poorrican/package-skill
configs/claude-code/skills/package-skill/SKILL.md
Package a Claude Code skill directory into a distributable .skill file. Use when the user wants to export, package, bundle, zip, or distribute a skill. Triggers on mentions of .skill files, packaging skills, exporting skills, or sharing skills.
development
Updated Apr 18, 2026
$ install --global
skillsauthnpx skillsauth add poorrican/dotfiles package-skillInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 18, 2026, 5:42 AM10.8s1 file scanned
SKILL.md
- name:
- package-skill
- description:
- Package a Claude Code skill directory into a distributable .skill file. Use when the user wants to export, package, bundle, zip, or distribute a skill. Triggers on mentions of .skill files, packaging skills, exporting skills, or sharing skills.
- allowed-tools:
- Read, Glob, Grep, Bash(zip *), Bash(unzip *), Bash(ls *), Bash(find *), Bash(file *), Bash(mkdir *), Bash(cat *), Bash(wc *)
Package Skill (.skill)
Package a Claude Code skill directory into a distributable .skill file.
What is a .skill file?
A .skill file is a zip archive containing a complete skill directory. It preserves the directory structure so the recipient can install it by unzipping into their skills location.
my-skill.skill (zip archive)
└── my-skill/
├── SKILL.md # Required
├── reference/ # Optional nested docs
│ └── *.md
└── *.sh / *.py # Optional scripts
Packaging Workflow
-
Identify the skill to package. Ask the user which skill directory to package. Check both locations:
- Project skills:
.claude/skills/*/SKILL.md - Personal skills:
~/.claude/skills/*/SKILL.md
- Project skills:
-
Validate the skill directory. Before packaging, verify:
SKILL.mdexists and has valid YAML frontmatter (name:anddescription:fields)- All files referenced in SKILL.md (e.g.,
reference/*.md, scripts) actually exist - No absolute paths leak into the SKILL.md content (all references should be relative like
reference/guide.md) - No secrets, API keys,
.envfiles, or credentials are included - Shell scripts have executable permissions (
chmod +x)
-
Run pre-package checks. Report to the user:
- Skill name (from frontmatter)
- File count and total size
- List of all files that will be included
- Any warnings (absolute paths, missing references, large files > 100KB)
-
Create the .skill file. Package the skill:
cd <parent-of-skill-dir> && zip -r <output-path>/<skill-name>.skill <skill-dir-name>/The zip must contain the skill directory as the top-level entry (not loose files).
-
Verify the package. After creating:
unzip -l <skill-name>.skillConfirm the structure looks correct.
-
Report the result. Tell the user:
- Output file path and size
- How to install:
unzip <name>.skill -d ~/.claude/skills/ - How to install project-wide:
unzip <name>.skill -d .claude/skills/
Validation Rules
SKILL.md Frontmatter
The SKILL.md must have valid frontmatter with at least:
---
name: skill-name
description: When to use this skill...
---
Optional frontmatter fields:
allowed-tools:— restricts which tools the skill can use
Relative References
All file references in SKILL.md must be relative to the skill directory. Flag these patterns as errors:
- Absolute paths:
/Users/...,/home/...,~/... - Project-relative paths:
.claude/skills/skill-name/reference/... - Source tree paths:
configs/...,src/...
Correct pattern: reference/guide.md, create_profile.sh
Excluded Files
Do not include in the package:
.DS_Storefiles__pycache__/directories.envor credentials files.git/directories- Files larger than 1MB (warn and ask user)
Use zip exclusion flags:
zip -r <output>.skill <dir>/ -x "*.DS_Store" -x "*__pycache__/*" -x "*.env" -x "*/.git/*"
Installing a .skill File
To install a .skill file:
# Personal (available in all projects):
unzip skill-name.skill -d ~/.claude/skills/
# Project-specific:
unzip skill-name.skill -d .claude/skills/
The skill is available immediately — no restart needed.
Output Location
Place the .skill file in the current working directory unless the user specifies otherwise.
Related Skills
poorrican/stacked-issues
development
VerifiedTrustedCommunity
Implement multiple GitHub issues sequentially as stacked branches in separate worktrees, with an implementer sub-agent and an independent reviewer sub-agent per issue. Use when the user gives you two or more dependent issues and asks for them to be implemented in order, or says "stacked branches", "sequential issues", "issue chain", "do these in worktrees", or describes a parent epic with child issues that build on each other. Also reach for this whenever the user wants implementation and verification done by separate agents.
SKILL.mdUpdated May 10, 2026
poorrican/research-proposal-structure
testing
VerifiedTrustedCommunity
Use when an agent needs to produce, update, validate, or normalize a standardized research proposal artifact without running an interview. Defines the canonical structure, confidence-tag semantics, decision logic, and completion checks for proposal.md-style research plans.
SKILL.mdUpdated May 5, 2026
poorrican/research-proposal-interview
development
VerifiedTrustedCommunity
Conducts a structured Socratic interview to produce a comprehensive markdown research proposal that handles cascading uncertainty (fixed end-question, branching experiments). Use this skill whenever the user wants to write a research proposal, research plan, study design, experiment plan, thesis proposal, RFC, or "spec out" a research direction — even if they don't explicitly say "interview me." Trigger when the user says things like "help me plan this research", "I want to design experiments for X", "draft a proposal for...", "think through a research direction", or shares a half-formed research idea and asks for help structuring it. The skill interviews the user, challenges their priors with evidence requests and falsifiers, optionally uses sub-agents to explore prior art, and builds the proposal markdown incrementally so context stays clean and the document is always grounded.
SKILL.mdUpdated May 5, 2026
poorrican/experiment-log-structure
testing
VerifiedTrustedCommunity
Use when an agent needs to produce, update, validate, or normalize a standardized experiment-log entry without running an interview. Defines the canonical structure, pre-registration rules, evidence/interpretation split, calibration tags, and append-only revision model for durable experiment records.
SKILL.mdUpdated May 5, 2026