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 minhnv0807/ai-business-skills --skill 65-team-performance-review-globalgit clone --depth 1 https://github.com/minhnv0807/ai-business-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/minhnv0807/ai-business-skills/65-team-performance-review-global)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/65-team-performance-review-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/65-team-performance-review-global/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/minhnv0807/ai-business-skills/65-team-performance-review-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/65-team-performance-review-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00167 | $0.01908 |
| Opus 5.5 | $0.00067 | $0.00763 |
| Sonnet 5.5 | $0.00033 | $0.00382 |
| Haiku 4.5 | $0.00017 | $0.00191 |
Grade A, and why
65-team-performance-review-global 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 1mo 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Performance Review (Global)
A review is not a grade — it exists so the person knows what to do to get better. Feedback without data is opinion; feedback with data is coaching. There should be no surprises in a review: feedback is given continuously through the period, and the review only summarizes it.
Information gathering
Read the brief history (64-team-brief-global), last period's output, and the reports (07-marketing-report-global) if available. If missing, ask up to 4 questions:
- Who is being reviewed, in what role, for what period? Content writer / designer / media buyer / channel owner; monthly or quarterly.
- What KPIs were set at the start of the period? If none were set, this review can only be qualitative — say so explicitly in the document.
- Concrete output data: pieces published, assets delivered, CPA/ROAS on campaigns they own, on-time rate, revisions per task.
- Specific observations from the period: 2-3 real situations (positive and negative) with dates.
Principles
- No surprises. Negative feedback is given when it happens, not saved for review day.
- Every statement needs evidence. "Hard-working" is not an assessment; "on time on 9 of 10 tasks, proposed two new content angles unprompted" is.
- Assess behavior, not character. Write "submitted late 3 times without notice", not "irresponsible".
- Rate consistently. Apply the same standard across the team; do not let personal rapport shift the scale.
- A review must produce a development plan. Without one it is just an unusable scorecard.
- The document is confidential. Leader and reviewee only.
Documentation caution
In many jurisdictions, written performance documentation carries employment-law weight and can be produced as evidence in a dispute. Write it accordingly:
- Record observable behavior and measurable outcomes with dates — what was delivered, when, against what agreed standard.
- Avoid subjective characterizations, comparisons to other individuals, and anything touching protected characteristics (age, gender, race, religion, disability, pregnancy, national origin, or similar).
- Do not put speculation about a person's attitude, motives, personal circumstances, or health in the document.
- Keep this review separate from any discussion of discipline, termination, or compensation changes. This skill does not give legal or HR advice. Anything termination-adjacent, any performance improvement plan with employment consequences, and any cross-border reporting line should go to HR or employment counsel before it is written or delivered.
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.
- 1mo ago First seen · 155 lines · 167 tokens per session scan A 01d97354368e
65-team-performance-review-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (631 stars, last pushed yesterday), licensed MIT. It adds 167 tokens to every session and 1,908 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
sdlc-review
Review Kanban handoffs and route verified outcomes.
teams-meeting-pipeline
Teams meeting summaries, job replay, Graph subscriptions.
action-items
Manage your private to-do list for the user. Use to add or update tasks, record what they are waiting on, track blockers, mark tasks complete or canceled, and clean up the list. Not for Dreamers or external task trackers.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
ghl
Use HighLevel contacts, pipelines, appointments, messages, and its broader operation catalog.