Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Suggest Skill Capture

ASecurity

After completing a genuinely teachable piece of work in this session (a multi-step task that followed project/team conventions, touched several files in a deliberate order, or encoded knowledge not written down anywhere), offer the user, at most once per session, to capture it as a skill via /handbook:learn. Never for routine or trivial work.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgo

Works with

cli

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add AhmetErenLapanta/TeamHandbook --skill suggest-skill-capture --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Suggest Skill Capture?

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

Security grade badge for Suggest Skill Capture
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ahmeterenlapanta-suggest-skill-capture/badge)](https://www.skillsdirectory.com/skills/ahmeterenlapanta-suggest-skill-capture)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: suggest-skill-capture
description: After completing a genuinely teachable piece of work in this session (a multi-step task that followed project/team conventions, touched several files in a deliberate order, or encoded knowledge not written down anywhere), offer the user, at most once per session, to capture it as a skill via /handbook:learn. Never for routine or trivial work.
---

TeamHandbook turns real session learnings into reviewed skills the user keeps, scopes to
a repo, or shares with their team. You are its in-session judgment for FIRST-TIME
procedures: the end-of-session harvest reads the conversation once, but you can
recognize a teachable task the moment it lands, because you just did it with full
context.

## When to offer

Offer only when ALL of these hold:

- The task is **complete and verified** (tests/build passed, or the user confirmed).
- It took **multiple meaningful steps in a deliberate order** — the kind of thing a
  teammate would do differently (or slower, or wrong) without guidance.
- The knowledge is **not trivially rediscoverable** from the code, README, or a
  quick search: project conventions, cross-file wiring, easy-to-miss requirements.
- Similar tasks are **plausibly recurring** for this user or team.

Never offer for: one-liners, boilerplate any tool scaffolds, routine edits, tasks
whose entire content is already documented, or anything you are not confident was
done correctly. At most ONE offer per session; if the user declines or ignores it,
do not offer again.

## How to offer

One short sentence, after the task is done, e.g.:

> This looked like a repeatable procedure (X steps, touches the usual Y conventions)
> — want me to capture it as a skill candidate with /handbook:learn? You'll choose at
> review whether to keep it for yourself, put it in this repo, or share it with the team.

If the user agrees, follow the `/handbook:learn` command's procedure mode: gather
the goal, the ordered meaningful steps actually taken, how success was verified,
and the files touched — strictly from this session, inventing nothing — and submit
them. The candidate is scored (a low score travels with it as advice at review, never
as a veto); relay the CLI's message verbatim.

Attribution

AhmetErenLapantaAhmetErenLapanta
View sourceMore from AhmetErenLapanta →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 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', ...

686011 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →