Prospective Memory Followthrough
Execute a requested action after a delay (e.g., in N turns) or at a specific future condition.
Skill by maksim-tsi
Chalk Labs
Need help deploying Prospective Memory Followthrough?
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/maksim-tsi-prospective-memory-followthrough
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/prospective-memory-followthrough
What's inside
- Skill name
Prospective Memory Followthrough- Description
- Execute a requested action after a delay (e.g., in N turns) or at a specific future condition. Keywords: in 2 turns, after responding, on my 5th message, later, remind me, append on response N.
- License
- MIT
- Compatibility
- YAAM runtime agents (OpenAI-compatible chat, LangGraph ToolRuntime / AutoGen function calling)
- Metadata
- yaam.layer: policy · yaam.mechanism_contract: docs/specs/spec-mechanism-maturity-and-freeze.md
- Instructions
- 13 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Prospective Memory Followthrough" does not match folder "prospective-memory-followthrough"
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
## Policy - Track delayed instructions precisely (turn counts and conditions). - When the trigger condition is met (e.g., "5th response"), perform the action exactly then. - If the user asks to cancel/forget the delayed instruction, stop applying it immediately. ## Output Rules - Always produce the user-facing answer for the current turn. - If a delayed action triggers on this turn (e.g., "append the quote"), append it after the main answer exactly as requested. - Do not output routing/planning text (no "selected_skill", "why", "next_action").
From maksim-tsi/yet-another-agents-memory, MIT.
More from maksim-tsi/yet-another-agents-memory
- 0.398score
Skill Builder (YAAM)
maksim-tsi
Use when creating or updating YAAM skills (policy artifacts) for runtime agents, especially for multi-agent memory management, knowledge lifecycle automation…
SkillDFreshness: DClaude Code +9 - 0.395score
Skill Selection (Executive Function)
maksim-tsi
Select the most appropriate YAAM skill(s) for the current user intent and constraints.
SkillDFreshness: DClaude Code +9 - 0.395score
L3 Similar Episodes (Qdrant Episodic Memory)
maksim-tsi
Find semantically similar past episodes (L3) using vector similarity search.
SkillDFreshness: DClaude Code +9 - 0.395score
CIAR Scoring and Promotion Gating
maksim-tsi
Decide what should be promoted to L2 working memory using CIAR (certainty×impact×age decay×recency boost).
SkillDFreshness: DClaude Code +9 - 0.395score
Context Block Retrieval (L1+L2+L3+L4)
maksim-tsi
Retrieve a focused context block for a session: recent turns, significant facts (CIAR), episode summaries, and knowledge snippets.
SkillDFreshness: DClaude Code +9 - 0.395score
Knowledge Lifecycle Distillation
maksim-tsi
Distill reusable patterns/rules from multiple episodes and store them as knowledge candidates with provenance.
SkillDFreshness: DClaude Code +9 - 0.395score
L2 Fact Lookup (Postgres Working Memory)
maksim-tsi
Perform fast keyword fact lookup in L2 working memory (Postgres tsvector).
SkillDFreshness: DClaude Code +9 - 0.395score
L3 Graph Traversal (Neo4j Templates)
maksim-tsi
Safely answer relationship and timeline questions via template-based L3 graph traversal (Neo4j).
SkillDFreshness: DClaude Code +9 - 0.395score
Retrieval-Reasoning Gap Mitigation
maksim-tsi
Mitigate cases where retrieved facts are present but the model ignores them or contradicts them.
SkillDFreshness: DClaude Code +9 - 0.395score
L4 Knowledge Synthesis (Typesense + Synthesizer)
maksim-tsi
Synthesize distilled knowledge (L4) into an answer with provenance and conflict detection.
SkillDFreshness: DClaude Code +9 - 0.392score
Skill Name
maksim-tsi
One sentence describing when to use this skill, with concrete keywords for matching.
SkillDFreshness: DClaude Code +9 - 0.390score
Roleplay + Instruction Following
maksim-tsi
Stay in a requested role (e.g., customer vs waiter) and follow scenario constraints.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 21, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from maksim-tsi
- 0.398score
Skill Builder (YAAM)
maksim-tsi
Use when creating or updating YAAM skills (policy artifacts) for runtime agents, especially for multi-agent memory management, knowledge lifecycle automation…
SkillDFreshness: DClaude Code +9 - 0.395score
L3 Similar Episodes (Qdrant Episodic Memory)
maksim-tsi
Find semantically similar past episodes (L3) using vector similarity search.
SkillDFreshness: DClaude Code +9 - 0.395score
CIAR Scoring and Promotion Gating
maksim-tsi
Decide what should be promoted to L2 working memory using CIAR (certainty×impact×age decay×recency boost).
SkillDFreshness: DClaude Code +9 - 0.395score
Context Block Retrieval (L1+L2+L3+L4)
maksim-tsi
Retrieve a focused context block for a session: recent turns, significant facts (CIAR), episode summaries, and knowledge snippets.
SkillDFreshness: DClaude Code +9 - 0.395score
Knowledge Lifecycle Distillation
maksim-tsi
Distill reusable patterns/rules from multiple episodes and store them as knowledge candidates with provenance.
SkillDFreshness: DClaude Code +9 - 0.395score
L2 Fact Lookup (Postgres Working Memory)
maksim-tsi
Perform fast keyword fact lookup in L2 working memory (Postgres tsvector).
SkillDFreshness: DClaude 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 Prospective Memory Followthrough 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
Prospective Memory Followthrough skill. Agent Mart. https://agentmart.dev/skills/maksim-tsi-prospective-memory-followthrough (last updated 2026-10-24)