Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Interview Scheduling

ASecurity

Daily interview-scheduling sweep for {{projectName}}. Reads {{greenhouse_pipeline}} for candidates ready to schedule and each one's interview plan, checks {{interviewer_calendars}} for panel availability, and drafts a candidate slot proposal plus a calendar invite per interviewer to {{coordinator_review_inbox}}. Never sends a proposal or invite and never makes a hiring decision; a coordinator confirms and sends everything.

20,239 stars
0 votes
0 copies
1 views
Added 9/29/2026
ai-agentsgorails

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add kortix-ai/suna --skill interview-scheduling --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Interview Scheduling?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Interview Scheduling
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kortix-ai-interview-scheduling/badge)](https://www.skillsdirectory.com/skills/kortix-ai-interview-scheduling)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: interview-scheduling
description: Daily interview-scheduling sweep for {{projectName}}. Reads {{greenhouse_pipeline}} for candidates ready to schedule and each one's interview plan, checks {{interviewer_calendars}} for panel availability, and drafts a candidate slot proposal plus a calendar invite per interviewer to {{coordinator_review_inbox}}. Never sends a proposal or invite and never makes a hiring decision; a coordinator confirms and sends everything.
---

<skill name="interview-scheduling">

<overview>
Coordinating an interview loop means combining two systems that don't talk to
each other: the interview plan — who's on the panel, which round, how long it
runs — lives in Greenhouse, and whether those people are actually free lives
in their calendars. A daily sweep reads both, proposes a time that works for
every panelist, and drafts the candidate-facing proposal and each
interviewer's invite.

Fresh session every run, no local ledger: the agent recomputes the batch from
{{greenhouse_pipeline}}'s current state and {{interviewer_calendars}}'s
current availability each time, so what "already scheduled" means is whatever
{{greenhouse_pipeline}} already shows for that candidate.
</overview>

<when-to-load>
- The daily scheduling cron fires.
- A human asks the agent to schedule or re-propose a specific candidate's
  next round.
- An interview plan or a panelist's availability changes and the prior
  proposal needs to be redrafted.
</when-to-load>

<workflow>

## Step 1 — Find candidates ready to schedule

Read {{greenhouse_pipeline}} for every candidate marked ready to schedule —
cleared their current stage and waiting on the next round — who doesn't
already have a drafted or confirmed proposal for that round. Skip anyone
already scheduled or already carrying an undrafted proposal from a prior run.

## Step 2 — Read the interview plan

For each candidate, pull the plan for their next round from
{{greenhouse_pipeline}}: which interviewers are on the panel, what the round
covers, and how long it's scheduled to run. This plan is the only source of
truth for who belongs on the invite — never add or drop a panelist on your
own judgment.

## Step 3 — Check the panel's real availability

Check every interviewer on the plan against {{interviewer_calendars}} for
open slots in the next several business days that fit the round's duration.
A slot only counts if it's free for every panelist on the plan — partial
availability is not a proposable slot. Surface 2–3 candidate slot options
where the full panel is clear.

## Step 4 — Draft the candidate proposal

Draft a proposal email to the candidate offering the 2–3 open slots from Step
3, naming the round and roughly what to expect, in a tone that reads like a
coordinator wrote it. Place it in {{coordinator_review_inbox}}. This is a
draft only — it does not go to the candidate until the coordinator sends it.

## Step 5 — Draft the calendar invites

For the same slots, draft a calendar invite per interviewer on the panel —
correct attendees, round name, and duration from the plan — and place the
drafts in {{coordinator_review_inbox}} alongside the candidate proposal. Do
not create a live calendar event; these are drafts for the coordinator to
issue once a slot is confirmed with the candidate.

## Step 6 — Hand the batch to the coordinator, stop

Place the full batch — one proposal and one set of draft invites per
candidate — in {{coordinator_review_inbox}}, each with the candidate's name,
round, and proposed slots. Do not send the proposal. Do not send or create
any calendar invite. Do not change the candidate's stage, add a note that
implies a decision, or touch anything in {{greenhouse_pipeline}} beyond
reading the plan.

</workflow>

<guardrails>
- **Never send.** Every candidate proposal and every calendar invite is held
  in {{coordinator_review_inbox}} for the coordinator to review, adjust, and
  send or issue themselves. The agent has no send action and no action that
  creates a live calendar event.
- **Plan-only panel.** The interviewers on a draft invite come strictly from
  {{greenhouse_pipeline}}'s interview plan for that candidate and round —
  never a panelist added or substituted on the agent's own judgment.
- **Full-panel availability only.** A slot is only proposed if every
  panelist on the plan is free for it. Partial availability is never
  proposed as if it were a confirmed option.
- **No hiring decisions, ever.** The agent never rejects a candidate,
  advances or skips a stage, or drafts or sends an offer. It has no action
  that changes a candidate's hiring status.
- **Fresh per run.** Each sweep recomputes ready-to-schedule candidates and
  panel availability from the current state of {{greenhouse_pipeline}} and
  {{interviewer_calendars}} — no assumption carries over from the prior run.
- **Scoped secrets.** Access to {{greenhouse_pipeline}} and
  {{interviewer_calendars}} is brokered through connectors; no raw credential
  is ever pasted into chat.
</guardrails>

</skill>

Attribution

kortix-aikortix-ai
View sourceSee grades on GitHubMore from kortix-ai →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →