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

Coverage

ASecurity

Code coverage skills: fix low coverage, enforce thresholds in CI, or audit coverage.config.xml for drift. Determines mode from user intent automatically. Triggers on: coverage fix, low coverage, improve coverage, fix low coverage, coverage gate, coverage threshold, enforce coverage, minimum coverage, coverage enforcement, add coverage gate, audit coverage config, coverage config drift, coverage.config.xml, check coverage targets, fix coverage config, stale coverage config, coverage missing pr...

2 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsgit

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add e128/dotnet-reference --skill coverage --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Coverage?

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

Security grade badge for Coverage
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/e128-coverage/badge)](https://www.skillsdirectory.com/skills/e128-coverage)

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: coverage
description: >
  Code coverage skills: fix low coverage, enforce thresholds in CI, or audit coverage.config.xml
  for drift. Determines mode from user intent automatically.
  Triggers on: coverage fix, low coverage, improve coverage, fix low coverage, coverage gate,
  coverage threshold, enforce coverage, minimum coverage, coverage enforcement, add coverage gate,
  audit coverage config, coverage config drift, coverage.config.xml, check coverage targets,
  fix coverage config, stale coverage config, coverage missing project, coverage work, coverage skill.
argument-hint: "[fix | gate | config-audit]"
---

# Coverage Skill

Determine mode from user intent, then execute.

| User wants to... | Mode | Key phrases |
|-------------------|------|-------------|
| Fix classes with low test coverage | **Fix** (below) | coverage fix, low coverage, improve coverage |
| Add/maintain coverage threshold in CI | **Gate** (below) | coverage gate, coverage threshold, enforce coverage |
| Audit coverage.config.xml for drift | **Config Audit** (below) | audit coverage config, coverage config drift, coverage.config.xml |

If ambiguous, ask which coverage task they need.

---

## Mode: Fix

Parse coverage output, identify lowest-covered classes, route to `fill-test-gaps` for test generation.

### Input Formats

Accepts three formats (pasted as `$ARGUMENTS` or message body):
- **Format A: Spectre Console ANSI**: `[#hex]-  NN.N%[/]  ClassName`
- **Format B: Pipe/tab table**: `| Class | Line Coverage | Branch Coverage |`
- **Format C: Summary text**: `ClassName  NN.N%`

### Workflow

1. **Parse input**: extract `(class_name, coverage_percentage)` pairs
2. **Rank and filter**: sort ascending, remove 100% and test classes, take bottom 15
3. **Present selection**: show ranked list, ask: "Which classes? (numbers, 'all', or 'top 5')"
4. **Locate source files**: `scripts/find.sh --class {ClassName}`
5. **Dispatch to fill-test-gaps**: spawn agents (up to 3 parallel) for selected classes
6. **Summary**: report before coverage + tests generated

### Rules

- Never skip the selection prompt
- Parallel limit of 3 fill-test-gaps agents
- This skill parses output: it does not run coverage. Direct users to run coverage tools first.

---

## Mode: Gate

Add or verify a coverage threshold enforcement step in CI.

### Steps

1. Read `.github/workflows/ci.yml`. Read `coverage.config.xml` if it exists
2. Determine threshold (user-specified or default 80% line coverage)
3. If no enforcement exists, propose a `reportgenerator` step that fails the build below threshold
4. Use `AskUserQuestion` to get approval before writing workflow changes:
```
AskUserQuestion({
  questions: [{
    question: "Apply coverage gate changes to the CI workflow?",
    header: "CI gate",
    options: [
      { label: "Apply", description: "Write changes to .github/workflows/ci.yml" },
      { label: "Cancel", description: "No changes made" }
    ],
    multiSelect: false
  }]
})
```
5. Verify `reportgenerator` is in the dotnet tool manifest
6. Apply changes + validate YAML

### Rules

- Never lower an existing threshold without approval
- Use `AskUserQuestion` for approval before writing workflow changes
- If `coverage.config.xml` is missing, warn: run config-audit first

---

## Mode: Config Audit

Cross-reference `coverage.config.xml` against the project list from `scripts/solution-inventory.sh --json` to catch silent drift. If `coverage.config.xml` does not exist, report that and stop.

### Steps

1. Read `coverage.config.xml`: extract `<ModulePath>` patterns in Include/Exclude
2. Run `scripts/solution-inventory.sh --json`: derive expected DLL names per project
3. Classify includes: match against src/ DLLs. Flag **dead entries** (no matching project) and **missing coverage** (no include pattern)
4. Classify excludes: verify test/benchmark assemblies still exist
5. Render audit report with missing/dead/valid counts
6. If issues found, ask once: "Apply suggested fixes?", add missing, remove dead, preserve comments

### Notes

- DLL name may differ from project name, check `.csproj` for `<AssemblyName>` override
- Only `src/` projects warrant coverage inclusion
- Regex patterns use .NET syntax: escape dots as `\.`

Attribution

e128e128
View sourceSee grades on GitHubMore from e128 →
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 →