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

What

ASecurity

Use when the user asks what is going on and needs a five-line summary of the session, branch, pull request, and ticket.

3 stars
0 votes
0 copies
2 views
Added 9/19/2026
ai-agentsgobashgit

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add tony/skills --skill what --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of What?

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

Security grade badge for What
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tony-what/badge)](https://www.skillsdirectory.com/skills/tony-what)

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: what
description: "Use when the user asks what is going on and needs a five-line summary of the session, branch, pull request, and ticket."
allowed-tools: ["Bash", "Read", "Grep", "Glob"]
argument-hint: "[what you are confused about]"
user-invocable: true
disable-model-invocation: true
---


# What

The reader is disoriented. End that in five lines.

Read `../../references/brief.md` first — it defines the
five-line budget, what earns a line, the option lines, and the evidence
tiers that keep this cheap enough to ask casually.

User arguments: $ARGUMENTS

## Context

Current branch:
`!git branch --show-current 2>/dev/null || echo "(detached HEAD)"`

Ahead / behind trunk:
`!git rev-list --left-right --count "$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null || echo origin/main)"...HEAD 2>/dev/null || echo "(no comparison available)"`

Working tree:
`!git status --short 2>/dev/null | head -20 || echo "(unavailable)"`

Commits since trunk:
`!TRUNK=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null || echo origin/main); BASE=$(git merge-base HEAD "$TRUNK" 2>/dev/null); if [ -n "$BASE" ]; then git log --no-merges --format='%h %s' "$BASE..HEAD" | head -15; elif git rev-parse --verify --quiet "$TRUNK" >/dev/null; then echo "(no merge-base with $TRUNK)"; else echo "(trunk $TRUNK not found)"; fi`

## Procedure

### 1. Read what was actually asked

Empty `$ARGUMENTS` means the whole situation: what this session has been
doing, and where the repository stands.

An argument narrows it to that subject, and narrowing is the point —
`/situate:what the test failure` answers about the test failure and
spends no lines on branch position.

### 2. Answer from the session first

The conversation is the highest-value evidence and the cheapest. When
the confusion is about what just happened — a command that ran, a
decision taken, why the work moved — the answer is already in context
and needs no tools at all.

The context block above is local git, already gathered. It measures from
trunk, which is the cheap approximation this command is built on — on a
branch stacked over another branch that range carries the parent's
commits too, so treat the count as approximate and say so rather than
re-resolving the base for a five-line answer.

Go beyond the block only for the paid tier in the brief reference: a
pull request when the branch has one, a ticket when an ID appears in the
branch name, a commit, or the pull request body.

### 3. Write the brief

Five lines maximum, ranked as the brief reference sets out: the blocker
first, then position, then what just happened, then what it is for, then
what is outstanding. Stop early when the situation runs out.

Then numbered single-line options — only when there is a real fork.

## Rules

- Read-only, and the same contract as `/situate`: no commits, no edits,
  no branch switches, no `git fetch`.
- Five lines is a ceiling on the body, not a target. Three good lines is
  a better answer.
- No headings, no preamble, no bullets in the body, no closing summary.
- Never spend a line reporting that a layer was checked and was quiet.
- One hedged inference at most. Two means say what is unknown instead.
- No `AskUserQuestion` panel — the options are plain numbered lines. A
  modal is heavier than the answer it would follow, and this command is
  often reached ambiently, mid-thought.
- If the branch has wandered from what it was for, do not diagnose it
  here. Say so in a line and offer `/situate:refocus` as an option.
- No local absolute paths, no third-party personal details.

## Output

The body, then the options. Nothing else — no title, no framing
sentence, no offer to go deeper.

```
⚠ CI is red on PR #12: the type-check job fails on three files this branch added.
feat-brief-mode, 4 commits ahead of main, 2 files uncommitted.
This session rewrote the output contract and has not re-run the gates since.
The ticket asks for a terse mode; the terse mode works, the failing types do not.

1. Fix the three type errors and push
2. Show the failing job output
3. Stash the uncommitted work and check whether the branch alone is green
```

Attribution

tonytony
View sourceSee grades on GitHubMore from tony →
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', ...

698431 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 →