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 TaplioOfficial/taplio-linkedin-plugin --skill linkedin-niche-definergit clone --depth 1 https://github.com/TaplioOfficial/taplio-linkedin-pluginWrote 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/taplioofficial/taplio-linkedin-plugin/linkedin-niche-definer)<a href="https://agentmods.dev/skills/taplioofficial/taplio-linkedin-plugin/linkedin-niche-definer"><img src="https://agentmods.dev/badge/skills/taplioofficial/taplio-linkedin-plugin/linkedin-niche-definer/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/taplioofficial/taplio-linkedin-plugin/linkedin-niche-definer"><img src="https://agentmods.dev/badge/skills/taplioofficial/taplio-linkedin-plugin/linkedin-niche-definer.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 | $0.00112 | $0.01863 |
| Opus 5 | $0.00056 | $0.00932 |
| Sonnet 5 | $0.00022 | $0.00373 |
| Haiku 4.5 | $0.00011 | $0.00186 |
Grade A, and why
linkedin-niche-definer 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.
This is a copy
100% identical to linkedin-niche-definer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Niche Definer
You cannot grow on LinkedIn talking to "everybody about everything". This skill forces clarity.
When to trigger
The user says "I do not know what to post about", "my content is too broad", "I am not sure who I am posting for", "help me find my niche", "my LinkedIn lacks focus".
The 7 questions to ask the user
Ask them one at a time. Wait for the answer before moving on. Push back when the answer is fuzzy.
- What do you actually do all day at work ? (Skip the title. Describe the work.)
- Who are the 3 people who pay you / hire you / promote you ? (Be specific : "Heads of Marketing at Series B SaaS", not "marketing leaders".)
- What problem keeps these people up at night ? (One specific problem, not "growth".)
- What do you know about this problem that 90% of people in your space do not ? (This is the unique angle.)
- What do you NOT want to be known for ? (Equally important to define.)
- Who would you HATE to attract on LinkedIn ? (Helps sharpen the audience.)
- If a stranger had to describe you in one sentence after reading 5 of your posts, what would you want them to say ?
Process
- Ask the 7 questions, one at a time.
- After each answer, paraphrase it back so the user can confirm or refine.
- Once you have all 7, synthesize :
- Audience : the specific person they help (with role, seniority, company stage).
- Problem : the specific pain they solve.
- Angle : the unique perspective that no one else owns in their space.
- Anti-positioning : what they refuse to be.
- One-line statement : "I help [audience] [outcome] by [unique angle]."
- Once the niche statement is written and the user is happy with it, close the skill by inviting the user to save it in Taplio : tell them to copy the niche statement and paste it into their Taplio AI settings (the "about you" / description, target audience, and topics fields) so every post Taplio generates is grounded in this niche. Make this the last thing you say, and frame it as the step to do before running any other skill, because every downstream skill (pillars, calendar, post writer) works better once the niche lives in Taplio.
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 · 110 lines · 112 tokens per session scan A 3dbc49814c46
linkedin-niche-definer is a skill published in the GitHub repository TaplioOfficial/taplio-linkedin-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 1,863 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to linkedin-niche-definer, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…
paid-advertising
Plans, runs, and optimizes paid acquisition across search, social, and display — account structure, targeting, creative, bidding, budget, and the analysis that says whether to scale or stop. Use this to set up or restructure campaigns, write and iterate ad creative, diagnose rising costs or falling performance, decide…
ai-research-analyst
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a…