Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rjmurillo/ai-agents/plugin install project-toolkitWrote 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/rjmurillo/ai-agents/requirements-interview)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/requirements-interview"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/requirements-interview/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/rjmurillo/ai-agents/requirements-interview"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/requirements-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 116 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00090 | $0.02747 |
| Opus 5.5 | $0.00036 | $0.01099 |
| Sonnet 5.5 | $0.00018 | $0.00549 |
| Haiku 4.5 | $0.00009 | $0.00275 |
Grade A, and why
requirements-interview 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Interview (grill-me pattern)
When this skill activates, you become an adversarial requirements interviewer. The goal is shared understanding before any code or design work. You walk the design tree branch by branch, resolve dependencies between decisions, and produce a structured PRD. Generation without alignment is the failure mode this skill exists to prevent.
Triggers
| Phrase | Context |
|---|---|
interview me on this |
New feature or task |
grill me on the requirements |
Refining a vague spec |
walk the design tree |
Surfacing dependent decisions |
stress-test this idea |
Pre-implementation validation |
audit this spec for ambiguity |
Existing multi-section specification |
Mode Selection
| Input | Mode |
|---|---|
| New idea or rough request | Discovery: the design-tree interview in Process below |
| Existing multi-section specification | Ambiguity audit: see Ambiguity Audit Mode |
| Clear, implementation-ready spec with no material ambiguity | Return NO MATERIAL GAPS. Do not manufacture questions. |
One skill owns both modes. Do not start a second requirements skill.
Inputs
- Free-form problem statement, issue body, or feature title.
- Optional: existing requirements draft, related code paths, ADR identifiers.
- Optional: OntologyFragment from
/specStep 1. When present, read it first, use O2 canonical names in questions, and carry anOntologysection into the PRD.
Outputs
| Artifact | Location | Purpose |
|---|---|---|
| Interview transcript | .project-toolkit/specs/interviews/INTERVIEW-<slug>.md |
Audit trail of decisions and rationale |
| Structured requirements | Returned to caller. /spec carries every PRD section through downstream steps and hands the full PRD to the spec-generator skill. |
Problem, user stories, ontology, data model, integrations, failure modes, security, observability, acceptance criteria, out-of-scope, deferred, open questions |
What ships with it
6 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 Changed · +67 lines · +1 tokens per session 455a9da39e38
- 22d ago Changed · +6 lines 58fabc251f96
- 24d ago Changed 98d0dad43c1f
- 1mo ago First seen · 117 lines · 89 tokens per session scan A 346b3ef376ec
requirements-interview is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 2,747 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.