recall-memory
Retrieve relevant lixSearch conversation context and semantic memory.
Skill by pollinations
Chalk Labs
Need help deploying recall-memory?
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/pollinations-recall-memory
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/recall-memory
What's inside
- Skill name
recall-memory- Description
- Retrieve relevant lixSearch conversation context and semantic memory. Use when a user refers to an earlier message, requests a recap or continuation, or needs facts established previously in the session.
- License
- CC0-1.0
- Instructions
- 28 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Recall Memory
Retrieve only the context needed for the current request.
## Workflow
1. Use `get_session_conversation_history`; trust the pipeline session ID.
2. Prefer the hot recent window for ordinary follow-ups.
3. Request broader history only for summaries or older references.
4. Deduplicate messages and trim context to the token budget.
5. Return relevant messages with roles and timestamps when available.
## Guardrails
- Do not invoke memory for self-contained requests.
- Never expose internal session identifiers or storage details.
- Treat memory as context, not fresh external evidence.
- Fail open when memory is unavailable.
## Runtime contract
agent: memory
tools: [get_session_conversation_history]
timeout_seconds: 3
max_concurrency: 1
output: context_bundleFrom pollinations/search.elixpo, CC0-1.0.
More from pollinations/search.elixpo
- 0.607score
make-images
pollinations
Create a new image from a user request.
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
know-oreolook-creator
pollinations
Provide verified creator and project-origin metadata for OreoLook.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
orchestrate-search
pollinations
Route lixSearch requests to the smallest useful set of specialist skills and arrange independent work in parallel.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
oreolook-persona
pollinations
Apply the OreoLook voice to user-facing answers.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
research-web
pollinations
Find, fetch, and verify current web information for lixSearch.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
synthesize-answer
pollinations
Combine lixSearch research, media, and conversation context into one clear streamed response.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
write-code
pollinations
Plan, write, review, and verify bounded software changes.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
write-content
pollinations
Draft, rewrite, summarize, and structure clear written content.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
communicate-naturally
pollinations
Adapt OreoLook responses to the user's language, dialect, and conversational register; translate text naturally; and present human-facing dates consistently.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
handle-media
pollinations
Process visual, YouTube, and audio inspection requests in lixSearch.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
export-documents
pollinations
Prepare and export lixSearch answers as polished PDF documents.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
optimize-search-runtime
pollinations
Select and execute the smallest sufficient OreoLook search plan.
SkillBFreshness: B★ 24Claude Code +9
Signals
- Stars
- 24
- Forks
- 6
- Open issues
- 8
- Last commit (this folder)
- Jul 25, 2026 (3 months ago)
- Last release
- Mar 27, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- CC0-1.0
- Repository
- github.com/pollinations/search.elixpo
- Website
- search.elixpo.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from pollinations
- 0.834score
Computer
pollinations
A private persistent computer: files and a bash shell that survive between runs.
ConnectorAFreshness: ARemote★ 5.2KClaude Code +3 - 0.834score
Ask Jev
pollinations
Evaluate state with typed choice, score, and probability questions.
ConnectorAFreshness: ARemote★ 5.2KClaude Code +3 - 0.834score
Pollinations
pollinations
Access Pollinations models and API capabilities through agent tools.
ConnectorAFreshness: ARemote★ 5.2KClaude Code +3 - 0.834score
Exa Search
pollinations
Search the live web and fetch clean content from source pages.
ConnectorAFreshness: ARemote★ 5.2KClaude Code +3 - 0.834score
Connected Apps
pollinations
Read Gmail, search GitHub, update Sheets, and post to Slack through Composio.
ConnectorAFreshness: ARemote★ 5.2KClaude Code +3 - 0.831score
FFmpeg
pollinations
Trim, convert, resize, compress, and remix audio and video.
ConnectorAFreshness: ARemote★ 5.2KClaude Code +3
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 recall-memory 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
recall-memory skill. Agent Mart. https://agentmart.dev/skills/pollinations-recall-memory (last updated 2026-10-24)