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 lossless-group/lossless-agent-skills --skill slide-targetgit clone --depth 1 https://github.com/lossless-group/lossless-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/lossless-group/lossless-agent-skills/slide-target)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/slide-target"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/slide-target/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/lossless-group/lossless-agent-skills/slide-target"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/slide-target.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 | $0.00205 | $0.01659 |
| Opus 5 | $0.00102 | $0.00830 |
| Sonnet 5 | $0.00041 | $0.00332 |
| Haiku 4.5 | $0.00020 | $0.00166 |
Grade A, and why
slide-target 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slide-target
Load everything needed to work on one slide of a DidiDecks deck, then keep the work scoped to that slide. This is the agent-side analogue of augment-it's "context broker → ActiveView" pattern: instead of re-describing which slide and where its files live every time, you name the slide once and the skill assembles the context slab for it.
First of the slide-* family. Later siblings (not yet built): slide-improve
(apply a design pass), slide-rank (set the audit status), slide-decompose
(scaffold the Play-UI counterpart). Designed to be extractable into a publishable
"DidiDecks slide skills" library.
When to use
- The user wants to iterate on a specific slide: "let's do slide 2", "fix the four cards", "work on the funder-pipeline slide", "/slide-target rural-income v1 02".
- Any slide-by-slide deck iteration under
dididecks-ai/client-sites/*.
Invocation forms
/slide-target <deck> <variant> <slot>— fully explicit, e.g./slide-target rural-income v1 02./slide-target <slot>— infer<deck>/<variant>from the most recently discussed deck in the conversation (confirm if ambiguous)./slide-target(no args) — Tier-1 bridge: if<client-root>/.dididecks/active-slide.jsonexists (written by the deck's dev shell as the user scrolls), read{deck, variant, slot}from it. If it doesn't exist, ask for the slide.
Slot is the zero-padded slot id (01, 02, 09, 10…), matching data-slot.
Resolution algorithm — assemble the context slab
Run these against the client-site root (the nearest ancestor of the cwd that
has src/data/decks.ts; if the user is in the monorepo root, ask which client).
- Section component (the thing you edit). Grep for the slide's section:
This finds the file whether the deck uses standalone section components (e.g. reach:grep -rl 'data-slot="<NN>"' <root>/src | xargs grep -l 'data-variant="<variant>"'src/layouts/sections/<deck>/T<NN>-*.astro) or inline<section>s in the scroll page (e.g. chroma'ssrc/pages/scroll/.../index.astro). Also note the Play-UI counterpart if it exists:src/components/slides/<variant>/<slot>-<slug>.astro. - Slot registry entry. In
src/data/slides.ts,SLOTS["<variant>"]→ the entry withslot === "<NN>"(itstitle,slug). - Deck registry entry. In
src/data/decks.ts, the deck<deck>and the variant<variant>(title, label, status, lede). - Narrative slot (source of truth for content). If a narrative exists, find
the matching slide in it:
- strategies:
context-v/narratives/strategies/<deck>/README.md - otherwise look under
context-v/narratives/for the deck's outline. Read the slot's bullet/section so edits stay faithful to the narrative.
- strategies:
- Rank / audit status. In
data/audits/slides.json, the key"<deck>/<variant>/<NN>"→{scroll, play}status (urgent-redo / could-be-better / passable / perfect / pending). - Live URLs. Scroll:
/scroll/<deck>/<variant>(jump with#s-<N>where N is the 1-based section index). Play (if the per-slide file exists):/play/<deck>/<variant>/<slot>. TOC:/toc/<deck>/<variant>. - Design system (so edits stay on-brand).
src/styles/deck-primitives.css(the token-driven section vocabulary) andsrc/styles/theme.css(the Tier-2 semantic +--fx-*tokens). Edits should compose these, not hardcode colors.
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.
- 11d ago First seen · 104 lines · 205 tokens per session scan A ecccc5f706c6
slide-target is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 18d ago), licensed MIT. It adds 205 tokens to every session and 1,659 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
gsd-ui-phase
Generate UI design contract (UI-SPEC.md) for frontend phases.
figma-implement-design
Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a…
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
improve-app
Guided journey from a shipped app that works but feels rough to a product that fits the job, flows without friction, reads clearly, and persuades honestly. Orchestrates nine skills phase by phase - jobs-to-be-done, ux-heuristics, design-everyday-things, refactoring-ui, microinteractions, made-to-stick…