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 akiotanaka847/qaio-desktop --skill evaluate-a-candidategit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/evaluate-a-candidate)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/evaluate-a-candidate"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/evaluate-a-candidate/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/akiotanaka847/qaio-desktop/evaluate-a-candidate"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/evaluate-a-candidate.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 | $0.00060 | $0.01824 |
| Opus 5 | $0.00030 | $0.00912 |
| Sonnet 5 | $0.00012 | $0.00365 |
| Haiku 4.5 | $0.00006 | $0.00182 |
Grade A, and why
evaluate-a-candidate 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 6d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate a Candidate
Two paths, same output: one candidate file per applicant, scored against role rubric. Pick source based on what in front of you.
When to use
source=resume- "screen this resume", "screen resume stack for {role}", "rank these resumes", "who strongest on pile". Single and batch both supported.source=linkedin- "score {LinkedIn URL}", "is candidate fit for {role}", "rate this profile", "0-100 on this LinkedIn". One per invocation. Batch = run many times.
Both chain into prep-an-interviewer and debrief-an-interview-loop, which expect candidates/{slug}.md exist.
Connections I need
I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.
- Files (Google Drive) — pick up resume PDFs you drop. Required when source is resume.
- Web scrape (Firecrawl) — read public LinkedIn or profile URLs. Required when source is linkedin.
- Sheets (Google Sheets, Airtable) — write back ranked stack if you want one. Optional.
- ATS (Ashby, Greenhouse, Lever, Workable) — dedupe and write back candidate state. Optional.
If none of the required categories are connected I stop and ask you to connect the one that matches your source.
Information I need
I read your people context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.
- Role rubric — Required. Why I need it: I score every candidate against your must-haves. If missing I ask: "What role and level is this candidate for, and what are your top three must-haves?"
- Resume or profile — Required. Why I need it: I have nothing to evaluate without it. If missing I ask: "Drop the resume in your connected drive folder, or paste the LinkedIn URL."
- Candidate name — Optional. Why I need it: clean filing under the right slug. If you don't have it I pull it from the resume or profile and keep going.
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.
- 6d ago First seen · 98 lines · 60 tokens per session scan A 2f9523dad629
evaluate-a-candidate is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 60 tokens to every session and 1,824 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
connecting-with-people
Applies advanced interpersonal techniques for building genuine, lasting connections in entrepreneurial contexts. Covers the power of validation as the deepest form of listening, leading with 'How can I help you?' as a first-meeting strategy, maintaining authentic online identity, vulnerability as a professional…
inspiring-and-retaining
Equips founders with practical retention and inspiration techniques grounded in selfless leadership, strategic kindness, and relationship maintenance at scale. Covers making it about the audience (not you), the random-act-of-kindness mood reset, the homelessness perspective technique, praise-to-criticism ratios…
influencing-and-persuading
Provides founders with Socratic influence techniques, confidence projection methods, and patience-based persuasion strategies for converting stakeholders without overt selling. Covers idea-seeding (making others believe your idea is theirs), the paradox of persuasion (listening as the primary influence tool)…
meeting-the-right-people
Applies modern networking and relationship-curation methods for entrepreneurs who need to build strategic networks efficiently. Covers standing out through signature differentiation, the warm-introduction chain for reaching anyone, building a personal advisory board, the discipline of hiring slow and firing fast in…
reading-people
Applies practical techniques for decoding what people actually mean beyond their words, through nonverbal communication, active listening, rapport micro-signals, bluff detection, and mirroring. Covers listening with eyes rather than ears, the 55/38/7 communication model, accepting rapport signals, reading dishonesty…
resolving-people-conflict
Delivers specific behavioural systems for resolving interpersonal conflict in real time -- reframing conflict as a helping stance, the 24-hour cooling rule, strategic surrender of what cannot be controlled, and the bulletproof vest protocol (a structured seven-step system for safe conflict resolution). Use when a…