felo-slides
Skill254 starsChanged 7 months agoMITView on GitHub
Generate PPT/slides with Felo PPT Task API in Claude Code. Use when users ask to create/make/generate/export presentations or slide decks, or when explicit commands like /felo-slides are used. Handles API key check, task creation, polling, and final ppt_url output.
- Reads credentials
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- Felo-Inc/felo-skillsedited, first seen Mar 16, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- Felo-Inc/felo-skills★ 24856% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- best-practices-for-agent-skillsSkill
- githubclaw-json-generatorSkill
- pr-creatorSkill
- skill-creatorSkill
- agent-browserSkill
- felo-searchSkill
- felo-superAgentSkill
- felo-web-fetchSkill
- felo-x-searchSkill
- find-skillsSkill
- gemini-audio-transcriberSkill
- gemini-deep-researcherSkill
- gemini-image-describerSkill
- gemini-lyria-3Skill
- gemini-nanobananaSkill
- gemini-summarySkill
- google-stitchSkill
- skill-creatorSkill
- telegram-notifySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 10 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Create/generate slides from a topic or outline
- Distinctive: line 23
Do NOT use this skill for:
- Distinctive: line 35
Create and copy your API key
- Distinctive: line 53
Use Bash tool commands and follow this workflow exactly.
- Distinctive: line 64
If key is missing, stop and return setup instructions.
- Very specific: line 68
Use the bundled script (no jq dependency).
- Very specific: line 117
if --json is used, also include task_id, terminal status, and optional metadata
- Distinctive: line 121
Use this response structure:
- Distinctive: line 157
If timeout reached, return last known status and instruct user to retry later
- Distinctive: line 168
Always execute this skill when user intent is slide generation.
- Very specific: line 169
Always return task_id so follow-up queries can continue from the same task.
- Distinctive: line 170
Do not claim completion without a terminal status.
- Distinctive: line 171
Keep API calls minimal: create once, then poll.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Felo Slides Skill
When to Use
Trigger this skill for requests about creating presentation files:
- Create/generate slides from a topic or outline
- Turn notes into a PPT deck
- Build a presentation with a page count requirement
- Export presentation content into a shareable slide link
Trigger keywords:
- Chinese prompts about making slides or presentations
- English: slides, PPT, presentation deck, generate presentation
- Explicit commands:
/felo-slides, "use felo slides"
Do NOT use this skill for:
- Real-time information lookup (use
felo-search) - Questions about local codebase files
- Pure text tasks that do not require slide generation
Setup
1. Get API key
- Visit felo.ai
- Open Settings -> API Keys
- Create and copy your API key
2. Configure environment variable
Linux/macOS:
export FELO_API_KEY="your-api-key-here"Windows PowerShell:
$env:FELO_API_KEY="your-api-key-here"How to Execute
Use Bash tool commands and follow this workflow exactly.
Step 1: Precheck API key
if [ -z "$FELO_API_KEY" ]; then
echo "ERROR: FELO_API_KEY not set"
exit 1
fiIf key is missing, stop and return setup instructions.
Step 2: Run Node Script (create + poll)
Use the bundled script (no jq dependency). To reduce black-box waiting and make task progress easier to track, prefer --json --verbose as the default mode:
node .agents/skills/felo-slides/scripts/run_ppt_task.mjs \
--query "USER_PROMPT_HERE" \
--interval 10 \
--max-wait 1800 \
--timeout 60 \
--json \
--verboseScript behavior:
- Creates task via
POST https://openapi.felo.ai/v2/ppts - Polls via
GET https://openapi.felo.ai/v2/tasks/{task_id}/historical - Treats
COMPLETED/SUCCESSas success terminal (case-insensitive) - Treats
FAILED/ERRORas failure terminal - Stops polling immediately on terminal status
- Prints
task_idto stderr when running in observable mode - Prints
ppt_urlon success (fallback:live_doc_url) - Includes richer error details such as
code/request_idwhen Felo returns them
Optional debug output:
node .agents/skills/felo-slides/scripts/run_ppt_task.mjs \
--query "USER_PROMPT_HERE" \
--interval 10 \
--max-wait 1800 \
--json \
--verboseThis outputs structured JSON including:
task_idtask_statusppt_urllive_doc_urllivedoc_short_idppt_business_iderror_message
Step 4: Return structured result
On success, return:
ppt_urlimmediately (script default output, fallbacklive_doc_url)- if
--jsonis used, also includetask_id, terminal status, and optional metadata
Output Format
Use this response structure:
## PPT Generation Result
- Task ID: <task_id>
- Status: <status>
- PPT URL: <ppt_url>
- Live Doc URL: <live_doc_url or N/A>
## Notes
- livedoc_short_id: <value or N/A>
- ppt_business_id: <value or N/A>Error format:
## PPT Generation Failed
- Error Type: <error code or category>
- Message: <readable message>
- Suggested Action: <next step>Error Handling
Known API error codes:
INVALID_API_KEY(401): key invalid or revokedPPT_TASK_CREATE_FAILED(502): create task downstream failedPPT_TASK_QUERY_FAILED(502): query task downstream failed
Timeout handling:
- If timeout reached, return last known status and instruct user to retry later
- Include
task_idso user can query again
Important Notes
- ⚠️ 路徑安全:skill 腳本位於 repo root 的
.agents/skills/下。若 cwd 不在 repo root,先執行git rev-parse --show-toplevel取得路徑再cd。禁止用$(...)語法。 - ⚠️ 指令安全:Copilot CLI 的安全過濾器會封鎖含有特定 shell 語法的指令,執行時禁止加入以下任何寫法,否則指令會被直接擋下:
set -e、set -u、set -o、set -euo pipefail等 set 指令${var@P}、${!var}等參數展開語法- 巢狀的
$(...)指令替換 - 正確寫法:直接執行
cd與node指令,不要包在 shell 腳本控制流程內
- Always execute this skill when user intent is slide generation.
- Always return
task_idso follow-up queries can continue from the same task. - Do not claim completion without a terminal status.
- Keep API calls minimal: create once, then poll.
References
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.

