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 agentmods add skills/olelehmann1337/workshop-plugin/skillcreator-interview-workshop-v2npx skills add olelehmann1337/workshop-plugin --skill skillcreator-interview-workshop-v2git clone --depth 1 https://github.com/olelehmann1337/workshop-pluginWrote 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/olelehmann1337/workshop-plugin/skillcreator-interview-workshop-v2)<a href="https://agentmods.dev/skills/olelehmann1337/workshop-plugin/skillcreator-interview-workshop-v2"><img src="https://agentmods.dev/badge/skills/olelehmann1337/workshop-plugin/skillcreator-interview-workshop-v2.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00162 | $0.03528 |
| Opus 5 | $0.00081 | $0.01764 |
| Sonnet 5 | $0.00032 | $0.00706 |
| Haiku 4.5 | $0.00016 | $0.00353 |
Grade A, and why
skillcreator-interview-workshop-v2 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 4d 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Extraction Interview
Most skill files read like Wikipedia entries. They explain what a thing IS instead of telling Claude how to DO it. The result: Claude uses them once, gets generic output, and the user stops using the skill.
A good skill captures a workflow — the actual sequence someone follows when they do the task, with the judgment calls, tool choices, and quality checks that make the output specialist-level. Those details never show up when you just describe the process at a high level. They show up when someone asks the right follow-up questions.
This skill runs that interview. It walks the user through 8 steps, asks targeted questions at each one, keeps probing until the workflow is concrete enough to execute, and packages the result into an Anthropic-blueprint skill file.
the core job
Run a structured interview that extracts the user's workflow, then produce a complete skill file they can install and call.
Output: A SKILL.md (plus references/ files if needed) saved to the directory the user picks — defaults to ~/.claude/skills/[skill-name]/ if they have no preference.
before you start
Two quick checks before launching into the interview:
- Scan CLAUDE.md. Claude auto-loads
~/.claude/CLAUDE.mdand any project-levelCLAUDE.md. If it already contains business context, voice rules, or ICP info, you can skip asking about those things later — just reference what's there. - One opening question only. Before Step 1, ask: "What's the one task you want to capture? In plain language, one sentence." This anchors the interview and prevents scope drift.
Everything else comes out of the 8-step interview below. Don't batch questions. Ask one step's worth at a time, wait for the answer, then move on.
the process
SCOPE → SEQUENCE → DECISIONS → TOOLS → QUALITY → FAILURE → TEMPLATE → PACKAGE
Eight steps. Each one pulls a specific part of the workflow out of the user's head. The order matters — scope before sequence (otherwise the user describes a different workflow than the one they named), sequence before decisions (otherwise the decisions have nowhere to live), and so on.
What ships with it
4 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.
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.
- 4d ago First seen · 320 lines · 162 tokens per session scan A 33c723f3bf32
skillcreator-interview-workshop-v2 is a skill published in the GitHub repository olelehmann1337/workshop-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 162 tokens to every session and 3,528 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…