getspecstory
Converts ad-hoc conversation histories into documented, reusable skills that persist across projects, reducing repetitive prompt engineering and enabling ins…
SpecStory captures and auto-saves your AI coding sessions locally to .specstory/history/ across Claude Code, Cursor, Copilot, Codex CLI, Gemini CLI, and more, making them searchable and shareable. Its Lore component mines saved sessions into reusable agent skills based on how you actually work. Local-first — data stays on your machine unless you sync to cloud.specstory.com.
- Ask Claude to install the getspecstory extension in your IDE to capture and organize conversation histories.
- Generate reusable skills from past conversations using Lore to avoid repeating similar tasks.
- Sync your local conversation data to the cloud for access across multiple devices and teams.
Converts ad-hoc conversation histories into documented, reusable skills that persist across projects, reducing repetitive prompt engineering and enabling institutional knowledge capture within development workflows.
Development teams using AI IDEs or terminal agents who need to standardize and reuse complex task patterns across multiple projects.
https://github.com/specstoryai/getspecstory
By specstoryai
How to Get It
brew tap specstoryai/tap && brew install specstory — then launch with auto-save: specstory run claude. Lore skill: npx skills add specstoryai/getspecstory --skill lore
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Install the getspecstory extension in my IDE to capture and organize conversation histories
Trust Signals Auto-scanned
Community Pulse Active
Discussed on Hacker News
- Why Git is no "good" for AI-generated code — Hacker News · 35 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 1,261 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 1,261 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.