semantic-recovery
Skill for safely restoring code to previous valid states using Mnemosyne's semantic checkpoints and symbol-level restoration.
Skill by alessandrobrunoh
Chalk Labs
Need help deploying semantic-recovery?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/alessandrobrunoh-semantic-recovery
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/semantic-recovery
What's inside
- Skill name
semantic-recovery- Description
- Skill for safely restoring code to previous valid states using Mnemosyne's semantic checkpoints and symbol-level restoration.
- License
- Apache-2.0
- Instructions
- 22 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Semantic Recovery Instructions When this skill is active, you are a "Code Surgeon". Your goal is to restore lost logic or revert accidental breaking changes with surgical precision. ## Procedures 1. **Verify Context**: Use `mnem status --json` to ensure the daemon is running and watching the project. 2. **Identify Version**: Use `mnem h [file] --json` to find the exact version or snapshot ID you want to restore. 3. **Symbol Recovery**: If only a specific function or class is needed, use `mnem r [file] --symbol [name] --json` to see the version of that specific symbol. 4. **Validation**: After restoration, always verify the state by running the project's tests. ## Tools (CLI Commands) - `mnem r <file> <version> --json`: Restore a file to a specific version. - `mnem r <file> --symbol <name> --json`: Restore a specific symbol (function/class) within a file. - `mnem r --undo --json`: Undo the last restoration operation. ## Rules - Never restore an entire file if only a single symbol needs to be reverted. - Always check `mnem r --list --json` before performing a restoration to understand the available checkpoints. - Prefer restoring to a named checkpoint (`--checkpoint`) if one exists.
From alessandrobrunoh/Mnemosyne, Apache-2.0.
More from alessandrobrunoh/Mnemosyne
- 0.474score
history-analysis
alessandrobrunoh
Skill for tracing code evolution, identifying bug origins, and understanding structural changes using Mnemosyne's history and search tools.
SkillDFreshness: D★ 11Claude Code +9 - 0.474score
db-maintenance
alessandrobrunoh
Skill for maintaining the health and performance of the Mnemosyne redb-based semantic database and content-addressable storage (CAS).
SkillDFreshness: D★ 11Claude Code +9 - 0.471score
latency-optimization
alessandrobrunoh
Skill for monitoring daemon performance and optimizing response times for high-frequency history capturing.
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
security-audit
alessandrobrunoh
Skill for auditing the security of Mnemosyne's IPC channels, authentication tokens, and storage permissions.
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
diagnostic-report
alessandrobrunoh
Skill for generating comprehensive health and performance reports for the Mnemosyne ecosystem.
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
protocol-design
alessandrobrunoh
Skill for designing and evolving the Mnemosyne Protocol (MNP) and JSON-RPC interfaces.
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
ci-cd-integration
alessandrobrunoh
Skill for integrating Mnemosyne into automated CI/CD pipelines for semantic diffs and regression analysis.
SkillDFreshness: D★ 11Claude Code +9
Signals
- Stars
- 11
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Mar 10, 2026 (7 months ago)
- Last release
- Mar 8, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/alessandrobrunoh/Mnemosyne
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from alessandrobrunoh
- 0.474score
history-analysis
alessandrobrunoh
Skill for tracing code evolution, identifying bug origins, and understanding structural changes using Mnemosyne's history and search tools.
SkillDFreshness: D★ 11Claude Code +9 - 0.474score
db-maintenance
alessandrobrunoh
Skill for maintaining the health and performance of the Mnemosyne redb-based semantic database and content-addressable storage (CAS).
SkillDFreshness: D★ 11Claude Code +9 - 0.471score
latency-optimization
alessandrobrunoh
Skill for monitoring daemon performance and optimizing response times for high-frequency history capturing.
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
security-audit
alessandrobrunoh
Skill for auditing the security of Mnemosyne's IPC channels, authentication tokens, and storage permissions.
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
diagnostic-report
alessandrobrunoh
Skill for generating comprehensive health and performance reports for the Mnemosyne ecosystem.
SkillDFreshness: D★ 11Claude Code +9 - 0.466score
protocol-design
alessandrobrunoh
Skill for designing and evolving the Mnemosyne Protocol (MNP) and JSON-RPC interfaces.
SkillDFreshness: D★ 11Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get semantic-recovery running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
semantic-recovery skill. Agent Mart. https://agentmart.dev/skills/alessandrobrunoh-semantic-recovery (last updated 2026-10-24)