whose domains have evolved
- [ ] Remove or demote sources that are no longer current
- [ ] Add newly discovered sources from recent research
development
Dry-run audit + targeted cleanup for shell command history. Currently wraps atuin (stats today, prune, dedup with dated preview artifacts); extensible to zsh/bash/mcfly backends. Always previews before applying — apply commands are echoed for the human to run, never auto-executed. Triggers on "/shell-history-hygiene", "audit atuin", "audit shell history", "clean shell history", "atuin prune", "atuin dedup", "shell history hygiene", "history cleanup". Replaces ad-hoc one-liners (e.g. `... | tee cmd > file.txt` which wrote two files, swallowed dedup output, and left a junk `cmd` file).
tools
Guided Cowork setup — install role-matched plugins, connect your tools, try a skill.
development
Manage AI agent session lifecycles with structured phases (FRAME, SHAPE, BUILD, PROVE), context preservation across sessions, handoff protocols, and session metadata tracking. Triggers on session management, agent lifecycle, or multi-session workflow requests.
tools
Parse a session transcript into a structured Session Governance Index — an annotated bibliography of every file modified and commit made, internal-energy accounting (tool uses, estimated tokens), shipped-vs-tasked atom tally, and classification of missing items as Gaps or Vacuums. Triggers on "visibility-schema-substrate-sweep", "session cascade audit", "session governance audit", or any request to summarize what a session actually produced versus what it was asked to produce.