Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add markoblogo/abvx-agent-skills --skill fluid-interaction-reviewgit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/markoblogo/abvx-agent-skills/fluid-interaction-review)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/fluid-interaction-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/fluid-interaction-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/fluid-interaction-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/fluid-interaction-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01131 |
| Opus 5 | $0.00032 | $0.00566 |
| Sonnet 5 | $0.00013 | $0.00226 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
fluid-interaction-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fluid Interaction Review
Use this only for direct-manipulation surfaces. It complements motion-review-gate; it is not a general visual-style or Apple-look preset.
Best Fit
- drawers, sheets, swipe actions, carousels, sliders, scrubbers, and draggable panels;
- gesture code using Pointer Events, Motion, Framer Motion, or a library with equivalent primitives;
- reviews where a transition looks acceptable after release but feels disconnected during manipulation.
Do Not Use For
- ordinary buttons, forms, tables, or static marketing sections;
- adding glass, bounce, sound, or haptics as decoration;
- replacing stable library behavior without a reproduced interaction defect;
- imposing universal spring constants or visual styling.
Interaction Contract
- Continuous tracking — while dragging or swiping, the surface follows the pointer 1:1. Preserve the offset from the point where the user grabbed it; do not jump to the element center.
- Pointer ownership — use Pointer Events and
setPointerCapture(pointerId)when implementing custom gestures so tracking survives leaving the element bounds. Release or cancel capture cleanly. - Interruptibility — a moving surface can be grabbed and redirected immediately. Retarget from the current on-screen value and current velocity, not from a stale logical target. Never lock input until an animation finishes.
- Velocity handoff — sample a short, timestamped movement history and pass release velocity into the settling spring. Guard zero distance, sparse events, and extreme velocity.
- Momentum projection — when a flick can cross snap points, select the destination from a bounded projection of release velocity, then settle with the handed-off velocity. Do not choose solely from release position.
- Hysteresis — keep the gesture undecided until movement exceeds a small, input-appropriate threshold. Resolve axis and intent before suppressing native scrolling or committing an action.
- Soft boundaries — beyond a real bound, apply progressively increasing resistance. Do not hard-stop while the pointer is still moving. Clamp the final resting state to a valid target.
- Spatial continuity — enter and exit use the same spatial path unless product meaning requires otherwise. Popovers and panels originate from their trigger or manipulation source; reversible motion preserves direction and velocity continuity.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 88 lines · 65 tokens per session scan A e7f2893b45b9
fluid-interaction-review is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,131 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
memstack-development-performance-audit
Use this skill when the user says 'performance audit', 'why is it slow', 'optimize performance', 'page speed', 'Core Web Vitals', 'lighthouse', 'load time', or needs to diagnose and fix frontend or backend performance issues. Do NOT use for code reviews or security audits.
css-debug
Use this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React rendering visibility problems.
docs-release-notes
Use when a change needs a user-visible release-note, changelog, or changeset entry — "add a release note", "add a changeset for this", "what goes in the changelog?", "write up what shipped", "note this for the next release" — or when finalizing a branch whose customer-visible features, bug fixes, or UI changes should…
ag-otimizar-codigo
Otimizacao de performance e legibilidade. Mede antes e depois. Nao otimiza sem medir. Use when optimizing code performance.
sapui5-linter
Use this skill when working with the UI5 Linter (@ui5/linter) for static code analysis of SAPUI5/OpenUI5 applications and libraries. Covers setup, configuring linting rules, running the linter to detect deprecated APIs, global variable usage, CSP violations, and manifest issues. Supports autofix for deprecated API…
axiom-auto-layout-debugging
Use when encountering "Unable to simultaneously satisfy constraints" errors, constraint conflicts, ambiguous layout warnings, or views positioned incorrectly - systematic debugging workflow for Auto Layout issues in iOS.