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.zipInstalls 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%+.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
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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| recall-before-claim (this skill) | 0 | 3mo | No flags | Beginner |
| using-superpowers | 95 | 3mo | No flags | Beginner |
| ultrawork | 11 | 2mo | No flags | Advanced |
| clawhub | 25 | 3mo | Review | Intermediate |
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
ultrawork
Yeachan-Heo
Parallel execution engine for high-throughput task completion
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.
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).
continuous-learning
affaan-m
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
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.