Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

using-chrisbanes-skills

skill · chrisbanes/skillsApache-2.0 licenceAudited 31 Oct 2026 · source f5fa5d08102c

★ 1,134pushed today
✓SAFEGrade B · 89/100 · 31 Oct 2026 · f5fa5d0
1,134repo stars · whole chrisbanes/skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit f5fa5d08102c and found no filesystem, network or shell access and no hard-coded secrets. What it does: Use when routing Kotlin or Jetpack Compose work, or physical Android benchmark evidence that needs a configuration decision, especially when several Kotlin or Compose concerns overlap.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “using-chrisbanes-skills (chrisbanes/skills)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/chrisbanes/using-chrisbanes-skills

Trust audit

Audit 0.4.1 · source read 31 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS1
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

Audit 0.4.1 · source sha f5fa5d08102c · 31 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherchrisbanes GitHub userOwner of the repository this skill is read from
  • Source folderchrisbanes/skills/skills/using-chrisbanes-skillsThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdictf5fa5d08102cA new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Use when routing Kotlin or Jetpack Compose work, or physical Android benchmark evidence that needs a configuration decision, especially when several Kotlin or Compose concerns overlap.

---
name: using-chrisbanes-skills
description: Use when routing Kotlin or Jetpack Compose work, or physical Android benchmark evidence that needs a configuration decision, especially when several Kotlin or Compose concerns overlap.
---

# Using chrisbanes skills

## Core principle

Route by the decision the code needs, not by the number of APIs mentioned.
Load one cluster when its shared procedure owns the concern; add a specialist
only when its independent behavior changes the same work.

## Routing procedure

1. Read the task. For Kotlin or Compose work, inspect the source that makes the
   concern concrete. For an Android benchmark comparison, inspect the supplied
   reports, configurations, and traces instead.
2. If one focused skill clearly matches, load it directly and stop routing.
3. Before loading a Compose skill, point to a concrete Compose API or composable
   in the inspected source, or to an explicit request to create or design
   Compose code. A hypothetical UI consumer is not evidence. If neither form
   of evidence exists, stay in the Kotlin cluster even when the task mentions
   UI, routes, or navigation.
4. Match each observed code signal to the table below.
5. Add a second skill only when it owns an independent decision in the same
   change; do not load adjacent skills speculatively. For example, a flow
   delivery defect plus a separate catch-all over a sealed route needs both
   `kotlin-concurrency-and-flow` and `kotlin-control-flow`. Load the latter
   because the branch mapping needs an explicit decision, including whether a
   data-bearing subtype's payload is used through a smart cast or deliberately
   discarded, not merely because a `when` appears in the file.
6. Finish routing when every material concern has one focused owner and those
   skills are loaded before advice or edits.

## Common routes

| Task signal | Start with |
|---|---|
| Evidenced Compose state, effects, screen ownership, or UI event collection | [`compose-state-and-effects`](../compose-state-and-effects/SKILL.md) |
| Recomposition, stability, frame-rate reads, back-writing, or `@ReadOnlyComposable` | [`compose-performance`](../compose-performance/SKILL.md) |
| Component modifiers, caller placement, slots, or public content shape | [`compose-component-design`](../compose-component-design/SKILL.md) |
| Visibility, value, transition, content-swap, or other motion API choice | [`compose-animations`](../compose-animations/SKILL.md) |
| Keyboard, TV, D-pad, focus targets, custom traversal, or key events | [`compose-focus-navigation`](../compose-focus-navigation/SKILL.md) |
| Compose UI, screenshot, semantics, focus/key, or interaction-state tests | [`compose-ui-testing-patterns`](../compose-ui-testing-patterns/SKILL.md) |
| Coroutine ownership, raw `Thread` or `Executor` work, cancellation, Flow state/events, sharing, or replay | [`kotlin-concurrency-and-flow`](../kotlin-concurrency-and-flow/SKILL.md) |
| Kotlin classification, `when`, guards, exhaustiveness, smart casts, or null branches | [`kotlin-control-flow`](../kotlin-control-flow/SKILL.md) |
| Kotlin function ownership, domain types, expect/actual, or platform seams | [`kotlin-api-design`](../kotlin-api-design/SKILL.md) |
| Planned Gradle execution or a Gradle-centered warning/failure workflow | [`gradle-run`](../gradle-run/SKILL.md) |
| Comparing physical Android benchmark configurations, reversed rankings, or an Android default | [`android-benchmark-comparison`](../android-benchmark-comparison/SKILL.md) |
| Unreleased changelog maintenance or specified-release notes | [`changelog`](../changelog/SKILL.md) |
| Kotlin library release preparation, publication, or readiness | [`release-kotlin-library`](../release-kotlin-library/SKILL.md) |
| One ready GitHub issue or in-chat task needs repository-aware planning | [`to-plan`](../to-plan/SKILL.md) |
| Polling PRs/MRs, review comments, CI failures, or routine follow-up | [`shepherd`](../shepherd/SKILL.md) |

## Combination boundaries

- Add [`kotlin-concurrency-and-flow`](../kotlin-concurrency-and-flow/SKILL.md)
  to Compose state work only when delivery, replay, sharing, or cancellation is
  a separate concern. Add state ownership or performance only when animation
  work changes that concern too.
- Pair focus navigation with UI testing when the task also needs a test shape.
  For a focus-aware `AnimatedContent` swap, load Compose animations as well:
  rendering each outgoing and incoming branch from its content-lambda target
  is a separate identity decision from focus timing and the interaction test.
- Add [`kotlin-control-flow`](../kotlin-control-flow/SKILL.md) when a Kotlin
  concern also has an independent branch decision, such as a catch-all over a
  sealed result that hides cases or branch payload. Plain route delivery with
  no separate branching issue does not need it. Do not add Compose without the
  evidence required in step 3.
- Encapsulating a Compose snapshot property behind a read-only public accessor
  remains one state-ownership decision. Do not add `kotlin-api-design` merely
  because the accessor is public; add it when the same change also needs a
  separate function-ownership, domain-type, compatibility, or platform-boundary
  decision.
- Load [`gradle-run`](../gradle-run/SKILL.md) only for planned Gradle execution
  or an existing Gradle workflow, not incidental Kotlin or Compose advice.

Excerpt, first 5,402 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit f5fa5d0

Download folder ↗
git clone https://github.com/chrisbanes/skills
git -C skills checkout f5fa5d08102c

The author documents no install command, so this uses the repository directly. Our verdict covers commit f5fa5d08102c only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source f5fa5d08102c

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/chrisbanes/using-chrisbanes-skills/badge.svg)](https://modelsatlas.com/skills/chrisbanes/using-chrisbanes-skills/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/chrisbanes/using-chrisbanes-skills/badge.svg)](https://modelsatlas.com/skills/chrisbanes/using-chrisbanes-skills/)

Questions about using-chrisbanes-skills

What does the using-chrisbanes-skills skill do?
Skills for Kotlin, Jetpack Compose, and Android development
Is using-chrisbanes-skills safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can using-chrisbanes-skills access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
What do I need installed to use using-chrisbanes-skills?
Its own instructions reference to-plan. Dependencies are pinned to exact versions.
How current is this page?
The grade is for one exact copy of the source (f5fa5d08102c), read on 2026-10-31. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.