slide-target
Skill4 starsChanged 3 months agoMITView on GitHub
Load the full working context for ONE DidiDecks slide (deck/variant/slot) so an agent can iterate on it slide-by-slide without re-explaining where things live. The first of the `slide-*` skill family (target → improve → rank → decompose). Use whenever the user wants to work on a specific slide of a DidiDecks/Astro deck — "let's work on slide 2", "fix this card", "/slide-target rural-income v1 02", "go slide by slide", "target the funder-pipeline slide" — or when iterating on a client-site deck under dididecks-ai (reach-edu-hub, chroma-decks, etc.). Assembles the section file, the slides.ts slot, the narrative slot, the rank/audit status, the live URLs, and the design-system tokens for exactly that slide, then scopes all work to it. Composes with deck-iteration-workflow and theme-system.
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 are 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 40
Run these against the client-site root (the nearest ancestor of the cwd that has src/data/decks.ts.
- Distinctive: line 56
Narrative slot (source of truth for content): If a narrative exists, find the matching slide in it:
- Distinctive: line 60
Read the slot's bullet/section so edits stay faithful to the narrative.
- Very specific: line 71
Read items 1, 4, and 7 in full.
- Very specific: line 76
Stay on this slide: Only touch the section file from step 1 (and, for a shared fix, deck-primitives.css/theme.css — but call that out …
- Very specific: line 79
Honor the design system: Use the deck-* primitives and the brand tokens (--color-*, --fx-*).
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
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.
Read items 1, 4, and 7 in full; surface 2/3/5/6 as a compact header so the user sees what's loaded.
Then: work scoped to the slide
- Stay on this slide. Only touch the section file from step 1 (and, for a
shared fix,
deck-primitives.css/theme.css— but call that out explicitly, since it affects every slide). - Honor the design system. Use the
deck-*primitives and the brand tokens (--color-*,--fx-*). No per-elementdark:/vibrant:hardcoding — the tokens make all three modes work. If a bug is mode-specific (e.g. dark-mode contrast), reproduce/verify in that mode. - Stay faithful to the narrative (step 4). Flag unverified figures with the
deck-verifymarker rather than inventing numbers. - After editing, offer to update the rank in
data/audits/slides.json(or, onceslide-rankexists, hand off to it) and tell the user the live URL to re-check.
Notes
- Variant slugs are currently globally unique per client (the shell keys
SLOTSby variant alone). If a slot lookup is ambiguous, that constraint was violated — see the dididecks shell limitation note. - The Tier-1 bridge file (
.dididecks/active-slide.json) is written by the deck dev shell from the SlideRankPill's IntersectionObserver. If it's not there yet, the explicit-args form is the path.
See also
deck-iteration-workflow— the Scroll-UI-first → variant rhythm this scopes into.theme-system/maintain-design-md— the token + design-system discipline.dididecks-ai/client-sites/reach-edu-hub/context-v/explorations/Deck-Collections-A-Menu-Layer-Above-Single-Deck-Convergence.md— the deck/variant/collection model.- augment-it
context-v/specs/Chat-Context-Awareness-Architecture.md— the context-broker pattern this borrows (ActiveView → context slab).
In this repository36 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- astro-knotsSkill
- augment-speakers-panelistsSkill
- changelog-conventionsSkill
- cloudflare-artifacts-interfaceSkill
- competitive-analysisSkill
- context-vigilanceSkill
- crawl-fetch-ingestSkill
- create-contact-list-from-image-or-spreadsheetSkill
- decile-hub-connectorSkill
- deck-iteration-workflowSkill
- event-prepSkill
- expense-report-generationSkill
- generate-consistent-og-imagesSkill
- gh-cli-projects-tasks-conventionsSkill
- git-conventionsSkill
- graphifySkill
- hubspot-interfaceSkill
- lossless-crm-interface-guidelinesSkill
- lossless-flavored-markdownSkill
- maintain-design-mdSkill
- maintain-filemapSkill
- maintain-splash-pagesSkill
- market-capture-analysisSkill
- obsidian-vault-hygieneSkill
- open-graph-share-seo-geoSkill
- openpanel-analyticsSkill
- overlay-svg-textSkill
- prep-images-for-embedSkill
- pseudomonoreposSkill
- remake-deckSkill
- search-lossless-corpusSkill
- study-repos-firstSkill
- surrealdb-canonical-layerSkill
- theme-systemSkill
- timeline-scenario-analysisSkill
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.

