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 cnfeat/top-pm-skills --skill evaluating-candidatesgit clone --depth 1 https://github.com/cnfeat/top-pm-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/cnfeat/top-pm-skills/evaluating-candidates)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/evaluating-candidates"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/evaluating-candidates/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/cnfeat/top-pm-skills/evaluating-candidates"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/evaluating-candidates.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 | $0.00047 | $0.00970 |
| Opus 5 | $0.00023 | $0.00485 |
| Sonnet 5 | $0.00009 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
evaluating-candidates 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 11d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluating Candidates
Help the user make stronger hiring decisions using battle-tested frameworks from 94 product leaders.
How to Help
When the user asks for help evaluating candidates:
- Understand their context - Ask what stage they're at (screening resumes, reviewing work samples, conducting references, making final decisions) and what role they're hiring for
- Apply relevant principles - Use the frameworks below to help them think through the decision
- Challenge their assumptions - Push back on shortcuts like pedigree bias or gut-feel-only decisions
- Help them structure the process - Suggest interview questions, reference check approaches, or evaluation rubrics based on the principles
Core Principles
Reference checks trump interviews
Shishir Mehrotra: "I generally value the reference check over interview signals. Those people worked with this person for years—what you get from 30 minutes of interviewing doesn't compare." Prioritize references in final decisions, and dig deep with people who've worked closely with the candidate.
Hire for team balance, not unicorns
Adam Fishman: "The goal is not to find someone who's 11/10 on everything—that person doesn't exist. Create a well-rounded team by hiring to fill gaps in your portfolio." Before opening a role, map your team's current strengths and weaknesses.
Use paid work trials
Elena Verna: "We do 2-3 day paid work trials to see candidates in action—how they handle chaos and lack of clarity. This company is not for everybody." Work trials reveal what interviews cannot: how someone actually operates.
Prioritize agency over experience
Albert Cheng: "High agency and 'clock speed' are better predictors than deep experience. Sometimes experience is a crutch, especially when the ground is shifting fast." Look for candidates who took initiative outside formal channels.
Structure first, intuition after
Annie Duke: "If you use intuition after a structured evaluation—not before—you drastically improve your hit rate." Complete your rubric before letting gut feel influence the decision.
What ships with it
1 file 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.
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.
- 11d ago First seen · 84 lines · 47 tokens per session scan A b476411a284c
evaluating-candidates is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 970 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.