mem-search
Search past sessions, decisions and fixes in humona's memory; also timeline reports of what happened.
Skill by mesutcandemir39
Chalk Labs
Need help deploying mem-search?
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/mesutcandemir39-mem-search
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 and code. Checked Nov 1, 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/mem-search
What's inside
- Skill name
mem-search- Description
- Search past sessions, decisions and fixes in humona's memory; also timeline reports of what happened.
- License
- MIT
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# mem-search Progressive recall — stop at the cheapest layer that answers: 1. `humona search "<query in English>" -k 5` → index with 1-line snippets (hybrid keyword + semantic). Add `-t semantic|episodic|procedural|short-term|knowledge` to narrow, `--all` to include Archive. 2. `humona timeline -n 10` (or `--all`) → chronological one-liners of episodes/decisions. 3. `humona recall <path>` → full note, only for the 1-3 hits you actually need (bumps recall strength). Timeline report (when asked "what did we do…"): run `humona timeline -n 20 [--all]`, recall only ambiguous items, answer as a short dated list grouped by project. Cite note paths. If nothing found, say so — don't guess.
From mesutcandemir39/humona, MIT.
More from mesutcandemir39/humona
- 0.576score
knowledge-agent
mesutcandemir39
Build a queryable knowledge base from documents (docs folders, notes, exported text) and answer from it.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
learn-codebase
mesutcandemir39
Learn a repository deeply once and store it in humona's memory (card, map, key facts).
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
make-plan
mesutcandemir39
Research and write an implementation plan into humona's memory, then execute it step by step (do).
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
smart-explore
mesutcandemir39
Explore code structure and trace code paths/flows without reading whole files.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 20, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mesutcandemir39/humona
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mesutcandemir39
- 0.576score
knowledge-agent
mesutcandemir39
Build a queryable knowledge base from documents (docs folders, notes, exported text) and answer from it.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
learn-codebase
mesutcandemir39
Learn a repository deeply once and store it in humona's memory (card, map, key facts).
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
make-plan
mesutcandemir39
Research and write an implementation plan into humona's memory, then execute it step by step (do).
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
smart-explore
mesutcandemir39
Explore code structure and trace code paths/flows without reading whole files.
SkillAFreshness: A★ 1Claude 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 mem-search 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
mem-search skill. Agent Mart. https://agentmart.dev/skills/mesutcandemir39-mem-search (last updated 2026-10-24)