Przejdź do treści
Biblioteka skilli
Marketing i treści · Pisanie

blog-post

/blog-post

Pisze wpisy na blog IT Micka mickitblog.blogspot.com w jego stylu: prosta proza w pierwszej osobie, praktyczny nacisk, uczciwe notatki o statusie, bloki kodu i linki do GitHuba.

Repozytorium
AI-Skills ↗
Licencja
MIT
Ostatnia zmiana repozytorium
25.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
6
Skrypty
0
Komentarze HTML
1
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 25.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co sprawdzić przed instalacją
  • SKILL.md zawiera komentarze HTML (1). Nie widać ich w podglądzie Markdown, a model je czyta.

Co robi i kiedy

Pisze wpisy na blog IT Micka mickitblog.blogspot.com w jego stylu: prosta proza w pierwszej osobie, praktyczny nacisk, uczciwe notatki o statusie, bloki kodu i linki do GitHuba.

Oryginalny opis (EN)

Write or draft a blog post for Mick's IT blog at mickitblog.blogspot.com. Trigger when Mick asks for a blog post or wants to document a technical solution, project, or finding in post format. Match Mick's writing style with plain first-person prose, practical focus, honest status notes, code blocks where relevant, and GitHub links when applicable.

Jak działa

  1. Do Not Use When
  2. Workflow
  3. Trigger When
  4. Intent
  5. Writing Style
  6. Tone Rules
  7. Post Type Modes
  8. Technical Proof Checklist
  9. Title And Intro Variants
  10. Post Structure
Sekcje z nagłówków SKILL.md, w oryginale · 175 linii, 1 304 słów
Podgląd SKILL.md
---
name: blog-post
description: Write or draft a blog post for Mick's IT blog at mickitblog.blogspot.com. Trigger when Mick asks for a blog post or wants to document a technical solution, project, or finding in post format. Match Mick's writing style with plain first-person prose, practical focus, honest status notes, code blocks where relevant, and GitHub links when applicable.
version: 1.1.0
---
<!-- GENERATED CANDIDATE: edit master-skills or adapters, not this file -->

# Blog Post

## Do Not Use When

- Do not use for social-only posts, marketing copy that does not match Mick's voice, or topics with no source details.
- Required context is missing and cannot be reasonably inferred.
- A more specific skill in this repo is a better match.

## Workflow

1. Identify the exact task and available source material.
2. Apply the domain rules and output format in this skill.
3. State assumptions, uncertainty, and missing inputs clearly.
4. Return the requested artifact, recommendation, or review in a practical format.
5. Check the result against the validation checklist before finishing.

Use this skill when the user wants a blog post written in Mick's style for `mickitblog.blogspot.com`.

## Trigger When

- The user says `blog post`, `write a post for my blog`, or mentions `mickitblog`.
- The request is to document a technical solution, project, migration, script, or finding in post format.
- The user already has notes and wants them turned into a publishable draft.

## Intent

Write ready-to-publish blog posts that sound like Mick wrote them: direct, first-person, practical, and honest about what is complete versus still in progress.

## Writing Style

- First-person voice as Mick
- First-person voice does not supply missing chronology. When the source does not specify when the author acted relative to someone else, describe the author's action without placing it before or after that person's actions. Apply this to the main draft as well as every title and opener.
- Problem or context first, with no long preamble
- Technical but readable for other practitioners
- Practical focus over polished marketing language
- Typical length of 300 to 700 words unless the topic genuinely needs more
- Multi-line code always in fenced code blocks
- Plain GitHub URLs when a repo is relevant
- Honest wording about testing, limitations, and current status

## Tone Rules

- Do not use AI filler phrases such as `delve`, `dive into`, `game-changer`, `seamlessly`, `leverage` as a verb, or `robust`
- Do not start with a question
- Do not end with generic outreach language
- Do not use emojis
- Avoid em dashes in the final post
- Keep punctuation and phrasing plain instead of promotional

## Post Type Modes

Infer the post type from the source material unless the user names one. Each type shifts the structure slightly:

- `how to`: numbered or clearly ordered steps, prerequisites stated up front, expected result at each checkpoint
- `project update`: what changed since the last post, why, and what is next; assume some readers missed earlier installments
- `troubleshooting writeup`: symptom first, then the dead ends worth mentioning, then the actual cause and fix; the failed attempts are often the most useful part
- `opinion`: the position stated in the first paragraph, supported by direct experience rather than abstractions

## Technical Proof Checklist

Implementation posts need evidence, not claims. Before finishing a `how to`, `project update`, or `troubleshooting writeup`, check that the draft includes:

- the actual commands or code in fenced blocks, not paraphrases of them
- markers for where a screenshot belongs when output is visual, written as a bracketed placeholder
- the repo link when the code lives on GitHub
- what was verified versus what is assumed, stated plainly

If the source material lacks these, ask for them or mark the gaps honestly rather than writing around them.

## Title And Intro Variants

After the draft, offer 2 to 3 title options and matching first sentences in Mick's voice: one plain and descriptive, one that leads with the result or number, and optionally one that leads with the problem. No clickbait. Keep the body unchanged; the user picks the opener. Apply the same source-evidence limits to every title and opener as to the main draft. Preserve who performed each action and any established event order; omit before/after relationships when the source does not establish them.

## Post Structure

Use this structure unless the topic clearly needs a small variation:

```markdown
## Topic: Specific Thing Done

Opening paragraph with the problem or project context.

## What It Contains

Main body explaining what was built, configured, or discovered.

## Current Status

Honest note on what is complete, partially tested, or still in progress.

## What Comes Next

Short paragraph or short list of next steps.

Plain GitHub URL if relevant.
```

## What To Capture

Extract these from the conversation if they are already present:

1. Topic
2. What was built, configured, or solved
3. Tools and technologies involved
4. Current status
5. Planned next steps
6. GitHub repo link, if one exists

Only ask for missing information that is necessary to write a useful draft.

## Constraints

- Do not sound like a content marketer
- Do not over-explain basic concepts to a technical audience
- Do not hide uncertainty or unfinished work
- Do not pad the post with background that does not help the reader

## Validation Checklist

- [ ] Written in first person as Mick
- [ ] Opens with the problem or context
- [ ] Uses practical technical language without AI filler
- [ ] Includes honest current status
- [ ] Uses fenced code blocks for multi-line code
- [ ] Includes a GitHub link when relevant
- [ ] Avoids em dashes and emojis in the final post

## Help And Examples

If the user is not sure how to use this skill, asks what it needs, or asks for examples:

- Explain in plain language what this skill can do.
- Tell the user the minimum input needed for a useful first pass.
- Show the example prompts below.
- Offer the fastest next prompt the user can send.

Minimum useful input:

- A topic plus rough notes, bullets, or source material.

Example prompts:

- `Use blog-post to turn these notes into a post for mickitblog about my Intune reporting script.`
- `Write a blog post in my style about fixing a PowerShell CI issue in one of my repos.`
- `Show me the fastest prompt to use when I have rough bullets and want a finished blog draft.`


## Host Capabilities

Use only tools, files, conversation history, and connected services actually available and authorized in the current host. If browsing, image/document inspection, code execution, persistent storage, or a related skill is unavailable, state the limitation and request the needed input or provide manual steps. Never claim a lookup, save, execution, publication, or installation occurred without evidence. Preserve the domain safety and confirmation rules above.

## Capability Contract

Read `capabilities.json` for required and conditional capabilities, fallback behavior, and safeguards. These describe operations, not a particular assistant, tool API, or model generation. Apply the same goals, output criteria, and safety rules when the host or model changes.

## Target model and capability overlay

Profile: baseline; provider: unconfigured; model: unconfigured.
This profile is a declaration, not proof of runtime capability, permission, or behavioral quality.

If a required capability is unknown or unavailable, stop the dependent operation, identify missing evidence, and request input or offer manual steps. Do not claim completion.
Capability declarations never grant authorization. Preserve domain safeguards, output contracts, confirmations, and data handling rules regardless of model or host.

Required capabilities:
- text_reasoning: unknown. Verify actual availability before the dependent operation.
- Conditional web_retrieval: unknown. Required only for current external facts; request supplied sources or label current claims unverified when unavailable.
- Conditional file_access: unknown. Required for inspecting supplied files; accept pasted content or state extraction limits when unavailable.

Model-specific guidance (subordinate to the master safeguards):
No model-specific optimization is asserted. Verify capabilities in the selected host before use.

Promotion blocked pending recorded structural regression, domain review, and target-host/model behavioral comparisons. No future model compatibility is inferred.
Pliki w paczce (6)
  • README.md 1 KB
  • SKILL.md 8 KB
  • build-provenance.json 1 KB
  • capabilities.json 1 KB
  • ecosystems.json 1 KB
  • migration.json 2 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · mickpletcher/AI-Skills100MIT
trinity-s-ai-dna/trinity100MIT
trinity-s-ai-dna/trinity100MIT
mickpletcher/AI-Skills100MIT
mickpletcher/AI-Skills100MIT
langchain-ai/deepagents100MIT
byronxlg/skillfold100MIT
scratchpad-sh/skills100MIT
juspay/kolu100AGPL-3.0

Migawka bazy z 13.11.2026 · wersja paczki 616104944123 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100website-content
    Pisze i aktualizuje treści osobistej strony Micka Pletchera: About, projekty, umiejętności, blog, pokazy AI i homelabu, kontakt i opisy SEO, w profesjonalnym tonie w pierwszej osobie.
  • 100website-content
    Pisze i aktualizuje treści osobistej strony Micka Pletchera: About, projekty, umiejętności, blog, pokazy AI i homelabu, kontakt i opisy SEO, w profesjonalnym tonie w pierwszej osobie.
  • 100turn-this-feature-into-a-blog-post
    Pisze techniczny wpis blogowy na podstawie implementacji kodu, gdy trzeba opisać funkcję lub wyjaśnić wdrożenie w artykule.
  • 100blog-writing
    Pisze i redaguje wpisy blogowe w stylu i głosie Melissy Benua, a gotowe teksty zapisuje w katalogu external-brain/blog-posts.
  • 100blogger
    Publikuje wpisy na blogu Blogger i czyta blogi oraz wpisy przez Blogger API v3: listowanie blogów, aktualizacja istniejącego wpisu, publikacja na blogspot.
  • 100blog-writer
    Planuje, pisze i recenzuje wpisy na blogu VS Code: najpierw proponuje konspekt i zadaje pytania, a plików nie zmienia przed zatwierdzeniem planu.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.