using-neon-jetpack
Skill0 starsChanged 3 months agoMITView on GitHub
Use when any writing, review, research, or shipping task begins — reviewing, polishing, or shipping human-facing writing or web pages, mapping a user journey, or protecting creative work. Routes to the right neon-jetpack skill (line-edit, ai-written-check, cringe-check, full-review, ux-web-design-review, journey-map, copyright-creative-work) and defines how they chain, so the right depth of review runs in the right order.
In this repository7 other files it gives its agents.
- ai-written-checkSkill
- copyright-creative-workSkill
- cringe-checkSkill
- full-reviewSkill
- journey-mapSkill
- line-editSkill
- ux-web-design-reviewSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Creative work ships with rights handled: If the deliverable is a song, photo set, or piece of writing headed for release, …
- Distinctive: line 33
Never silently inflate a claim: If an edit would make a claim bigger than the stated truth, stop and ask.
- Distinctive: line 35
Say what you didn't do: Every review ends by naming which passes ran and which didn't, so "reviewed" never overstates coverage.
≈ “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.
Files
Using neon-jetpack
neon-jetpack is a team of seven skills that take a piece of human-facing work from draft to shipped: polish the sentences, strip machine tells, fix the tone, verify the claims, check the page it lives on, map the user journey behind it, and protect it if it's creative work. This skill is the dispatcher — read it, pick the right skill(s), and run them in order.
The routing table
| The user's situation | Skill | Depth |
| "Polish this," "proofread," "tighten this email" — a draft they wrote, sentence-level only | line-edit | Light |
| "Does this sound like AI?" — mechanical tells in prose | ai-written-check | Focused |
| "Does this sound cocky / try-hard / like sucking up?" — tone and positioning | cringe-check | Focused |
| "Review my copy" for anything high-stakes: resume, cover letter, portfolio, case study, proposal, bio | full-review | Deep — orchestrates the two checks above plus honesty, register, and fact passes |
| "Review my site / page / landing page UX" — layout, readability, hierarchy, trust | ux-web-design-review | Focused |
| "Map the journey / build a journey map / chart the experience" — turning research or funnel data into a milestone map | journey-map | Focused — interviews for inputs, builds incrementally |
| Releasing a song, publishing writing or photos, registering copyright, splits with collaborators | copyright-creative-work | Focused |
How the team chains
- Escalate, don't duplicate.
line-editis grammar and clarity only; if tone or honesty problems surface mid-edit, finish the line edit, then recommend the matching check — don't improvise a tone review inside a line edit. full-reviewis the orchestrator. It invokesai-written-checkandcringe-checkas passes 1 and 4. Never run those two separately and then also runfull-review— that duplicates work. Either run a focused check alone, or runfull-reviewand let it delegate.- Copy going onto a web page gets two lenses.
ux-web-design-reviewjudges whether the page is scannable and usable;full-review(or the focused checks) judges whether the words are honest and human-sounding. For a page about to go live, run UX first (structure), then copy review (words) — structural changes invalidate copy edits, not the other way around. - Creative work ships with rights handled. If the deliverable is a song, photo set, or piece of writing headed for release,
copyright-creative-workruns before publication, after all copy passes are done. - Research artifacts feed copy, then get the copy treatment.
journey-mapproduces the evidence-tagged map; if its narrative summary or readout copy is headed to stakeholders or a portfolio, that prose goes throughline-editorfull-reviewlike any other writing. The map's ASSUMED flags are the same never-inflate rule applied to research claims.
Ground rules (apply to every skill in the pack)
- Sign-off before changes. Present findings; don't rewrite the author's work without explicit approval.
line-editis the one exception (it hands back a clean version plus a judgment-call list to overrule). - Never silently inflate a claim. If an edit would make a claim bigger than the stated truth, stop and ask.
- Preserve voice. A rough, specific sentence beats a smooth, generic one. These skills subtract noise; they don't add polish-paste.
- Say what you didn't do. Every review ends by naming which passes ran and which didn't, so "reviewed" never overstates coverage.
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
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.