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 profile-an-employeegit 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/profile-an-employee)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/profile-an-employee"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/profile-an-employee/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/profile-an-employee"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/profile-an-employee.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 | $0.00052 | $0.01232 |
| Opus 5 | $0.00026 | $0.00616 |
| Sonnet 5 | $0.00010 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
profile-an-employee 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Profile an Employee
When to use
- Explicit: "tell me about {employee}", "pull everything on {employee}", "prep me for my 1:1 with {employee}", "dossier on {employee}".
- Implicit: routed before review cycle, sensitive conversation (performance improvement plan, promotion, comp change), or exit interview.
- Frequency: on-demand per employee.
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.
- HR platform (Gusto, Deel, Rippling, Justworks) — read role, level, tenure, manager, comp, work authorization. Required.
- Chat (Slack) — pull recent thread context if relevant. Optional.
- Docs (Notion) — pull review notes or 1:1 docs if you keep them there. Optional.
- Inbox (Loops) — pull recent comms if useful. Optional.
If your HR platform isn't connected I stop and ask you to link Gusto, Deel, Rippling, or Justworks from the Integrations tab.
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.
- Employee identity — Required. Why I need it: I won't pull a dossier for someone I can't pin down. If missing I ask: "Which employee, full name, and team if you have it?"
- Authorization to view confidential fields — Required when comp or visa data is requested. Why I need it: I never leak one employee's comp or status to another without it. If missing I ask: "Should this dossier include comp and work-authorization details, or keep it to role and tenure only?"
- Roster source — Required when HR platform isn't connected. Why I need it: I need somewhere to read the basics. If missing I ask: "Connect your HR platform so I can pull this directly, or paste the employee record."
Steps
- Read people-context doc. Read
context/people-context.mdfor leveling, comp bands, confidentiality rules around dossier content. If missing/empty, tell user: "I need the people-context doc first - run the set-up-my-people-info skill." Stop. - Read ledger.
config/context-ledger.json. If HR platform not connected and no roster link recorded, ask ONE targeted question with modality hint - "Connect your HR platform (Gusto, Deel, Rippling, or Justworks) in Integrations tab, or paste employee record." Write resolution, continue. - Confirm authorization. Confirm requester authorized to see confidential data for this employee. Never reveal one employee's confidential data (comp, performance, medical, immigration) to another without explicit authorization.
- Discover HR platform tool - run
composio search hrisfor read-only profile slug. Pull: role, level, tenure, manager, location, comp (if authorized), work-authorization / visa status (if authorized), start date. - Local source pulls (read-only).
onboarding-plans/{employee-slug}.md- if this agent onboarded them. Skim Day-30/60/90 hits + misses.checkins/- scan most-recent check-ins referencing this employee-slug.retention-scores/- most recent score for this employee-slug.interview-loops/{employee-slug}.md- if past candidate, pull panel-debrief signal.- If any sibling agent dir missing (standalone install), silently skip, note "N/A - sibling not installed" in dossier.
- Compose dossier with four sections:
- Profile - name, role, level, tenure, manager, location, work-authorization status (if authorized).
- History - hire path (recruiter → offer → start), onboarding highlights, level changes, comp changes (if authorized).
- Recent signals - 1:1 themes from last N check-ins, retention score + trend, recent approvals run through this agent.
- Upcoming - next review date, visa expiry (if any), equity cliff (if any), next milestone from onboarding plan.
- Write dossier atomically to
dossiers/{employee-slug}.md(*.tmp→ rename). Keep to one scannable page. - Append to
outputs.json- read existing array, add{ id, type: "dossier", title, summary, path, status: "draft", createdAt, updatedAt }. Write atomically. - Summarize to user - one paragraph with headline signal (tenure + retention score + next milestone) and path to artifact.
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.
- 7d ago First seen · 69 lines · 52 tokens per session scan A ccdc2d40c684
profile-an-employee is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 1,232 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…
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…
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…