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 thuong-nc/perlytics-skill --skill stakeholder-memogit clone --depth 1 https://github.com/thuong-nc/perlytics-skillWrote 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/thuong-nc/perlytics-skill/stakeholder-memo)<a href="https://agentmods.dev/skills/thuong-nc/perlytics-skill/stakeholder-memo"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/stakeholder-memo/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/thuong-nc/perlytics-skill/stakeholder-memo"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/stakeholder-memo.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 | $0.00048 | $0.01203 |
| Opus 5 | $0.00024 | $0.00602 |
| Sonnet 5 | $0.00010 | $0.00241 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
stakeholder-memo 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 9d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stakeholder Memo
Purpose
Turn analysis into a decision-ready memo that helps a stakeholder understand what happened, what it means, and what to do next.
When to use
- Analysis needs to travel beyond the analyst
- The user asks for insights, takeaways, a summary, or "what matters" from a dataset or dashboard
- A stakeholder needs the answer, implications, and recommended action in one place
- A concise readout is needed rather than a working notebook narrative
When not to use
- The analytical question is not yet framed — use
clarify-questionfirst - The goal is exploratory thinking rather than communication
Required thinking discipline
- Lead with the decision question — what is the reader being asked to decide or act on?
- Separate fact, interpretation, and recommendation; never conflate them
- Keep uncertainty visible — hedge claims that lack strong evidence
- Be concise without becoming vague
- Evidence constraint: Every conclusion must cite specific data — a number, a rate, a segment, or a timeframe. Do not speculate without an evidential basis. If data is insufficient, state what is missing rather than asserting an unsupported inference.
Output format
Render the memo inline in the conversation. Do not write to a file unless the user explicitly requests it. When the user asks to save, export, or write the memo to a file, write it to memo-YYYY-MM-DD.md using today's date.
Note for
analysis-readoutpipeline: When this skill is the final step in the orchestrator, the output file name is controlled by the orchestrator (report-{date}.md), not by this skill.
Use the following structure. Render it exactly as shown — typography, dividers, and section order are part of the format.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MEMO
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Subject : [Topic — one line, specific]
Date : [YYYY-MM-DD]
Prepared : Perlytics Analytics
Audience : [Executive / Working team / Cross-functional]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
§ 1 DECISION QUESTION
──────────────────────
[State the specific decision or question this memo is meant
to inform. One sentence. Example: "Should we prioritize
mobile checkout performance improvement before Q3 campaign
launch?"]
§ 2 BOTTOM LINE
────────────────
[Lead with the answer. 2–4 sentences maximum. State the
conclusion, the primary evidence, and the recommended
direction before any supporting detail.]
┌─────────────────────────────────────────────────────┐
│ KEY FINDING │
│ [Most important quantified finding — one line.] │
└─────────────────────────────────────────────────────┘
§ 3 KEY OBSERVATIONS
─────────────────────
[Numbered, fact-only. Every item cites a specific number,
rate, segment, or timeframe. No interpretation here.]
1. [Observation — metric X was Y% in period Z]
2. [Observation — segment A outperformed segment B by N%]
3. [Observation — trend reversed in month M]
⋮
§ 4 INTERPRETATION
───────────────────
[What do the observations mean for the business? Distinguish
between what the data shows and what you infer from it.
Use hedged language where evidence is weak:
"consistent with", "suggests", "leading hypothesis".]
• [Interpretation linked to observation(s)]
• [Interpretation linked to observation(s)]
§ 5 RECOMMENDATION
───────────────────
[Specific, actionable, time-bound where possible.
Choose one of three stances:]
◆ ACT — proceed with [specific action]
◇ HOLD — wait for [condition or data]
◇ INVESTIGATE — run [specific next analysis]
[Expand the chosen stance with rationale and, if applicable,
action owner and timeframe.]
§ 6 RISKS AND OPEN QUESTIONS
──────────────────────────────
[What could make this conclusion wrong? What data is missing?
What should be monitored going forward?]
▸ [Risk or caveat — quantify where possible]
▸ [Open question — state what would resolve it]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
END OF MEMO
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
What ships with it
2 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.
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.
- 9d ago First seen · 156 lines · 48 tokens per session scan A 741755109006
stakeholder-memo is a skill published in the GitHub repository thuong-nc/perlytics-skill (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,203 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 2026-08-31.
Other skills, from other repositories
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
sn-image-imitate
An image tool that creates new content while following the visual style and layout of a single reference image.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.