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 liqiongyu/lenny_skills_plus --skill evaluating-candidatesgit clone --depth 1 https://github.com/liqiongyu/lenny_skills_plusWrote 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/liqiongyu/lenny_skills_plus/evaluating-candidates)<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/evaluating-candidates"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/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/liqiongyu/lenny_skills_plus/evaluating-candidates"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/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 | $0.00030 | $0.02090 |
| Opus 5 | $0.00015 | $0.01045 |
| Sonnet 5 | $0.00006 | $0.00418 |
| Haiku 4.5 | $0.00003 | $0.00209 |
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 13d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluating Candidates
Scope
Covers
- Defining an explicit hiring bar (what “great” means for this role at this company, right now)
- Turning interviews, work samples/trials, and references into evidence, not vibes
- Designing job-relevant work samples (and paid trials when appropriate)
- Running high-signal reference checks and integrating them into the decision
- Producing a decision-ready recommendation with clear risks and mitigations
When to use
- “Help me decide whether to hire this candidate.”
- “Create a scorecard and decision memo based on interview notes + references.”
- “Design a work sample / take-home (or paid trial) and a scoring rubric.”
- “Plan and run reference checks; give me a summary and recommendation.”
- “Calibrate our hiring bar for a and compare candidates fairly.”
When NOT to use
- You need to define the role outcomes or write the job description (use
writing-job-descriptions) - You need to design/run structured interviews and question maps (use
conducting-interviews) - You need to negotiate an offer or close a candidate (use
negotiating-offers) - You need to build a sales team hiring pipeline or GTM hiring strategy (use
building-sales-team) - You need legal/HR compliance guidance or to adjudicate high-risk employment issues (this skill is not legal advice)
- You need compensation/offer negotiation strategy (use
negotiating-offers)
Inputs
Minimum required
- Role + level + function (e.g., “Senior PM”, “Founding AE”, “Staff ML Engineer”)
- Company/team context and “what’s hard” (stage, constraints, velocity expectations)
- Evaluation criteria (4–8 competencies) and any non-negotiables / red flags
- Candidate materials available (resume/portfolio + interview notes, if already interviewed)
- Which signals you want to include: interviews, work sample/take-home, paid trial, references
- Constraints: timeline, confidentiality/PII rules, internal-only vs shareable output
Missing-info strategy
- Ask up to 5 questions from references/INTAKE.md (3–5 at a time).
- If criteria or notes are missing, propose a default criteria set and clearly label assumptions.
- Do not request secrets. If notes contain sensitive info, ask for redacted excerpts or summaries.
What ships with it
13 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.
- eval/eval_config.json 1.5 KB
- eval/SHOWCASE.md 4.7 KB
- eval/with_skill.md 37 KB
- eval/without_skill.md 18 KB
- README.md 1.3 KB
- references/CHECKLISTS.md 1.9 KB
- references/EXAMPLES.md 906 B
- references/INTAKE.md 1.6 KB
- references/RUBRIC.md 4.4 KB
- references/SOURCE_SUMMARY.md 1.7 KB
- references/TEMPLATES.md 3.8 KB
- references/WORKFLOW.md 3.8 KB
- skillpack.json 383 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.
- 13d ago First seen · 135 lines · 30 tokens per session scan A 20d23b49d41b
evaluating-candidates is a skill published in the GitHub repository liqiongyu/lenny_skills_plus (52 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,090 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
cangjie-skill
A process for turning a book, course, podcast, interview, long video, or other long material into reusable instructions for an AI agent. It extracts methods and principles, checks them, and packages them as skills.
plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…
loop-library
Compatibility alias for Loopy. Use only when an existing installation or older instruction explicitly invokes loop-library; use Loopy for new installations and requests. Provides the same discovery, recommendation, audit, repair, adaptation, guided crafting, bounded execution, run debrief, project loop saving, and…
naval-almanack
A reference guide for applying ideas from The Almanack of Naval Ravikant, a book about wealth, work, happiness, judgment, and long-term thinking. It routes questions to the relevant topic guidance and notes when professional help is needed.
decision-heuristics
A set of heuristics for making difficult personal decisions such as changing jobs, buying a home, moving, forming a partnership, or getting married. It is intended for major choices, not everyday decisions.
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.