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/zai-org/synapse/interview-designernpx skills add zai-org/Synapse --skill interview-designergit clone --depth 1 https://github.com/zai-org/SynapseWhat 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 | $0.00082 | $0.00850 |
| Opus 5 | $0.00041 | $0.00425 |
| Sonnet 5 | $0.00016 | $0.00170 |
| Haiku 4.5 | $0.00008 | $0.00085 |
Grade A, and why
interview-designer 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 2d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Designer Skill
Core Mission: Elevate interview planning from "glancing at resume and asking questions" to "evidence-based investigation and projection." Operating Mechanism: Define Scorecard (set standards) → Forensic Scan (evidence gathering) → Future Simulation (performance prediction). Prompt Strategy: This skill uses <Chain of Thought>. When executing, maintain an "Objective Evaluator" perspective, seeking both Red Flags and Green Signals.
1. Dynamic War Room (Expert Panel)
Dynamically summon the most matching best minds into the war room based on candidate's role attributes:
- Geoff Smart (Who): Responsible for Define & Verify.
- Principle: Scorecard First. Before looking at any resume, clarify what the standard for an "A Player" is.
- Lou Adler (Performance-based): Responsible for Predict.
- Principle: Past performance predicts future performance only if the context is similar. Must design simulations for future scenarios.
- Daniel Kahneman (Bias Control): Responsible for De-bias.
- Principle: Beware of "confirmation bias." If concerns are found, also seek counter-evidence; if highlights are found, verify their replicability.
- Domain Expert: Responsible for Depth.
2. Core Execution Workflow
Step 1: Scorecard Definition - Smart's Priority
Don't look at the resume first! Based on JD or role requirements, define A Player standards for this position:
- Mission: One sentence - why does this role exist?
- Outcomes: 3-5 specific, measurable results that must be achieved within 12 months.
- Competencies: Hard/soft skills required to achieve the above outcomes.
Step 2: Forensic Resume Scan - Smart's Forensic
Use Step 1 standards to scan the resume, looking for Gaps (discrepancies) and High Points (highlights):
- The "Too Good To Be True" Heuristic: Logical gaps behind perfect data.
- The "Passenger vs Driver" Heuristic: Individual's true contributions under big company halo.
- The "First Principles" Heuristic: Principle understanding behind technical jargon.
What ships with it
5 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.
- 2d ago First seen · 54 lines · 82 tokens per session scan A 5505ed177082
interview-designer is a skill published in the GitHub repository zai-org/Synapse (438 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 850 once invoked, about $0.0004 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.
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…