Install
$ agentstack add skill-theshubh007-agent-skill-finder-write-a-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Process
Step 1 — Gather Requirements
Ask the user:
- What task or domain does this skill cover?
- What specific use cases must it handle?
- Does it need executable scripts or instructions only?
- Are there reference materials to incorporate?
Step 2 — Draft the Skill
Produce:
SKILL.md— concise instructions (target under 100 lines)REFERENCE.md— detailed documentation if content exceeds 500 linesscripts/— utility scripts for deterministic, repeatable operations
Step 3 — Review With User
Present the draft and ask:
- Does this cover all intended use cases?
- Is anything missing or ambiguous?
- Should any section be expanded or reduced?
Directory Structure
skill-name/
├── SKILL.md # Primary instructions (required)
├── REFERENCE.md # Extended documentation (if needed)
├── EXAMPLES.md # Worked examples (if needed)
└── scripts/ # Utility scripts (if needed)
└── helper.js
SKILL.md Template
---
id: skill-name
name: Human-Readable Skill Name
version: 1.0.0
description: >
One-paragraph capability description. Specific enough for BM25 routing.
Use when [explicit trigger conditions].
capability:
type: data-transform|code-execution|retrieval|agentic-pipeline|ml-inference
inputs: [...]
outputs: [...]
graph:
depends_on: []
complements: [...]
co_used_with: [...]
compatibility:
claude_code: true
gemini: true
mcp: true
risk: safe|network|exec|critical|unsafe
---
## Quick Start
[Minimal working example]
## Workflows
[Step-by-step processes with checklists for complex tasks]
## Advanced Features
See REFERENCE.md
Description Requirements
The description field is the sole routing signal — the agent reads it to decide whether to load this skill. It must be specific enough to distinguish this skill from all others.
Requirements:
- Maximum 1024 characters
- Written in third person
- First sentence: what the skill does
- Second sentence: "Use when [specific triggers, keywords, file types, or user phrases]"
Good: > Extracts text, tables, and form fields from PDF files; merges and splits documents. Use when working with PDF files or when the user mentions forms, document extraction, or PDF processing.
Poor: > Helps with documents.
When to Add Scripts
Add a scripts/ entry when:
- The operation is fully deterministic (validation, formatting, linting)
- The same code would be regenerated repeatedly across invocations
- Explicit error handling is required for edge cases
When to Split Into Separate Files
Split when:
SKILL.mdexceeds 100 lines- Content spans distinct domains (e.g., finance schema vs. sales schema)
- Advanced reference material is rarely needed during normal use
Review Checklist
- [ ]
descriptionincludes explicit trigger conditions ("Use when...") - [ ]
SKILL.mdis under 100 lines - [ ] No time-sensitive or environment-specific information embedded
- [ ] Terminology is consistent throughout
- [ ] At least one concrete example is included
- [ ] Cross-references are one level deep (no nested includes)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: theshubh007
- Source: theshubh007/agent-skill-finder
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.