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 inklate/social-skills --skill idkgit clone --depth 1 https://github.com/inklate/social-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/inklate/social-skills/idk)<a href="https://agentmods.dev/skills/inklate/social-skills/idk"><img src="https://agentmods.dev/badge/skills/inklate/social-skills/idk/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/inklate/social-skills/idk"><img src="https://agentmods.dev/badge/skills/inklate/social-skills/idk.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 | $0.00125 | $0.01117 |
| Opus 5 | $0.00063 | $0.00558 |
| Sonnet 5 | $0.00025 | $0.00223 |
| Haiku 4.5 | $0.00013 | $0.00112 |
Grade A, and why
idk 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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Map what the user wants onto the one social skill whose procedure fits, and hand them the phrase that triggers it. Route, don't perform — the named skill does the work.
Context
Read social-context.md at the project root (also check .agents/social-context.md). If it
is missing, the user hasn't been set up: your first recommendation is always the
social-context skill ("set up my social context"), because every other skill reads that
file. If it exists, setup is done — route straight to the task skill.
Workflow
- Name the job in one line. Restate what the user is trying to produce or decide — one post, a thread, a week of content, a plan, ad copy, a fix, an audit. If it is ambiguous, ask one question; don't guess across two different procedures.
- Match the job to exactly one skill using the Skill map below. Match on the procedure the user needs, not the platform — platform is a constraint each skill already handles.
- Check the prerequisite. If
social-context.mdis missing, recommendsocial-contextfirst, then the task skill. If the task leans on voice and the Voice section is thin, suggestsocial-voicealongside. - Hand off. Name the skill, say in one line why it fits, and give the trigger phrase the user can say to invoke it. If two skills genuinely both fit (one post vs many), present the pair with the one-line difference and let the user pick.
Skill map
| The user wants to… | Skill | Trigger phrase |
|---|---|---|
| Set up who they are / audience / pillars / red lines | social-context |
"set up my social context" |
| Teach the agent their writing voice | social-voice |
"learn my voice" |
| Write one post for one platform | social-post |
"write a LinkedIn post about…" |
| Write a thread / multi-post sequence | social-thread |
"turn this into an X thread" |
| Build an Instagram/LinkedIn carousel | social-carousel |
"make a carousel about…" |
| Get scored hook options for a draft | social-hook |
"give me hooks for this" |
| Adapt one message across many platforms at once | social-crosspost |
"post this on LinkedIn, X, and Instagram" |
| Mine one source into a week of different posts | social-repurpose |
"turn my blog into a week of posts" |
| Triage and reply to comments/mentions/DMs | social-reply |
"help me reply to these comments" |
| Write paid ad copy variants | social-ad |
"write Facebook ad variants" |
| Plan a 2-week content calendar | social-calendar |
"plan my next two weeks" |
| Validate a draft before posting | social-check |
"will this work on Instagram?" |
| Audit a profile / content history vs goals | social-audit |
"audit my LinkedIn" |
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.
- 12d ago First seen · 81 lines · 125 tokens per session scan A 23b629a38ed1
idk is a skill published in the GitHub repository inklate/social-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 1,117 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…