All plugins

interview-prep-coach

Prepares the user for their own interview: researches only the people they will meet, from public professional sources; predicts and tiers likely questions; builds STAR answers only from real experience; runs scored mock interviews; writes questions to ask; assembles a cheat sheet; lists post-interview signals with evidence (no grade or prediction); drafts application materials and thank-you notes the user sends. Disclosure: no tools, hooks, MCP servers, scripts or stored credentials; uses the agent's own web search, never with the user's name, resume or notes; never sends, applies or contacts anyone; never signs in; candidate-side only, its profiles are not consumer reports; never records or infers race, color, religion, sex (including pregnancy, sexual orientation and gender identity), national origin, age, disability, genetic information, veteran, marital, family, citizenship or immigration status, health, politics, home address, personal accounts, graduation years, photos or other protected traits.

KellerAIGeneralv1.0.0Updated 5 hours ago

About

Prepares the user for their own interview: researches only the people they will meet, from public professional sources; predicts and tiers likely questions; builds STAR answers only from real experience; runs scored mock interviews; writes questions to ask; assembles a cheat sheet; lists post-interview signals with evidence (no grade or prediction); drafts application materials and thank-you notes the user sends. Disclosure: no tools, hooks, MCP servers, scripts or stored credentials; uses the agent's own web search, never with the user's name, resume or notes; never sends, applies or contacts anyone; never signs in; candidate-side only, its profiles are not consumer reports; never records or infers race, color, religion, sex (including pregnancy, sexual orientation and gender identity), national origin, age, disability, genetic information, veteran, marital, family, citizenship or immigration status, health, politics, home address, personal accounts, graduation years, photos or other protected traits.

Interview Prep Coach

Interview Prep Coach is a plugin for Hermes Agent. It prepares you for a specific interview: it researches the panel from public professional sources, predicts the questions each interviewer is likely to ask, builds STAR answers from your real experience, runs a mock interview with scored feedback, and drafts your application materials and thank-you notes for you to send.

Install

hermes plugins install KellerAI/hermes-plugins#interview-prep-coach --no-enable
hermes plugins enable interview-prep-coach

This plugin is not listed in the Hermes plugin catalog; install it from this repository as shown. Portable packages stay disabled until you enable them. Once enabled, the skills appear as interview-prep-coach:<skill>.

Skills

SkillUse it when
get-startedYou have just enabled Interview Prep Coach, or want to know what it does and how to start.
interviewer-researchYou know who is on the panel and want a cited, public-source profile of each person.
question-predictorYou want the questions you are most likely to be asked, ranked and tiered.
answer-crafterYou want STAR answers built from your real experience, with follow-ups and a 60-second version.
mock-interviewYou want to rehearse with an in-character interviewer and get scored feedback.
questions-to-askYou want tailored questions to ask each interviewer.
prep-briefYou want a one-page cheat sheet or a fuller brief the night before.
debriefThe interview is over and you want the signals listed with their evidence, and a follow-up plan.
application-packageYou want a tailored resume summary, cover letter, recruiter message or 30-60-90 plan.

What it does not do

  • It never sends, posts, submits or applies for anything, and never contacts an interviewer, recruiter or employer. Every message is a draft you send yourself.
  • It never invents experience. Tailoring rewords what is true.
  • It researches only the people you will be interviewed by or are applying to, from public professional sources only. It declines to research job candidates or other private people. Its profiles are not intended to be consumer reports, and Interview Prep Coach is not a consumer reporting agency.
  • It never looks up, records, scores or comments on race, color, religion, sex (including pregnancy, sexual orientation and gender identity), national origin, age, disability, genetic information, veteran or military status, marital or family status, citizenship or immigration status (beyond lawful work authorization), health, politics, home addresses, personal accounts or any other legally protected characteristic. It does not record graduation years, career-start dates or photos, or infer protected characteristics from names, schools or history.
  • It never predicts or role-plays questions about a protected characteristic. If you report being asked one, the debrief flags it as possibly improper (not legal advice).
  • It never signs in anywhere; it stops at login walls.
  • A debrief lists signals with their evidence; it gives no overall grade and is not a prediction of the employer's decision.
  • It is skills only: no tools, no hooks, no MCP servers, no scripts.

Disclosure

  • No network calls of its own, no model calls of its own, no telemetry.
  • No scripts, no background processes, no stored credentials, no compiled binaries.
  • Uses your agent's own web search to read public pages for interviewer and company research, citing each source with the date read. Sends nothing to KellerAI.
  • Your resume and notes are used only in the conversation: web searches contain only the interviewer's name and title, the company and the role, never your name, resume or notes. It does not save your resume, notes or interviewer profiles to persistent memory unless you ask. Outputs are printed as Markdown for you to keep.

License and credit

Apache-2.0. See LICENSE and NOTICE.

Built by KellerAI (https://kellerai.io). KellerAI on X: @KellerAI_KAI · Jonathan Bowe, Co-Founder & COO, on X: @KellerAI_COO · LinkedIn: https://www.linkedin.com/in/jonathan-bowe-kellerai

KellerAI is not affiliated with or endorsed by Nous Research, xAI or OpenAI.

README from the reviewed commit cf34342; it updates when the author re-pins.

More by KellerAI

4 plugins by KellerAI in the catalog.

KellerAIhook-deskSkills-only plugin. Studies the opening lines of posts you paste, names the pattern, keeps a sourced formula file and drafts opening lines in your voice for your approval. Never posts or browses. Disclosure: no network calls, no model calls of its own, no shell, no stored credentials; reads only text the user provides.CommunitygeneralKellerAIproveit-testsFlags recognizable ways an agent weakens tests to reach green: removed or loosened asserts, skip/xfail/.only, deleted tests, expected literals rewritten to match failing output, assert True and tautologies, try/except pass wrappers, and test-runner escape hatches (pytest || true, -k "not ...", --deselect, --passWithNoTests, CI continue-on-error), and pytest config / conftest.py narrowing (addopts -k/-m/--deselect/--ignore, testpaths, collect_ignore, deselecting hooks). Net-new only: each edit is compared with the file as it was before, so pre-existing skips are not blamed on the edit. Deterministic AST + regex, no model calls. Modes: observe (default), escalate to the human-approval gate, or block on unattended/cron runs. SHA-256 receipts and a /proveit ledger. Python-strong; JS/TS coverage is heuristic and limited. Disclosure — no network calls and no model calls. Reads edited test, CI, pytest-config and conftest.py files and tool arguments to compare before/after; appends warnings into tool results; may escalate or block tool calls when configured. Ledger is written only under the Hermes plugin data dir (in-memory if none); terminal findings keep a short, secret-redacted command excerpt locally. Not a sandbox and not unbypassable: an agent can still rewrite via shell, disable the plugin, or invent new weakenings. No findings is not proof that tests were preserved.CommunitytoolsKellerAIreliability-deskHigh-reliability practices on your real launches, changes and incidents: go/no-go polls with named veto owners, blameless incident reviews that fix conditions rather than people, FMEA with RPN and severity override, closed-loop readbacks, stop-the-line triggers, change-control recommendations and session checklists. Every finding cites its evidence, and every GO, NO-GO or change-control outcome is a recommendation for a named human. Disclosure: no tools, hooks, MCP servers, scripts, network calls or stored credentials; works from what the user pastes; never sends, posts or pages anything; merges, deploys, rollbacks or other changes happen only when the user confirms that exact action in their own message; never signs in.Communitygeneral

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section