contribute
Skill0 starsChanged 29 days agoMITView on GitHub
Use when someone says "I have an idea", "I want to add / change / fix something" in inite-visibility (the INITE AI-visibility MCP server — local robots/identity/page checks plus the inite.ai bridge) — runs idea → spec → plan → change → tests → gates → PR, stopping at red zones and explaining each step in plain words.
- Commits and pushes
16 other projects use a version of this.
Adopted by
Most recently taken up by
- gdhub-io/character-forge-mcptheir own version, first seen Nov 15, 2026
- egregore-labs/egregoretheir own version, first seen Nov 6, 2026
- grafana/gcxtheir own version, first seen Nov 2, 2026
- Devolutions/IronRDPtheir own version, first seen Nov 1, 2026
- inite-ai/inite-brain-servicetheir own version, first seen Nov 1, 2026
- manor-os/manor-aitheir own version, first seen Oct 31, 2026
Used with
Projects with it also use review-pr.
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.
DockerSkillreview-pr
Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.
Also in 3 projects that use this
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- mindfold-ai/Trellis★ 15ksame name
- gluestack/gluestack-ui★ 5.3ksame name
- Devolutions/IronRDP★ 3.3ksame name
- grafana/gcx★ 819same name
- egregore-labs/egregore★ 293same name
- manor-os/manor-ai★ 158same name
- inite-ai/inite-brain-service★ 43same name
- yusukebe/skills★ 36same name
- zajca/pohunek★ 9same name
- marwan562/agents-skills★ 8same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 51
Run, and show the person the result:
- Distinctive: line 59
All green, or explain what failed and fix it.
“Common” is measured: kept by at least 6 in 10 of the 15 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.
Files
/contribute — inite-visibility
The person may not be an engineer. Say what you are doing, and why, in plain
words at every step. AGENTS.md is the source of truth; re-read the section a
step names when unsure.
1. Understand
Restate the idea in two or three plain sentences. Ask at most 3 clarifying questions — only ones whose answer changes what gets built.
2. Does it belong here?
This repo holds the three local checks and a bridge. The score, the
full audit (analyze_site, get_analysis), the portal and the Atlas tools
live in the inite.ai service, not here. If the idea is about those, say so,
offer /spec-idea to file it, and stop. Local checks report facts, never a
score (AGENTS.md rule 3) — an idea that needs weights or a model call belongs
to the service too.
Search first:
gh issue list -R inite-ai/inite-visibility --search "<key words>" --state all.
3. Zone and spec
Find the zone in AGENTS.md "Zones"; tell the person which and what it means. Spec: problem · what the tool will report · tool surface change (new tool or new optional input only) · what gets fetched from the site · risks · out of scope.
- Red (
publicUrl/getinsrc/checks.ts, the bridge insrc/index.ts,src/auth.ts, renaming/removing a tool or input,package.jsonidentity,server.json): stop. Show the spec, get a yes, file it with the "Product idea" template (/spec-ideadoes this), and explain that a maintainer approves the design before code.
4. Plan, then build — tests first
Branch from main: git switch -c feat/<slug>. Follow AGENTS.md
"Architecture map → Add a local tool" step by step. Write the test in
test/checks.test.js first (pure helper, no network), watch it fail, then
implement. Update the README "Tools" table when tools change.
5. Gates
Run, and show the person the result:
npm ci
npm run build
npm testAll green, or explain what failed and fix it. Never skip or delete a test to get green.
6. Commit and PR
Conventional commits (feat(checks): …, fix: …, docs: …). No version
bump unless a maintainer asked for a release (AGENTS.md rule 8). Then:
git push -u origin HEAD
gh pr create --fill # then edit the body to follow .github/PULL_REQUEST_TEMPLATE.mdFill every section: plain-language summary, zone, gates, tests, AI-assisted disclosure. Share the link and what happens next: CI runs, a maintainer reviews.
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.

