agentleFS
jajupmochijajupmochi/agent-harness/.claude/skills/publish/SKILL.md

publish

Skill1 starsChanged 4 months agoMITView on GitHub

Tag a new version of agent-harness, push to GitHub, and create a GitHub release. Use when shipping a meaningful update (new rules, new templates, etc.). Asks for SemVer bump and writes release notes from git log.

  • Deletes or force-pushes
  • Commits and pushes

67 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use clips, outliers and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MelvynxSkill

    clips

    Turns one long video (YouTube link, podcast, webinar, livestream, or a local file) into finished vertical shorts. Use when the user says long to short, repurpose, long video to shorts, clips from my video, podcast clips, cut my YouTube video into shorts, or gives a long video link. Finds clips that stand alone (one idea, 20 to 60 seconds), scores them, cuts them and edits each one with short-editing (split-screen paper look, captions, cuts, hook, boards, 1080x1920), and writes new scripts in the studio-script format from the ideas too spread out to clip. Reads YouTube captions and chapters with yt-dlp, or transcribes a local file with the short-editing engine (whisper.cpp, free, offline).

    Also in 3 projects that use this

  • MelvynxSkill

    outliers

    Finds the outlier reels of Instagram accounts or videos of TikTok accounts (3x their own account's median views or more) through Treg and turns the 5 best into remake scripts in the creator's voice. Two modes - /outliers @handle digs one account; /outliers with no account starts from the creator's own reels, uses and grows a competitor watchlist (video-agent/competitors.json, 70 % main language / 30 % second language when they watch two), ranks every account's outliers against its own median and writes 5 scripts into video-agent/scripts/. Use when the user says outliers, find outliers, what blew up for my competitors, what works in my niche, find me videos to remake, ideas from @someone, what blew up on TikTok.

    Also in 3 projects that use this

  • khadinakbarlabsSkill

    keywords

    Research and prioritize SEO keywords, search intent, topic clusters, competitor keyword gaps and keyword-to-page mappings. Use when asked what to rank for, keyword opportunities, long-tail keywords, a content calendar, or a keyword plan. Uses owned Apify keyword/SERP Actors with approved budgets, or supplied exports offline. Does not invent volume or organic difficulty.

    Also in 3 projects that use this

  • MicrosoftSkill

    create

    Also in 4 projects that use this

  • justinseger015-ctrlSkill

    edit

    Edit a video using the video-editing orchestrator. Detects format, routes to correct editing skill, and executes the full process. Use when user says: /edit, edit video, edit clip, edit this, make it polished, finish editing, polish this video.

    Also in 3 projects that use this

  • LangChainSkill

    render

    Turn an SVG design into a PNG and look at it. Use after you write or change a design, but only if execute is one of your tools.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 56 edited versions we read keep these.

  • 3

    Distinctive

    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
  1. Distinctive:

    If no bump type is given, asks interactively.

    line 17
  2. Distinctive:

    Verify the working tree is clean (git status — no uncommitted changes)

    line 21
  3. Distinctive:

    Verify on main branch (not a feature branch)

    line 22
  4. Very specific:

    Verify origin is git@github.com:jajupmochi/agent-harness.git (or HTTPS equivalent)

    line 23
  5. Very specific:

    Verify gh CLI is authenticated (gh auth status)

    line 24
  6. Very specific:

    If no tags exist, current version is v0.0.0.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 56 edited versions of this file we could read. “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

/publish

Cut a new release of agent-harness.

Usage

/publish [<patch|minor|major>]

If no bump type is given, asks interactively.

Pre-flight

  • Verify the working tree is clean (git status — no uncommitted changes)
  • Verify on main branch (not a feature branch)
  • Verify origin is git@github.com:jajupmochi/agent-harness.git (or HTTPS equivalent)
  • Verify gh CLI is authenticated (gh auth status)

Steps

  1. Determine current version:

    git tag --list 'v*' --sort=-v:refname | head -1

    If no tags exist, current version is v0.0.0.

  2. Ask user for bump type (or use the argument):
    • patch (v0.1.0 → v0.1.1) — bug fix, doc tweak, no API change
    • minor (v0.1.0 → v0.2.0) — new rule / skill / hook / recommendation, no breaking change
    • major (v0.1.0 → v1.0.0) — breaking change to consumer interface (rare)
  3. Compute new version and confirm with user.
  4. Generate release notes from git log since last tag:

    git log <prev-tag>..HEAD --oneline | grep -E '^\w+ (feat|fix|docs|chore|refactor)' > /tmp/release-notes.md

    Group by Conventional Commit type. Edit if needed.

  5. Run final verification:
    • jq empty on every *.json in the repo
    • Markdown link check (best-effort): find . -name "*.md" -exec grep -l "](" {} + — manually skim suspicious entries
    • Privacy scan: invoke /privacy-redact on key files (README, INVENTORY, recommendations/) — should report 0 findings before publish
  6. Create the tag:

    git tag -a <new-version> -m "Release <new-version>"
    git push origin main
    git push origin <new-version>
  7. Create GitHub release:

    gh release create <new-version> \
      --title "agent-harness <new-version>" \
      --notes-file /tmp/release-notes.md
  8. Optional: announce the release (Telegram channel, blog, etc. — out of this skill's scope).

Anti-patterns

  • ❌ Tagging without first running the privacy scan — public release, can't easily redact later
  • ❌ Skipping the git status check — committing pending work in a release tag is messy
  • ❌ Force-pushing the tag (git push --force origin <tag>) — breaks any consumer pinning to the version

Companion

  • docs/CONTRIBUTING.md — Conventional Commits convention
  • skills/general/privacy-redact/SKILL.md — required pre-publish scan

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.