RE

recall-before-claim

A guardrail that ensures the agent performs a memory search before making any factual assertions.

Install

mkdir -p .claude/skills/recall-before-claim && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17089" && unzip -o skill.zip -d .claude/skills/recall-before-claim && rm skill.zip

Installs to .claude/skills/recall-before-claim

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Forces a memory_search before the agent sends a message containing a factual assertion that has not yet been grounded this turn. Closes the citation-rate gap from ~40% to ~90%+.
177 charsno explicit “when” trigger
Beginner

Key capabilities

  • Intercept outgoing messages
  • Detect unverified factual assertions
  • Require a memory_search call
  • Integrate memory search results
  • Prevent ungrounded assertions

How it works

An interceptor checks outgoing messages for factual assertions; if no memory tool has fired, it forces a memory_search before the message is sent.

Inputs & outputs

You give it
Agent's draft message containing a factual assertion
You get back
Agent's message grounded by memory_search results

When to use recall-before-claim

  • Prevent hallucinated factual claims
  • Improve citation accuracy
  • Ground responses in historical data

About this skill

recall-before-claim

This skill installs a deterministic guard around the agent's outgoing messages. When the candidate message contains a factual-assertion shape ("X is Y", "A did B") and no memory tool (memory_search / deep_recall / knowledge_graph_search) has fired in the current turn, the interceptor requires a memory_search call against the assertion's subject before the message goes out.

Why this exists

Bitterbot has a strong memory system, but it only helps the user if the agent actually consults it before making claims. In practice the agent skips memory recall a meaningful fraction of the time — relying on its in-context knowledge instead. This produces ungrounded assertions that the user has no easy way to spot.

The interceptor closes that loop without depending on the LLM remembering to do it.

What you'll see

When this fires, the agent will run a memory_search first, integrate the result, and then send. You may notice slightly longer responses to factual questions; you should notice that the agent stops making confidently wrong statements about things it actually has memory of.

How it decides not to fire

  • Opinion shapes ("I think", "maybe", "in my opinion") are skipped.
  • Questions are skipped.
  • If a memory tool already fired in the last ~30 seconds, the assertion is considered grounded.

Implementation

Built-in interceptor recall-before-claim:default lives in src/agents/skills/builtin-interceptors/recall-before-claim.ts. Fires at most 8 times per session.

When not to use it

  • When the message contains opinions
  • When the message is a question
  • When a memory tool has recently fired

Limitations

  • The interceptor fires at most 8 times per session.
  • The interceptor only acts on factual assertions, not opinions or questions.
  • The interceptor considers assertions grounded if a memory tool fired in the last ~30 seconds.

How it compares

This skill programmatically enforces memory recall for factual claims, unlike relying on the LLM to remember to consult its memory.

Compared to similar skills

recall-before-claim side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
recall-before-claim (this skill)03moNo flagsBeginner
using-superpowers953moNo flagsBeginner
ultrawork112moNo flagsAdvanced
clawhub253moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

using-superpowers

obra

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

95205

ultrawork

Yeachan-Heo

Parallel execution engine for high-throughput task completion

11184

clawhub

openclaw

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

25151

skill-installer

openai

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

29141

continuous-learning

affaan-m

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

995

memory-keeper-proactive-context-maintenance

b4CU-R4U

Automatically detect and maintain memory freshness by monitoring context staleness, significant code changes, task completions, and phase transitions. Proactively suggests and executes memory sync operations with user confirmation. Use when the user says "sync memory", "update context", or when the Skill detects that context is stale (>2 hours), significant changes have occurred (new commits), tasks completed, or major milestones reached. Replaces passive "context is stale" warnings with active maintenance.

694

Search skills

Search the agent skills registry