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

Recall

ASecurity

Test your understanding of code the agent wrote. Run /recall after a slice you did not write, or when onboarding into an area. The agent asks, you answer; it never explains first.

10 stars
0 votes
0 copies
0 views
Added 10/1/2026
documentation

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/1/2026

$npx -y skills add pwguler/skills --skill recall --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Recall?

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

Security grade badge for Recall
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/pwguler-recall/badge)](https://www.skillsdirectory.com/skills/pwguler-recall)

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: recall
description: Test your understanding of code the agent wrote. Run /recall after a slice you did not write, or when onboarding into an area. The agent asks, you answer; it never explains first.
disable-model-invocation: true
---

Never explain first. No walkthrough, no orientation, no "quick context before we start", no label for where the session begins. An explanation followed by "does that make sense" is the exact substitution this skill exists to prevent.

Rules:
- Work from the slice that just landed, or the area the user named.
- Pick the spots where being wrong is expensive: invariants, error paths, ordering assumptions, anything touching money or auth. Never line by line.
- Ask one question at a time, about behavior and consequence, not syntax. "What happens if this runs twice" beats "what does this function do". Never list the questions up front; reading ahead is not being asked.
- Carry three or four candidate answers with it, the way `core-interview` carries them, with one difference: mark none of them. A fork has no right answer, a probe has one in the code, and a marked option hands it over. Wrong answers come from how this code gets misread, not from filler. Use the harness question tool when it has one; without it, number the options in the reply and close with "or something else"; an answer the options missed stays right. A decision question waits until the session is over.
- Never take a pick without the reason: ask for it with every probe, one line. The pick is cheap and can be a guess; the reason is what gets scored against the code, and a hollow one shows the gap the pick hid.
- Stay silent after asking. The wait is the mechanism. An absent answer is an answer.
- On a wrong pick, a hollow reason, or no answer, state the gap in one sentence, then explain that spot. Explaining after the attempt is repair. Explaining before it is the failure.
- If a probe surfaces a real defect, note it and keep recalling. Repairs come after the session, through the normal loop.
- A slice small enough to hold in one glance needs no recall; say so and stop.
- When the questions run out, report the gaps found, in a few lines, and stop. Record nothing. A generated document substitutes the appearance of understanding for the real thing. If something durable emerges, it is a `CONTEXT.md` term per [terms.md](references/terms.md) or an ADR per [decision-record.md](references/decision-record.md), and the user decides.

Attribution

pwgulerpwguler
View sourceSee grades on GitHubMore from pwguler →
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

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

Architecture Diagram Creator

Create comprehensive HTML architecture diagrams with data flows, business context, and system architecture.

6661 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in W...

1798860 votes
View all in documentation →