Conf Abstract Enrichment
Thicken a thin or missing conference-session abstract through targeted web research so short, noisy text becomes classifiable — pulling the speaker's recent work, the linked repo or paper, and the company/product to add signal. Every enriched claim carries provenance (source URL + retrieval date) and a confidence, the enriched text is stored separately from the original (never overwriting it), and enrichment is gated so already-rich abstracts are left alone. Conference-agnostic. Use when an event record has been flagged thin by program extraction, when a session lacks enough text to classify,
Install
/plugin marketplace add lyndonkl/claudeThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add lyndonkl/claude --skill conf-abstract-enrichmentgit clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/conf-abstract-enrichment ~/.claude/skills/conf-abstract-enrichmentPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Conference Abstract Enrichment
Most of what a scheduler needs to know about a talk is not in its abstract, because the abstract is short, sometimes missing, and written to attract an audience rather than to be classified. This is the one stage in the pipeline where **runtime web search earns its keep**: a one-line blurb plus the speaker's recent work, the linked GitHub repo, and the sponsoring company is often enough to recover the topic, depth, and stakes that the program left out.
Enrichment is powerful and therefore dangerous. Unconstrained, it invents plausible detail, over-enriches talks that were already fine, and launders a guess into the record as if it were sourced. This skill keeps it honest with four rails: a **gate** (only enrich what is actually thin), a **source-priority ladder** (search the most reliable signal first), **mandatory provenance** (every claim names where it came from), and **separation** (enriched text never overwrites the original — it lives beside it so the source of truth survives).
The output is an **enrichment record** written to the side; the ingestor merges it back into the event. Enrichment never edits the program's own words and never reclassifies on its own — it supplies *better text and clearer axis signals* with sources, and lets extraction/clustering do the classifying.
## The enrichment record (output contract)
One JSON file per event, written to `enrichment/{event_id}.json`. Canonical — reproduce these field names.Details
- Skill name
conf-abstract-enrichment- Repository
- lyndonkl/claude
- Path
skills/conf-abstract-enrichment/SKILL.md- Repo updated
- 1 September 2026
FAQ
What does the Conf Abstract Enrichment skill do?
Thicken a thin or missing conference-session abstract through targeted web research so short, noisy text becomes classifiable — pulling the speaker's recent work, the linked repo or paper, and the company/product to add signal. Every enriched claim carries provenance (source URL + retrieval date) and a confidence, the enriched text is stored separately from the original (never overwriting it), and enrichment is gated so already-rich abstracts are left alone. Conference-agnostic. Use when an event record has been flagged thin by program extraction, when a session lacks enough text to classify,
How do I install the Conf Abstract Enrichment skill?
Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Conf Abstract Enrichment popular?
It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.
Related skills
Abstraction Concrete Examples
200lyndonkl/claude
Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
Academic Letter Architect
200lyndonkl/claude
Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
Adr Architecture
200lyndonkl/claude
Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
Cross Reference Claim
200lyndonkl/claude
Finds and cites a primary source for each substacker draft claim — original arXiv paper, official documentation, RFC, canonical textbook. Source hierarchy enforced — primary > secondary > tertiary > not-a-source. Records URL, title, passage/result that settles the claim. Use after classify-claim; runs once per claim unless classification is simplified-correct with high confidence on standard undergrad material. Trigger keywords — cross-reference, primary source, citation, arXiv, RFC, paper lookup, source hierarchy.
Citation Form Check
200lyndonkl/claude
Verifies every paper or named research result cited in a substacker draft uses the inline "Author(s), Institution, Year" form per style-guide, not a bare hyperlink or title-alone reference. Flags bare-hyperlink citations and missing-institution attributions. Use whenever the draft references external research. Trigger keywords — citation, paper citation, bare hyperlink, authors, institution, reference format.
Design Evaluation Audit
200lyndonkl/claude
Systematically evaluates existing designs against cognitive science principles using repeatable checklists, scoring rubrics, and severity-classified fix recommendations. Use when conducting design reviews or critiques, evaluating designs for cognitive alignment, performing quality assurance before launch, diagnosing usability issues, or choosing between design alternatives with objective criteria.
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.