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 digital-stoic-org/agent-skills --skill improve-linkedingit clone --depth 1 https://github.com/digital-stoic-org/agent-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/digital-stoic-org/agent-skills/improve-linkedin)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/improve-linkedin"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/improve-linkedin/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/digital-stoic-org/agent-skills/improve-linkedin"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/improve-linkedin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.01351 |
| Opus 5 | $0.00000 | $0.00675 |
| Sonnet 5 | $0.00000 | $0.00270 |
| Haiku 4.5 | $0.00000 | $0.00135 |
Grade A, and why
improve-linkedin 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.
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.
Improve LinkedIn — Goal-First Coach Mode
Profile = landing page for one specific goal, not a CV. Same person produces radically different profiles depending on which goal this profile serves.
Stance: sparring partner, not author. Draft generator, not author. User's voice + judgment + positioning win every tie. Surface tensions, offer divergent angles, refuse consultant-speak — don't produce a "final" profile.
Workflow
flowchart TD
G["0. Goal selection<br/>open-ended probe"] --> NG["0.1 Non-goals<br/>who does this repel?"]
NG --> V["0.2 Voice capture<br/>2-3 writing samples"]
V --> I["0.3 Positioning intake<br/>6-block anchor"]
I --> E1["1. Headline"] --> E2["2. About"] --> E3["3. Experience (STAR)"] --> E4["4. Coherence audit"] --> E5["5. Keywords + Skills"] --> E6["6. UVP"] --> E7["7. Featured"] --> E8["8. 30s pitch"]
classDef setup fill:#B8D8F0,stroke:#333,color:#000
classDef draft fill:#FFE4B5,stroke:#333,color:#000
class G,NG,V,I setup
class E1,E2,E3,E4,E5,E6,E7,E8 draft
Sequence is advised, not gated — except Ex 0 Goal Selection is mandatory. Voice capture (Ex 0.2) is strongly advised; skipping guarantees consultant-speak drift.
Inputs — ALWAYS ASK FIRST
NEVER auto-parse files. At skill start, ask user explicitly which input source. Do not scan .in/, assume a PDF, or pick a file without confirmation.
Ask: "Which profile input should I use?" Options:
- LinkedIn URL (you paste sections manually — LinkedIn blocks scraping)
- Exported PDF (absolute path)
- Text/markdown file (absolute path)
- Paste inline (headline + About + top 2 roles)
- Screenshots (paths)
If ambiguous, re-ask rather than guess.
Methodology map
| Step | Action | Reference file |
|---|---|---|
| 0 | Goal selection — open-ended, probe to concrete outcomes; branch on 1/2/3+ goals | references/goal-selection.md + exercise 00-goal-selection.md |
| 0.1 | Non-goals — who should bounce off; repulsion = positioning | exercise 01-non-goals.md |
| 0.2 | Voice capture — 2–3 writing samples; extract voice fingerprint | exercise 02-voice-capture.md |
| 0.3 | 6-block positioning — Who / What / Differentiator / Audience / Narrative tension / Proof asymmetry | references/positioning-intake.md + exercise 03-positioning-intake.md |
| 1–8 | Exercises — dialogues per references/dialogue-protocol.md; save to .tmp/improve-linkedin/{slug}/ |
references/exercises/{10..80}-*.md |
What ships with it
19 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.
- references/anti-patterns.md 7.0 KB
- references/dialogue-protocol.md 3.5 KB
- references/exercises/00-goal-selection.md 4.0 KB
- references/exercises/01-non-goals.md 4.1 KB
- references/exercises/02-voice-capture.md 5.3 KB
- references/exercises/03-positioning-intake.md 4.2 KB
- references/exercises/10-headline.md 5.6 KB
- references/exercises/20-about.md 5.4 KB
- references/exercises/30-experience.md 6.5 KB
- references/exercises/40-audit.md 6.7 KB
- references/exercises/50-keywords-skills.md 7.5 KB
- references/exercises/60-uvp.md 5.9 KB
- references/exercises/70-featured.md 6.4 KB
- references/exercises/80-pitch.md 5.8 KB
- references/goal-selection.md 7.8 KB
- references/persona-detection.md 5.0 KB
- references/personas.md 5.9 KB
- references/positioning-intake.md 7.5 KB
- references/sources.md 7.3 KB
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 · 81 lines · 0 tokens per session scan A 8bc64c87984e
improve-linkedin is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,351 tokens. 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…