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

HTMLReport Compact

ASecurity

Produce a COMPACT HTML report from a Claude Code session — small enough to render inline in Claude's preview. Use when the user asks for a compact report, a small report, a report they can read here, or a preview of the audit.

2 stars
0 votes
2 copies
8 views
Added 9/19/2026
ai-agentsbashgit

Works with

claude codecli

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add jagmeetchawla/gitreceipts --skill HTMLReport-Compact --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of HTMLReport Compact?

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

Security grade badge for HTMLReport Compact
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jagmeetchawla-htmlreport-compact/badge)](https://www.skillsdirectory.com/skills/jagmeetchawla-htmlreport-compact)

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
---
description: Produce a COMPACT HTML report from a Claude Code session — small enough to render inline in Claude's preview. Use when the user asks for a compact report, a small report, a report they can read here, or a preview of the audit.
---

# Compact HTML report — small enough to read right here

Same receipt as `/gitreceipts:audit`, rendered as a self-contained page and
kept small on purpose: commits with unexplained findings keep their full
file and command lists, everything else collapses to its headline, and long
prose and captured output are clipped. A full report runs several hundred
KB and preview panes choke; this one is a fraction of that.

**This is the one that renders inline.** Write the file and hand back the
path — let the preview show it. Don't open a browser unless the user asks;
that's `/gitreceipts:HTMLReport-Full`'s job.

## Run it

Requires the `git-receipts` binary (0.1.1+) — `/gitreceipts:recap` owns the
install and upgrade offers if it's missing or old.

```bash
F="${TMPDIR:-/tmp}/gitreceipts-report.html"
git receipts audit --format html --compact > "$F" && echo "$F"
```

Match the scope to whatever the user is asking about — the same flags every
other skill takes: `--commit <hash>` (much smaller, ~20KB — the best case
for inline preview), `--project`, `--latest`, `--this-session <marker>`,
`--full-history`. For the story rather than the verdict, swap `audit` for
`recap`; the page framing follows the command.

State the path. It lands OUTSIDE the repo deliberately — a report must not
leave files its own next run would flag as residue. If the user wants it
kept somewhere, regenerate to the path they name.

## What to tell them

Say what the page contains and what it hides: every cap in a compact page
announces how much it omitted, and the JSON receipt
(`/gitreceipts:JSONExport`) is always complete. If they need the full
inventory for every commit, that's `/gitreceipts:HTMLReport-Full`.

## Privacy

The page is built from the user's prompts and command output — private by
default. Whenever sharing comes up, name the flags in the same breath:
`--no-intent` (drops the conversation, keeps every count), `--no-identity`
(drops names and emails), `--redact <word>`. Home paths are masked
automatically. **Never pass `--no-scan`** — the secret/PII scanner stays on.

Attribution

jagmeetchawlajagmeetchawla
View sourceSee grades on GitHubMore from jagmeetchawla →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

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 Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

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".

1087401 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', ...

697551 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 →