#912 by GitHub stars
nexu-io/codex-slides
🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4–5 minutes — Fast mode renders every page in parallel. 🔍 Watch the whole chain live: research → outline → style → render → edit → present → export PDF/PPTX. 🖥<U+FE0F> Browser-first · zero API keys · durable projects.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/codex-slides/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dbc2a5992e93 → dbc2a5992e93
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dbc2a5992e93
No earlier version was observed for comparison.
skills/codex-slides-browser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dbc2a5992e93 → dbc2a5992e93
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dbc2a5992e93
No earlier version was observed for comparison.
skills/codex-slides-deck/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dbc2a5992e93 → dbc2a5992e93
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dbc2a5992e93
No earlier version was observed for comparison.
skills/codex-slides-known-errors/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dbc2a5992e93 → dbc2a5992e93
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dbc2a5992e93
No earlier version was observed for comparison.
skills/codex-slides-research/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dbc2a5992e93 → dbc2a5992e93
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dbc2a5992e93
No earlier version was observed for comparison.
skills/codex-slides-structured-intake/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dbc2a5992e93 → dbc2a5992e93
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dbc2a5992e93
No earlier version was observed for comparison.
skills/codex-slides-verification/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dbc2a5992e93 → dbc2a5992e93
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dbc2a5992e93
No earlier version was observed for comparison.
Heat
3.2- Star growth, last 7 daysAhead of 75% of tracked repositories
- Star growth, last 24 hoursAhead of 3% of tracked repositories
- Rank movement, last 7 daysAhead of 17% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- codex-slides
skills/codex-slides - codex-slides-browser
skills/codex-slides-browser - codex-slides-deck
skills/codex-slides-deck - codex-slides-known-errors
skills/codex-slides-known-errors - codex-slides-research
skills/codex-slides-research - codex-slides-structured-intake
skills/codex-slides-structured-intake - codex-slides-verification
skills/codex-slides-verification
How it works
codex-slides
When your agent uses it
Create, research, revise, restyle, present, inspect, and export Codex Slides slide decks from Codex, including scenario workflows, project Design Files, and always-on brand design systems. Use when the user asks for a presentation, PPT/PPTX, slide deck, research brief converted into slides, an existing deck edit, a marked-up slide revision, brand/style controls, project files, or to open and operate Codex Slides in the Codex in-editor Browser.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
2,694 tokensWhen the skill is activated
Reference documents
4,414 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Browser-first default
- Choose a transport
- Build a deck
- Operate Design Files
- Reuse project templates
- Maintain the brand design system
- Edit an existing deck
- Route to focused workflow skills
- Open and verify in Codex Browser
- Export only after review
- Runtime
Scripts executed separately
scripts/codex-slides.mjsscripts/probe.mjs
Files
SKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesagents/openai.yamlasset304 bytesreferences/CAPABILITY_MATRIX.mddoc6,989 bytesreferences/COMMANDS.mddoc10,031 bytesscripts/codex-slides.mjsruns42,957 bytesscripts/probe.mjsruns2,891 bytes
Read SKILL.md
# Codex Slides
Run Codex Slides as an interactive product inside Codex. The live Browser
workspace is the primary experience; MCP and the bundled CLI are transports
for opening the workspace and performing deterministic operations, not a reason
to hide the presentation workflow in a long-running Codex turn.
## Browser-first default
For every new deck request, unless the user explicitly asks for a headless,
unattended, one-call, or CLI-only run:
1. Call `open_codex_slides` / CLI `open` **without** a project id, immediately
navigate the returned URL in Codex's in-editor Browser, and verify that theView the complete source on GitHubcodex-slides-browser
When your agent uses it
Compatibility entry point for opening and operating Codex Slides in Codex's in-editor Browser, including scenario selection, Design Files, brand systems, decks, and Play mode. Use when the user asks to open, launch, preview, view, play, inspect, or directly manipulate Codex Slides or a deck without leaving Codex.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
603 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
../codex-slides/scripts/codex-slides.mjs../codex-slides/scripts/codex-slides.mjs../codex-slides/scripts/codex-slides.mjs../codex-slides/scripts/codex-slides.mjs../codex-slides/scripts/codex-slides.mjs../codex-slides/scripts/codex-slides.mjs
Files
SKILL.mdcore2,739 bytesagents/openai.yamlasset255 bytes../codex-slides/scripts/codex-slides.mjsruns42,957 bytes../codex-slides/scripts/codex-slides.mjsruns42,957 bytes../codex-slides/scripts/codex-slides.mjsruns42,957 bytes../codex-slides/scripts/codex-slides.mjsruns42,957 bytes../codex-slides/scripts/codex-slides.mjsruns42,957 bytes../codex-slides/scripts/codex-slides.mjsruns42,957 bytes
Read SKILL.md
# Codex Slides Browser
This specialized skill remains for compatibility. The canonical
`codex-slides` sibling skill owns the full workflow and portable CLI.
1. Call `open_codex_slides` when the MCP tool is available. Otherwise run
`node ../codex-slides/scripts/codex-slides.mjs open --json '<input>'` from
this skill directory. Pass `projectId` when the user named a deck;
otherwise omit it for the create workspace.
Use `view:"scenarios"` for the 24-workflow catalog,
`view:"design-files"` plus `projectId` and optional `filePath` for project
files, or `view:"brand-system"` plus `projectId` for the brand editor.
2. Navigate the returned resource link in the Codex in-editor Browser. Do not
stop after printing the URL and do not ask the user to open it manually.View the complete source on GitHubcodex-slides-deck
When your agent uses it
Compatibility entry point for scenario-led creation, Design Files, brand systems, inspecting, revising, restyling, and exporting Codex Slides slide decks. Use when a user asks Codex to make a presentation, use project files, edit an existing deck, manage slide structure, apply brand or template rules, or export PDF/PPTX.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
902 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Choose the flow
- Edit with the right tool
- Show and verify
Scripts executed separately
../codex-slides/scripts/codex-slides.mjs
Files
SKILL.mdcore3,888 bytesagents/openai.yamlasset244 bytes../codex-slides/scripts/codex-slides.mjsruns42,957 bytes
Read SKILL.md
# Codex Slides Deck
The canonical `codex-slides` sibling skill owns the complete workflow. Use the
`codex_slides` MCP tools when available; otherwise run its self-contained CLI
at `../codex-slides/scripts/codex-slides.mjs`. Keep the live workspace available
in the in-editor Browser whenever visual review helps.
## Choose the flow
- Default to the live Browser workflow: open the Codex Slides home screen,
submit the request there, then operate the created project through clarify,
outline confirmation, style selection, rendering, and review. Keep the
Browser visible throughout.
- If Browser UI submission fails, use `start_project` / CLI `start-project` toView the complete source on GitHubcodex-slides-known-errors
When your agent uses it
Diagnose and recover from Codex Slides plugin, MCP, Browser handoff, local runtime, durable run, project resume, rendering, Design Files, export, and version-contract failures. Use when a tool fails, a run stalls, a project appears stale, or Codex and the Browser disagree.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
630 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Runtime and installation
- Durable runs
- Browser handoff and project resume
- Rendering and project state
- Design Files and export
Files
SKILL.mdcore2,851 bytesagents/openai.yamlasset280 bytes
Read SKILL.md
# Codex Slides Known Errors
Classify the failure before retrying. Preserve the same project id and run id;
do not recreate a deck merely because a Browser tab closed or a wait timed out.
## Runtime and installation
- **Plugin version contract fails:** `.codex-plugin/plugin.json` must start with
the exact root `package.json` version plus `+codex.`. The desktop package must
use the same product version.
- **App is unreachable:** inspect `CODEX_SLIDES_URL` and `CODEX_SLIDES_LOG`.
The local MCP launcher may need to prepare dependencies or a standalone build.
- **Installed skill or tool inventory looks stale:** reinstall/upgrade the
plugin and start a new Codex task so the versioned plugin cache is refreshed.View the complete source on GitHubcodex-slides-research
When your agent uses it
Compatibility entry point for researching a current topic into a source-backed Markdown brief and turning it into a Codex Slides outline or rendered deck. Use for market, competitive, policy, technical, academic, or other presentation requests that need current facts, figures, comparisons, or citations.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
454 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
../codex-slides/scripts/codex-slides.mjs
Files
SKILL.mdcore2,030 bytesSKILL.mdcore2,030 bytesagents/openai.yamlasset260 bytes../codex-slides/scripts/codex-slides.mjsruns42,957 bytes
Read SKILL.md
# Codex Slides Research
The canonical `codex-slides` sibling skill owns the complete workflow. Use
`deep_research` when MCP is available; otherwise run CLI command `research` at
`../codex-slides/scripts/codex-slides.mjs`. Preserve its Markdown and citations
so the user can review or edit the evidence before slide generation.
For the default interactive workflow, first open the Codex Slides home screen
in the Codex Browser, submit the research request there, and keep the created
project visible while its research, outline, style, and render checkpoints
advance. Use the lower-level sequence below only for CLI automation, recovery,
or a user-requested headless workflow:
1. If a research workflow fits, call `list_scenarios` / CLI `scenarios` andView the complete source on GitHubcodex-slides-structured-intake
When your agent uses it
Collect and persist structured presentation requirements for Codex Slides, including scenario choice, audience, page count, language, format, research mode, visual direction, source-file roles, and clarification checkpoints. Use when a new deck request is ambiguous or scenario-led.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
431 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Flow
Files
SKILL.mdcore2,097 bytesSKILL.mdcore2,097 bytesSKILL.mdcore2,097 bytesSKILL.mdcore2,097 bytesagents/openai.yamlasset311 bytes
Read SKILL.md
# Codex Slides Structured Intake
The Codex Slides Browser owns the canonical intake form. Structured intake must
produce one durable project and one shared clarification state, not a separate
chat-only questionnaire.
## Flow
1. Call `open_codex_slides` without a project id and follow its
`browserHandoff` to the home/create workspace.
2. When a workflow preset fits, call `list_scenarios`, then open the selected
scenario deep link. Use product-owned defaults and source slots.
3. Submit the user's topic and available files in the Browser. Assign every
uploaded file its scenario role; do not flatten datasets, source decks,View the complete source on GitHubcodex-slides-verification
When your agent uses it
Verify that Codex Slides changes are durably reflected in project state and visibly reflected in the exact Codex Browser slide, panel, version, checkpoint, or presentation surface. Use after creation, rendering, editing, restyling, mark edits, speaker-note changes, version restores, or export.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
394 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Verification sequence
Files
SKILL.mdcore1,867 bytesagents/openai.yamlasset291 bytes
Read SKILL.md
# Codex Slides Verification
Use two signals before reporting a presentation task complete:
1. Read canonical project state with `get_project`, and read a named durable job
with `get_project_run` or `wait_project_run` when a `runId` was returned.
2. Follow the returned `browserHandoff` and inspect the exact visible result in
the Codex in-editor Browser.
## Verification sequence
1. Confirm the project id rather than guessing from a similar title.
2. For a durable run, require a terminal `complete` status. Treat `error` and
`cancelled` as incomplete; a timed-out wait leaves the run active.View the complete source on GitHubSkills included
- codex-slides
- codex-slides-browser
- codex-slides-deck
- codex-slides-known-errors
- codex-slides-research
- codex-slides-structured-intake
- codex-slides-verification
Repository facts
- License
- MIT
- Created
- Jul 10, 2026
- Last pushed
- Jul 21, 2026
- Forks
- 83
- Open issues
- 4
- Project activity
- Slowing
Rank over the last 12 weeks
Now #912 · best #626 · down 137 in 30 days
- #896 from Oct 29 to Oct 30
- #899 from Oct 31 to Nov 1
- #906 on Nov 2
- #910 from Nov 3 to Nov 4
- #913 on Nov 5
- #912 since Nov 6
69 earlier periods
- #660 on Aug 2
- #645 on Aug 7
- #641 on Aug 8
- #637 on Aug 9
- #665 on Aug 10
- #669 on Aug 11
- #663 on Aug 12
- #658 on Aug 13
- #655 on Aug 14
- #633 on Aug 15
- #643 on Aug 16
- #654 on Aug 17
- #666 on Aug 18
- #651 from Aug 19 to Aug 20
- #655 on Aug 21
- #626 on Aug 22
- #678 on Aug 24
- #681 on Aug 25
- #661 on Aug 26
- #674 on Aug 27
- #694 on Aug 28
- #645 on Aug 29
- #643 on Aug 30
- #674 on Aug 31
- #688 on Sep 1
- #672 on Sep 2
- #676 on Sep 3
- #655 on Sep 4
- #645 on Sep 5
- #666 on Sep 6
- #680 on Sep 7
- #699 on Sep 8
- #687 on Sep 9
- #688 on Sep 10
- #671 on Sep 11
- #677 from Sep 12 to Sep 13
- #699 on Sep 14
- #687 on Sep 15
- #699 on Sep 16
- #700 on Sep 17
- #689 on Sep 18
- #680 on Sep 20
- #696 on Sep 21
- #716 on Sep 22
- #706 on Sep 23
- #681 on Sep 24
- #667 from Sep 25 to Sep 26
- #700 on Sep 27
- #746 on Sep 29
- #693 on Oct 2
- #675 on Oct 3
- #734 on Oct 7
- #775 on Oct 8
- #742 on Oct 9
- #726 on Oct 10
- #723 on Oct 11
- #741 on Oct 12
- #746 on Oct 13
- #757 on Oct 14
- #736 on Oct 17
- #723 on Oct 18
- #765 on Oct 19
- #771 on Oct 20
- #782 on Oct 21
- #762 on Oct 22
- #767 on Oct 23
- #729 on Oct 24
- #879 on Oct 25
- #888 on Oct 28
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 17 notes
skills/codex-slides/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/scripts/codex-slides.mjs:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/scripts/codex-slides.mjs:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/scripts/codex-slides.mjs:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/scripts/codex-slides.mjs:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides/scripts/codex-slides.mjs:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides-research/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides-structured-intake/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides-structured-intake/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codex-slides-structured-intake/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 37 network referencesin 3 files: codex-slides/scripts/codex-slides.mjs:13 codex-slides/scripts/probe.mjs:50 codex-slides/references/COMMANDS.md:249
- No hidden or obfuscated text
- No instruction overrides
- 10 executable scriptsin 2 files: codex-slides/scripts/codex-slides.mjs:1 codex-slides/scripts/probe.mjs:1
- No access to secrets
- No requests to vote in Hot
Show all 47 signals by file
skills/codex-slides/references/COMMANDS.md
skills/codex-slides/scripts/codex-slides.mjs
- Executable scriptline 1
#!/usr/bin/env node - Executable scriptline 1
#!/usr/bin/env node - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env node - Executable scriptline 1
#!/usr/bin/env node - Network accessline 13
const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url)); const BASE = (process.env.CODEX_SLIDES_URL || "http://127.0.0.1:4311").replace(/\/$/, ""); - Network accessline 13
const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url)); const BASE = (process.env.CODEX_SLIDES_URL || "http://127.0.0.1:4311").replace(/\/$/, ""); - Network accessline 13
const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url)); const BASE = (process.env.CODEX_SLIDES_URL || "http://127.0.0.1:4311").replace(/\/$/, ""); - Network accessline 13
const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url)); const BASE = (process.env.CODEX_SLIDES_URL || "http://127.0.0.1:4311").replace(/\/$/, ""); - Network accessline 14
const BASE = (process.env.CODEX_SLIDES_URL || "http://127.0.0.1:4311").replace(/\/$/, ""); - Network accessline 14
const BASE = (process.env.CODEX_SLIDES_URL || "http://127.0.0.1:4311").replace(/\/$/, ""); - Network accessline 14
const BASE = (process.env.CODEX_SLIDES_URL || "http://127.0.0.1:4311").replace(/\/$/, ""); - Network accessline 14
const BASE = (process.env.CODEX_SLIDES_URL || "http://127.0.0.1:4311").replace(/\/$/, ""); - Network accessline 165
async function reachable() { try { const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); - Network accessline 165
async function reachable() { try { const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); - Network accessline 165
async function reachable() { try { const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); - Network accessline 165
async function reachable() { try { const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); - Network accessline 166
try { const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); return response.ok; - Network accessline 166
try { const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); return response.ok; - Network accessline 166
try { const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); return response.ok; - Network accessline 166
try { const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); return response.ok; - Network accessline 167
const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); - Network accessline 167
const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); - Network accessline 167
const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); - Network accessline 167
const response = await fetch(`${BASE}/api/agents`, { signal: AbortSignal.timeout(2500) }); - Network accessline 216
async function apiFetch(path, init = {}) { await ensureServer(); return fetch(`${BASE}${path}`, init); - Network accessline 216
async function apiFetch(path, init = {}) { await ensureServer(); return fetch(`${BASE}${path}`, init); - Network accessline 216
async function apiFetch(path, init = {}) { await ensureServer(); return fetch(`${BASE}${path}`, init); - Network accessline 216
async function apiFetch(path, init = {}) { await ensureServer(); return fetch(`${BASE}${path}`, init); - Network accessline 217
await ensureServer(); return fetch(`${BASE}${path}`, init); } - Network accessline 217
await ensureServer(); return fetch(`${BASE}${path}`, init); } - Network accessline 217
await ensureServer(); return fetch(`${BASE}${path}`, init); } - Network accessline 217
await ensureServer(); return fetch(`${BASE}${path}`, init); } - Network accessline 218
return fetch(`${BASE}${path}`, init); - Network accessline 218
return fetch(`${BASE}${path}`, init); - Network accessline 218
return fetch(`${BASE}${path}`, init); - Network accessline 218
return fetch(`${BASE}${path}`, init);
skills/codex-slides/scripts/probe.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 50
throw new Error(`Expected 6 groups and 24 scenarios, got ${scenarios.groups?.length}/${scenarios.scenarios?.length}.`); } if (!opened.url?.startsWith("http://127.0.0.1:4311")) throw new Error("Browser URL is missing."); - Network accessline 51
} if (!opened.url?.startsWith("http://127.0.0.1:4311")) throw new Error("Browser URL is missing."); if (!opened.url.includes("view=scenarios") || !opened.url.includes("scenario=new-deck")) { - Network accessline 52
if (!opened.url?.startsWith("http://127.0.0.1:4311")) throw new Error("Browser URL is missing.");
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/codex-slides/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/codex-slides/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/codex-slides/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/codex-slides/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/codex-slides/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/codex-slides/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/nexu-io-codex-slides/)