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 skills add magnus919/agent-skills --skill job-interview-coachinggit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/job-interview-coaching)<a href="https://agentmods.dev/skills/magnus919/agent-skills/job-interview-coaching"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/job-interview-coaching/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/magnus919/agent-skills/job-interview-coaching"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/job-interview-coaching.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00084 | $0.02160 |
| Opus 5.5 | $0.00034 | $0.00864 |
| Sonnet 5.5 | $0.00017 | $0.00432 |
| Haiku 4.5 | $0.00008 | $0.00216 |
Grade A, and why
job-interview-coaching 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 yesterday.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Interview Coaching
Help candidates demonstrate real capability and assess the opportunity. Help interviewers elicit job-relevant evidence consistently while treating candidates well. Be candid, specific, and supportive; neither empty reassurance nor theatrical harshness teaches useful skills.
Establish the task
Infer candidate, interviewer, or both from the request. A transcript review by a candidate is candidate coaching; a hiring manager improving their questions is interviewer coaching. Ask one short clarifying question only if the purpose changes the next action. Do not force candidates through an interviewer-design intake.
Use supplied materials first. Establish role, actual responsibility level, interview stage/format, time available, and the user's goal only as needed. Say when the rubric is inferred. If they ask to practise now, begin with a suitable question promptly and state any material assumption.
Load only the relevant references
Read the mode reference, then the most specific format/profession reference needed for the task. The four broad family references are for cross-field orientation; prefer the focused playbook for a named profession. Do not load the whole library.
| Need | Read |
|---|---|
| Candidate preparation, example selection, motivation, setbacks | Candidate coaching |
| Transcript or recorded-interview critique | Transcript analysis |
| Mock interview, rehearsal, practice plan | Practice and feedback |
| Interview design, question quality, probing, candidate experience | Interviewer coaching |
| Scorecards, evidence review, interviewer debrief | Assessment and calibration |
| Behavioral, situational, panel, asynchronous, case, portfolio, demonstrations | Interview formats |
| Apprentice through executive; career transitions | Responsibility levels |
| Engineering, software, data, product, design, research | Technical and creative professions |
| Trades, manufacturing, logistics, retail, hospitality, administration | Operational professions |
| Healthcare, education, legal and other regulated work | Care and regulated professions |
| Consulting, sales, finance, management, public service | Business and public service |
| Access needs, language, culture, career gaps, difficult questions, privacy | Inclusive practice and boundaries |
| Evidence basis, source limitations, further research | Research and sources |
| Choosing an intervention after observing a weakness | Coaching diagnosis |
| Opening, motivation, conflict, weakness, gap, or unexpected question | Question-specific preparation |
| A full example of transcript-to-practice reasoning | Worked transcript |
| Professional coaching approaches and reference materials | Practitioner methods |
| Research methods, findings, and design consequences | Evidence review |
| Training an interview team and measuring candidate experience | Interviewer training |
| Software, infrastructure, security | Software interviews |
| Data, analytics, applied science | Data interviews |
| Physical engineering and laboratory technical work | Engineering interviews |
| Design, product, writing, creative portfolio | Creative interviews |
| Academic research, fellowship, faculty | Academic interviews |
| Healthcare, nursing, allied health, care | Healthcare interviews |
| Teaching, training, education | Education interviews |
| Legal, compliance, professional advice | Legal interviews |
| Apprentices, trades, maintenance, manufacturing | Trade interviews |
| Customer service, retail, hospitality | Service interviews |
| Logistics, administration, coordination | Operations interviews |
| Consulting and business cases | Consulting interviews |
| Finance, accounting, audit, risk | Finance interviews |
| Sales, account management, fundraising | Sales interviews |
| People management, directors, executives | Leadership interviews |
| Public service, civil service, mission-led roles | Public-service interviews |
| Unfamiliar profession, ambiguous title, or cross-field task | Profession adaptation |
| Reusable output forms | Session brief, review worksheet, interview plan, practice log, evidence bank, coaching plan |
What ships with it
47 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.
- evals/coordinator-interview.md 2.2 KB
- evals/evals.json 19 KB
- evals/rubric-notes.md 3.5 KB
- evals/trigger-probes.json 866 B
- README.md 2.5 KB
- references/academic-interviews.md 4.5 KB
- references/answer-types-and-difficult-questions.md 5.6 KB
- references/assessment-and-calibration.md 3.4 KB
- references/business-and-public-service.md 4.0 KB
- references/candidate-coaching.md 4.0 KB
- references/care-and-regulated.md 3.8 KB
- references/coaching-diagnosis.md 5.9 KB
- references/consulting-interviews.md 4.4 KB
- references/data-science-interviews.md 4.5 KB
- references/design-creative-interviews.md 4.6 KB
- references/education-interviews.md 4.5 KB
- references/engineering-interviews.md 4.6 KB
- references/finance-accounting-interviews.md 4.5 KB
- references/healthcare-interviews.md 4.8 KB
- references/inclusive-practice.md 5.8 KB
- references/interview-formats.md 3.4 KB
- references/interviewer-coaching.md 3.7 KB
- references/interviewer-training-and-experience.md 4.7 KB
- references/leadership-interviews.md 4.6 KB
- references/legal-interviews.md 4.6 KB
- references/operational-professions.md 3.8 KB
- references/operations-administration-interviews.md 4.4 KB
- references/practice-and-feedback.md 6.3 KB
- references/practitioner-methods.md 7.4 KB
- references/public-service-interviews.md 4.5 KB
- references/research-and-sources.md 15 KB
- references/research-evidence-and-design.md 6.8 KB
- references/responsibility-levels.md 2.8 KB
- references/sales-interviews.md 4.6 KB
- references/service-hospitality-interviews.md 4.5 KB
- references/software-interviews.md 4.6 KB
- references/technical-and-creative.md 4.0 KB
- references/trades-maintenance-interviews.md 4.5 KB
- references/transcript-analysis.md 4.9 KB
- references/transcript-worked-case.md 9.3 KB
- references/unfamiliar-professions.md 4.4 KB
- templates/coaching-plan.md 798 B
- templates/evidence-bank.md 1.0 KB
- templates/interview-plan.md 801 B
- templates/practice-log.md 421 B
- templates/session-brief.md 483 B
- templates/transcript-review.md 749 B
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.
- yesterday First seen · 111 lines · 84 tokens per session scan A 59616057b5cd
job-interview-coaching is a skill published in the GitHub repository magnus919/agent-skills (147 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 2,160 once invoked, about $0.0003 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 2026-10-24.
Other skills, from other repositories
cocoplus-off
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
cocoplus-on
Activate Full Assist Mode — enables all CocoPlus features simultaneously: Memory Engine, Environment Inspector, Safety Gate (normal), Code Quality Advisor, Context Mode, and CocoMeter. Also triggers a background environment scan. Idempotent.
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".
cocoplus-console
Launch CocoConsole, the CocoPlus 2.0 read-only local browser control plane. Use $cocoplus console, $cocoplus console status, or $cocoplus console stop.
meter-waste
Analyze CocoMeter context waste and surface repeatable reduction opportunities.
pulse-configure
Configure CocoPulse observation intervals and scopes.