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

Lean Tighten

ASecurity

Use when tightening named files or pasted text in place by removing verbose prose, brittle references, and low-value noise.

3 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsbashgit

Works with

claude code

Security Analysis

A100/100

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

Scanned 9/19/2026

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

Installs into .claude/skills of the current project.

Are you the author of Lean Tighten?

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

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

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: lean-tighten
description: >-
  Use when tightening named files or pasted text in place by removing
  verbose prose, brittle references, and low-value noise.
disable-model-invocation: true
allowed-tools: ["Bash", "Read", "Grep", "Glob", "Edit", "AskUserQuestion"]
metadata:
  argument-hint: "[paths/globs] [--stdin] [--gates] [--diff-only]"
  source: "plugins/lean/skills/tighten/SKILL.md"
---

# this skill

Tighten specified files in the working tree and print a diff. Never
commits, never pushes, never requires a clean tree, never scans
repo-wide.

This skill is invoked by name, never routed to on the model’s initiative: it edits files,
so it must be user-explicit.

## Difference from the `slop-scan` skill

### Use this skill when

The slop is in files you are actively editing and you want a quick
in-place tidy with a diff to review — no commit ceremony, dirty tree
fine.

### Use the `slop-scan` skill when

You want repo-wide coverage with one reviewable, revertable commit per
finding, on a clean tree.

## `$ARGUMENTS`

- `paths/globs` — files to tighten (via `git ls-files -- <glob>` when
  tracked, else literal paths).
- `--stdin` — tighten a pasted draft read from stdin instead of files;
  print the tightened text and edit nothing.
- `--gates` — after editing, run the project's discovered
  format/lint/typecheck once and report. Never commits.
- `--diff-only` — show what would change without editing.

If `$ARGUMENTS` is empty, ask which files via `ask-user-choice`.

## Steps

1. **Resolve targets.** Expand paths/globs, or read stdin with
   `--stdin`. Reject an empty target set with a clear message.
2. **Load the rubric and voice.** Read
   `references/lean-rubric.md`, then `./AGENTS.md`
   and `./CLAUDE.md` for the host's rubric and accepted voice. For
   `--gates`, take the format/lint/typecheck commands from a checks
   section in those files; if none is defined, skip gates.
3. **Detect.** Flag slop per the rubric — AI signatures, brittle
   references, diff narration, prose inflation, coded labels, and
   tables where prose reads cleaner. Preserve every load-bearing
   reference and "why" comment.
4. **Preview and confirm.** Show the proposed edits and confirm via
   `ask-user-choice` before writing; the preview and the printed diff
   (Step 6) are the review surface. Skip when `--diff-only`.
5. **Apply in place.** Use `Edit`. Replacements must be concrete and
   shorter than the original.
6. **Diff.** Print `git diff -- <targets>`. With `--gates`, run the
   discovered checks once and report; commit on neither pass nor fail.
7. **Report and hand off.** Summarize findings resolved and skipped,
   then offer next steps via `ask-user-choice`: commit with `/commit`,
   run the `slop-scan` skill for repo-wide coverage, or discard the edits —
   review the printed diff first, since `git checkout -- <file>` resets
   the whole file to HEAD and drops any other uncommitted work in it.

## What this does not do

- Commit or push — you decide; use `/commit`.
- Rewrite history — that is the `pr-deslop` skill.
- Scan the whole repo — that is the `slop-scan` skill.
- Delete whole files — too consequential; report them instead.


## Portability notes

- `ask-user-choice` — present the listed options and wait for the user to pick one. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it; otherwise print a numbered list and wait for a numbered reply. Never proceed on an assumed answer.
- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.
- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.

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', ...

698461 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 →