petrogurcak/session-context
plugins/development/skills/session-context/SKILL.md
Manages persistent context between Claude Code sessions by loading ACTIVE_CONTEXT.md and DECISIONS.md at session start and saving progress at session end. Use when user says "load context", "nacti kontext", "save context", "uloz kontext", "log decision", or automatically at session start/end. NOT for project setup (use projectsetup) or for tracking mistakes (use workflow-optimization).
$ install --global
skillsauthnpx skillsauth add petrogurcak/skills session-contextInstall 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 16, 2026, 4:50 AM4.0s1 file scanned
SKILL.md
- name:
- session-context
- description:
- Manages persistent context between Claude Code sessions by loading ACTIVE_CONTEXT.md and DECISIONS.md at session start and saving progress at session end. Use when user says "load context", "nacti kontext", "save context", "uloz kontext", "log decision", or automatically at session start/end. NOT for project setup (use projectsetup) or for tracking mistakes (use workflow-optimization).
- author:
- Petr
- version:
- 1.0.0
Session Context Skill
Manages persistent context between Claude Code sessions.
When to Use
- Auto-triggered at session start (via using-superpowers)
- Manually when user says "ulož kontext" / "save context" / "načti kontext" / "load context"
- Auto-triggered at end of development-workflow Phase 3
Load Context (Session Start)
Process
- Check if
.claude/ACTIVE_CONTEXT.mdexists in current project - If exists:
- Read
.claude/ACTIVE_CONTEXT.md - Read
.claude/DECISIONS.md(last 5 entries if file is long) - Announce briefly current state
- Read
- If not exists: Continue normally (project without session context)
Announcement Format
Pokračuji kde jsme skončili:
- Branch: [branch name]
- Stav: [what was completed / in progress]
- Další krok: [recommended next action]
Keep it brief - 2-3 lines max. User can ask for details if needed.
Save Context (Session End / Task Complete)
When to Save
- After completing a feature (development-workflow Phase 3)
- When user explicitly asks ("ulož kontext", "save context")
- Before ending a session with work in progress
- After making significant decisions
Update ACTIVE_CONTEXT.md
Replace entire content with:
# Aktuální stav práce
## Poslední session
- **Datum:** [YYYY-MM-DD]
- **Branch:** [current git branch]
- **Dokončeno:** [what was completed this session]
- **Rozděláno:** [work in progress, if any]
- **Další krok:** [recommended next action]
## Otevřené otázky
[any unresolved questions or decisions pending - or "Žádné"]
## Poznámky pro další session
[important context that future Claude should know - or "Žádné"]
Log to DECISIONS.md (if applicable)
Checklist - log if ANY is true:
- [ ] Volil jsem mezi 2+ validními přístupy
- [ ] Rozhodnutí ovlivní více souborů
- [ ] Rozhodnutí bude platit dlouhodobě
- [ ] Budoucí já by se mohl ptát "proč?"
Do NOT log:
- Triviální změny (typo, formatting)
- Rozhodnutí vynucená existujícím kódem
- Dočasná řešení (debugování)
- Implementation details without alternatives
Format for new entry (prepend to file after header):
## [YYYY-MM-DD]: [Název rozhodnutí]
**Kontext:** [Proč bylo potřeba rozhodnout]
**Rozhodnutí:** [Co jsme zvolili]
**Alternativy:** [Co jsme zvažovali]
**Důvod:** [Proč tato volba]
---
Commands
"Načti kontext" / "Load context"
- Read
.claude/ACTIVE_CONTEXT.md - Read
.claude/DECISIONS.md - Display summary of current state
- List recent decisions (last 3-5)
"Ulož kontext" / "Save context"
- Ask user: "Co bylo dokončeno? Co je rozděláno? Jaký je další krok?"
- Update
.claude/ACTIVE_CONTEXT.md - Ask: "Bylo učiněno nějaké důležité rozhodnutí k zalogování?"
- If yes → append to
.claude/DECISIONS.md - Confirm save
"Ulož rozhodnutí" / "Log decision"
- Ask user for decision details or summarize from conversation
- Append to
.claude/DECISIONS.mdusing format above - Confirm logged
File Locations
Files are stored in project's .claude/ directory:
.claude/ACTIVE_CONTEXT.md- Current state, updated each session.claude/DECISIONS.md- Architectural decisions log, append-only
These files are created by projectsetup skill or can be created manually.
Integration
With using-superpowers
At session start, using-superpowers triggers context load automatically.
With development-workflow
At Phase 3 completion, development-workflow triggers context save.
Standalone
User can manually trigger load/save at any time.
Examples
Session Start (auto-load)
[Claude reads ACTIVE_CONTEXT.md]
Pokračuji kde jsme skončili:
- Branch: feature/forgot-password
- Stav: Deploy script s rollback dokončen
- Další krok: Merge do main a deploy
Mohu pokračovat s merge, nebo potřebuješ něco jiného?
Session End (save)
User: "ulož kontext"
Claude: Aktualizuji session context...
Co bylo dokončeno tuto session?
→ [user odpovídá nebo Claude shrne]
[Claude zapíše do ACTIVE_CONTEXT.md]
Bylo učiněno nějaké architektonické rozhodnutí k zalogování?
→ [pokud ano, zapíše do DECISIONS.md]
✅ Kontext uložen.
Decision Logging
User: "zaloguj rozhodnutí o databázi"
Claude: Loguji rozhodnutí...
## 2025-12-01: Migrace z SQLite na PostgreSQL
**Kontext:** Potřeba concurrent writes pro background jobs
**Rozhodnutí:** PostgreSQL 15 s connection pooling
**Alternativy:** SQLite s WAL mode, MySQL, MongoDB
**Důvod:** Robustnost, podpora pro JSONB, zkušenosti týmu
✅ Rozhodnutí zalogováno do .claude/DECISIONS.md
Related Skills
petrogurcak/testimonial-harvesting
development
VerifiedTrustedCommunity
Builds a pre-launch social proof strategy through structured beta programs using D'Souza Brain Audit interviews. Use when launching new products/services and need compelling testimonials, planning a beta cohort, designing interview questions to harvest objection-busting social proof, improving video testimonials for landing pages, or designing case studies with metrics. Trigger phrases include "beta tester program for testimonials", "pre-launch social proof", "Brain Audit testimonial framework", "case study harvest", "reverse testimonial", "video testimonial mechanics", "social proof landing page", "sběr referencí", "beta tester program", "testimonial pro landing page", "social proof před launchem", "rozhovor s klientem", "case study sběr", "reference před spuštěním". NOT for ongoing case study production (use growth-hacking case-study approach), offer design (use offer-creation), or conversion optimization (use ux-optimization).
2SKILL.mdUpdated May 14, 2026
petrogurcak/launch-orchestrator
development
VerifiedTrustedCommunity
Use when planning a product launch and the product type is unclear or could be either generic (SaaS/app/physical) or info-product. Routes between marketing:launch-strategy (generic launches) and marketing:info-product-launch (courses, memberships, ebooks, cohorts, communities). Trigger phrases - "launch", "spuštění", "go-to-market", "product launch", "release strategy", "uvedení na trh", "launch plan", "spuštění produktu", "launch sequence", "launch strategy". Do NOT trigger when product type is already clear (use specific skill directly).
2SKILL.mdUpdated May 14, 2026
petrogurcak/info-product-launch
testing
VerifiedTrustedCommunity
Specialized 8-week launch cadence for info-products — online courses, cohort programs, memberships, communities, ebooks, masterminds. Combines Jeff Walker's Product Launch Formula (Seed/Internal/JV variants, PLC sequence, open-cart day-by-day) with Stu McLaren's membership mechanics (closed cart, Success Path) and Hormozi Grand Slam Offer stacking. Use when planning "launch online kurzu", "info-product launch", "PLF launch", "course launch", "membership launch", "cohort launch", "ebook launch", "open cart close cart", "8-week launch of online course", "beta cohort to launch sequence", "spuštění kurzu", "launch členské sekce", "open cart strategie". Differentiates from marketing:launch-strategy (generic SaaS/app launches) — info-product-specific. NOT for SaaS launches, physical products, or services.
2SKILL.mdUpdated May 14, 2026
petrogurcak/mobile-store-release
development
VerifiedTrustedCommunity
Use when releasing an Expo/React Native mobile app to App Store and Google Play - covers eas submit, ASC "Submit for Review", Play promote Internal→Production, OTA update, and decoding common silent failures (Apple agreement expiry, missing English locale, Background Location declaration, web bundle failure on react-native-maps).
2SKILL.mdUpdated May 14, 2026