Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nealcaren/social-data-analysis --skill interview-bookendsgit clone --depth 1 https://github.com/nealcaren/social-data-analysisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nealcaren/social-data-analysis/interview-bookends)<a href="https://agentmods.dev/skills/nealcaren/social-data-analysis/interview-bookends"><img src="https://agentmods.dev/badge/skills/nealcaren/social-data-analysis/interview-bookends/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nealcaren/social-data-analysis/interview-bookends"><img src="https://agentmods.dev/badge/skills/nealcaren/social-data-analysis/interview-bookends.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.01876 |
| Opus 5 | $0.00015 | $0.00938 |
| Sonnet 5 | $0.00006 | $0.00375 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
interview-bookends scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Bookends
You help sociologists write introductions and conclusions for interview-based research articles. Given the Theory section and Findings section, you guide users through drafting the framing prose that opens and closes the article.
When to Use This Skill
Use this skill when users have:
- A drafted Theory/Literature Review section
- A drafted Findings section
- Need help writing the Introduction and/or Conclusion
This skill assumes the intellectual work is done—the contribution is clear, the findings are established. The task is crafting the framing prose that positions the contribution and delivers on promises.
Connection to Other Skills
| Skill | Purpose | Key Output |
|---|---|---|
| interview-analyst | Analyzes interview data | Codes, patterns, quote database |
| interview-writeup | Drafts methods and findings | Methods & Findings sections |
| interview-bookends | Drafts introduction and conclusion | Complete framing prose |
This skill completes the article writing workflow.
Core Principles (from Genre Analysis)
Based on systematic analysis of 80 sociology interview articles from Social Problems and Social Forces:
1. Introductions Are Efficient; Conclusions Do Heavy Work
- Median introduction: 761 words, 6 paragraphs
- Median conclusion: 1,173 words, 8 paragraphs
- Ratio: Conclusions are 67% longer than introductions
- Introductions subtract (narrow to the gap); conclusions expand (project to significance)
2. Phenomenon-Led Openings Dominate (74%)
- Most introductions open with empirical phenomena, not questions
- Question-led openings are rare (1%)—they feel performative
- Theory-led openings cluster in theory-extension articles (30%)
- Show the puzzle; don't just assert it exists
3. Parallel Coherence Is Normative (66%)
- Introductions make promises; conclusions must keep them
- Escalation (20%) is acceptable—exceeding promises reads as discovery
- Deflation (6%) is penalized—overpromising damages credibility
- Callbacks to introduction are universal (100%)
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- clusters/concept-building.md 6.1 KB
- clusters/gap-filler.md 4.9 KB
- clusters/problem-driven.md 6.1 KB
- clusters/synthesis.md 5.9 KB
- clusters/theory-extension.md 6.1 KB
- phases/phase0-intake.md 4.5 KB
- phases/phase1-introduction.md 7.3 KB
- phases/phase2-conclusion.md 8.5 KB
- phases/phase3-coherence.md 7.2 KB
- techniques/opening-moves.md 7.9 KB
- techniques/signature-phrases.md 6.9 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 225 lines · 29 tokens per session scan A 8fd4caa19c62
interview-bookends is a skill published in the GitHub repository nealcaren/social-data-analysis (85 stars, last pushed 10d ago), licensed MIT. It adds 29 tokens to every session and 1,876 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…