Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Anti Amnesia

ASecurity

Answer retrospective questions about immediately preceding work from the current conversation and tool record without needless re-execution, and close tool-using work with the shared handoff receipt. Use when the user asks what you just did, changed, ran, found, tested, or concluded. Do not use for requests to verify present state or investigate new changes.

2 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agents

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add MTEnt/special-skills --skill anti-amnesia --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Anti Amnesia?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Anti Amnesia
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mtent-anti-amnesia/badge)](https://www.skillsdirectory.com/skills/mtent-anti-amnesia)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: anti-amnesia
description: Answer retrospective questions about immediately preceding work from the current conversation and tool record without needless re-execution, and close tool-using work with the shared handoff receipt. Use when the user asks what you just did, changed, ran, found, tested, or concluded. Do not use for requests to verify present state or investigate new changes.
license: MIT
metadata:
  version: "0.2.0"
  author: MTEnt
---

# Anti-Amnesia

Treat a question about your immediately preceding work as retrospective unless the user asks whether that state remains true now.

## Recall recent work

1. Use the available record in this order: tool results from the relevant turn, the completed assistant response, the most recent receipt, then any compacted conversation summary.
2. Answer directly from that record. Do not call tools merely to rediscover actions already recorded.
3. Distinguish actions performed, checks and observed results, and anything left unresolved. Keep the answer proportional to the question.
4. Do not claim that recorded state is current unless it was verified in the present turn.

If the record is missing, ambiguous, or contradictory, say exactly what cannot be recovered. Do not silently reconstruct it by inspecting the workspace. Inspect only when the user requests current-state verification or asks you to reconstruct the missing record.

## Preserve verification

Use tools normally when the user asks what exists now, whether something still works, or for a fresh check. A retrospective answer and a present-state verification are different tasks; state which one you are providing when that distinction matters.

<!-- contract:handoff-receipt:start -->
## Close with a receipt

After tool-using or mutating work, end the response with a compact factual receipt. Omit it when no work was performed. Every line comes from the recorded actions of this session, not from memory of what was intended.

```text
RECEIPT
Outcome: <what was delivered or decided>
Changed: <files, systems, or state touched; "none" when read-only>
Verified: <checks run and their observed results>
Unverified: <claims, risks, or checks that were skipped, with the reason>
Open: <blocked or deferred items and who decides>
```
<!-- contract:handoff-receipt:end -->

The receipt is the record a later retrospective question is answered from. Write it so a reader who sees nothing else knows what happened, what was proven, and what was not.

Attribution

MTEntMTEnt
View sourceSee grades on GitHubMore from MTEnt →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →