stanislavjiricek/phase-slideshow
skills/phase-slideshow/SKILL.md
Phase guidance for the neuroflow /slideshow command. Loaded automatically when /slideshow is invoked to orient agent behavior, slide structure decisions, format selection, and audience calibration for presentation generation.
$ install --global
skillsauthnpx skillsauth add stanislavjiricek/neuroflow phase-slideshowInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 14, 2026, 2:41 AM16.9s1 file scanned
SKILL.md
- name:
- phase-slideshow
- description:
- Phase guidance for the neuroflow /slideshow command. Loaded automatically when /slideshow is invoked to orient agent behavior, slide structure decisions, format selection, and audience calibration for presentation generation.
phase-slideshow
The slideshow phase generates a structured slide deck outline from .neuroflow/ contents — covering selected phases, analyses, figures, and key findings — ready to export as Markdown/reveal.js or a PowerPoint-compatible structured outline.
Approach
- Confirm scope (which phases), audience, talk length, and output format before loading any files
- Use
flow.mdfiles to navigate.neuroflow/rather than reading all content up front - Calibrate slide count and detail level to the stated talk length — do not pad or over-explain
- Synthesize, do not transcribe — a slide is a claim supported by evidence, not a file dump
- Flag figures by path but do not attempt to embed binary image files
Relevant skills
neuroflow:neuroflow-core— read first; defines the command lifecycle and.neuroflow/write rulesneuroflow:notebooklm— when the user says "use NotebookLM" or wants AI-narrated slides / an audio walkthrough of the slides, route the output to thenotebooklmskill instead of (or in addition to) generating Markdown/reveal.js
Audience calibration
| Audience | Approach | |---|---| | Specialist (same field) | Include technical detail in methods; abbreviations are fine | | General neuroscience | Explain modality-specific methods briefly; avoid jargon in results | | Mixed | Lead with big-picture framing; keep methods to one slide; emphasise findings | | Non-scientists | One-sentence lay summary per section; no statistical notation without explanation |
Slide count heuristic
| Talk length | Target slides | |---|---| | 5–10 min | 8–12 | | 15–20 min | 15–22 | | 30 min | 25–30 | | 45 min | 32–40 |
If the user asks for more slides than the heuristic suggests, comply but note that the pace may be tight.
Output format guidance
Markdown / reveal.js
- Use YAML frontmatter with
title,author,date,theme ---separates horizontal slides;--separates vertical sub-slides within a section- Recommended themes:
white(light),black(dark),moon(dark, muted) - Remind the user to install reveal.js or use Slidev for rendering
Structured text outline (PowerPoint / Keynote)
- Each slide block starts with
[SLIDE] - Use
[TITLE],[BULLET],[IMAGE: path/to/figure],[SPEAKER NOTE]markers - This format can be copied into a presentation app slide by slide
- Remind the user to replace
[IMAGE: ...]markers with actual figure files
Workflow hints
- Save the slideshow to
.neuroflow/slideshow/slideshow-YYYY-MM-DD.md— confirm before writing - If a same-date file exists, append
-v2,-v3, etc. - Keep bullet points to ≤ 6 words per line where possible — slides are prompts, not paragraphs
Slash command
/neuroflow:slideshow — runs this workflow as a slash command.
Related Skills
stanislavjiricek/bids
testing
VerifiedTrustedCommunity
This skill should be used whenever the user mentions BIDS, Brain Imaging Data Structure, BIDS conversion, BIDS validation, BIDS compliance, organizing neuroimaging data, dataset_description.json, participants.tsv, bids-validator, pybids, MNE-BIDS, or asks how to structure EEG/MEG/fMRI/iEEG/PET/DWI data for sharing or preprocessing. Also invoke when the user asks how to name scan files, what sidecar JSON fields are needed, how to set up derivatives/, or how to run fMRIPrep/MRIQC on their dataset. Invoke proactively during /data, /data-preprocess, and /data-analyze phases whenever the dataset structure is relevant to the task at hand.
3SKILL.mdUpdated Jun 5, 2026
stanislavjiricek/phase-meeting
tools
VerifiedTrustedCommunity
Phase guidance for the /meeting command. Covers meeting file structure, recurring templates, attendee resolution from profiles, Google Calendar MCP integration, agenda preparation with project context, and action-item-to-task conversion at all three levels (project, flowie, hive).
3SKILL.mdUpdated Apr 25, 2026
stanislavjiricek/worker-critic
data-ai
VerifiedTrustedCommunity
Worker-critic agentic loop protocol — orchestrator coordinates a worker agent and a critic agent across up to 3 revision cycles to produce a vetted output for any phase.
3SKILL.mdUpdated Apr 14, 2026
stanislavjiricek/wiki
development
VerifiedTrustedCommunity
Knowledge base skill — Karpathy-style LLM-maintained wiki at three levels (personal/flowie, project, team/hive). Handles ingest, query, lint, schema, and project-tagging workflows. Invoked by /flowie --wiki-* (personal), /wiki (project), /hive --wiki-* (team).
3SKILL.mdUpdated Apr 14, 2026