agentleFS
ric03uecric03uec/clawrium/skills/hermes/blog-author/SKILL.md

blog-author

Skill67 starsChanged 2 months agoApache-2.0View on GitHub

Watch ric03uec/clawrium release tags; draft a short blog post per user-visible feature as a PR against blog/.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Add the tag to blog-author:tagged only after the PR opens cleanly.

    line 80
  2. Distinctive:

    Never merge your own PRs.

    line 88
  3. Very specific:

    Never push to main directly.

    line 89
  4. Very specific:

    Never publish (move out of status: draft).

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

blog-author

Poll ric03uec/clawrium release tags every 30 minutes. For each new tag, draft a short blog post per user-visible feature and open a PR against blog/. The post is a draft for human review and editing — never publish on your own.

Inputs

  • gh release list --repo ric03uec/clawrium --limit 5 and the per-release gh release view <tag> --json body,tagName,publishedAt.
  • The diff between the previous tag and this one for surface area context: git log <prev>..<tag> and selective git show on commits the release notes call out.
  • Existing scenarios under scenarios/ — the post must reference at least one runnable snippet (see "Output" below).
  • Memory key blog-author:tagged — release tags already drafted.

Triage rule — what gets a post

Each user-visible feature in the release notes gets its own post. Bundled posts produce shallow writeups; split aggressively.

A change qualifies if it falls into one of:

  • New clawctl command, option, or workflow.
  • New agent type, integration, channel, or skill.
  • New GUI route or page.
  • Behavior change a user would notice on upgrade.

Skip:

  • Internal refactors, dependency bumps, test changes.
  • Documentation-only or scenario-only edits.
  • Security fixes — let the maintainer write those by hand.

Output — PR

For each qualifying feature, open a PR against main titled:

blog: <tag> — <feature one-liner>

The PR adds one file: blog/<YYYY>-<MM>-<DD>-<slug>.md.

Required front-matter:

---
title: <feature one-liner>
date: <YYYY-MM-DD from release publishedAt>
tag: <release tag>
status: draft
author: maurice
---

Required structure (short — aim for ~250–400 words):

  1. What changed — one paragraph in engineer voice.
  2. Why — one paragraph, lifted/condensed from the release notes or linked issue. No marketing fluff.
  3. Try it — at least one runnable snippet from scenarios/ or built from the actual CLI signatures in src/clawrium/cli/. The snippet must work on a fresh clawrium install at this tag.
  4. Links — release notes URL, the primary PR(s).

Add the tag to blog-author:tagged only after the PR opens cleanly.

Hard constraints

  • One feature, one post, one PR. No combined posts.
  • Snippet runnability is non-negotiable: if you can't find a valid scenario or construct one from real CLI signatures, drop the post rather than fabricate commands.
  • Never merge your own PRs.
  • Never push to main directly. PR target is main; branch name is blog/<tag>-<slug>.
  • Never publish (move out of status: draft). Human edits drive that.

Voice

  • Engineer to engineer. Same rules as daily-digest: no marketing copy, no hedging, no flattery, emoji only when informational.
  • First-person plural ("we shipped") is fine. Avoid first-person singular — these are project posts, not personal essays.

Anti-patterns

  • Lifting whole paragraphs from the release notes. Rewrite for the blog's reader, who has not seen the changelog.
  • Padding to a minimum word count. 250 words is enough if the feature is small. Cut, do not stretch.
  • Inventing CLI commands or option names. Read the real source.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.