skill-builder-pack plugin
Find, create, lint, audit and security-scan Agent Skills, plus agent memory and session handoffs
How to install the skill-builder-pack plugin
Run both commands inside Claude Code. The first adds the marketplace once; the second installs the plugin.
/plugin marketplace add milad-ahmd/agent-skills
/plugin install skill-builder-pack@milad-agent-skillsWhat's inside skill-builder-pack
5 parts read from the plugin's own files.
Skills 5
Claude loads it when the task matches- agent-memory-keeper
Carries a coding agent's context across sessions with two files. MEMORY.md holds durable project lessons (verified commands, conventions, decisions, gotchas, user preferences); it is loaded at the start of work and updated whenever the user corrects the agent. HANDOFF.md holds the state of the current task (goal, status checklist, exact next step, failed attempts, open questions, branch and uncommitted files); it is written when a session ends mid-task and checked against git when the next session resumes. Use when the user says "remember this", "don't forget", "forget that note" or "what do you remember", says "write a handoff", "I'm running out of context", "continue this in a new session", "pick up where we left off", or "hand this to another agent or a teammate", and at the start of any session in a repo with MEMORY.md or HANDOFF.md.
- prompt-injection-scanner
Scans an AI agent's instruction and tool-config files (CLAUDE.md, AGENTS.md, skills, slash commands, subagents, Cursor and Cline rules, hooks, MCP server configs) for prompt injection, hidden Unicode or HTML-comment instructions, exfiltration commands, and risky permissions or unpinned MCP packages, then recommends what to remove or quarantine. Use when the user installs third-party skills or plugins, clones an unfamiliar repo, adds an MCP server, or asks whether their agent setup is safe to trust.
- skill-creator-pro
Designs and writes new Agent Skills (SKILL.md) from a described workflow. It produces a precise trigger description, a step-by-step workflow, rules, an output format, optional helper scripts, and a README, then checks the new skill before handing it over. Use when the user wants to create, write, improve, or package an agent skill, SKILL.md, Claude skill, or reusable agent workflow.
- skill-finder
Answers "is there a skill for X?" and "find me a skill" requests by recommending an existing agent skill for the job, so nobody rebuilds what already exists. Notes which ones are already present so it never suggests a duplicate, ranks this collection's bundled catalog with a BM25 search script, and falls back to the skills.sh directory and leaderboard with `npx skills find`. Presents the best 1 to 3 matches with the reason it fits, its publisher and popularity, and the exact command to add it, then adds it only after the user says yes. Use it first whenever the user asks "is there a skill for this", even when a matching skill seems to be on hand already, or wants to find, look up, discover, browse or get a recommendation for a skill or plugin that does some job, asks which skill to use for a task, or asks which skills they already have.
- skills-doctor
Audits installed Agent Skills (SKILL.md) for problems that stop them from working, such as invalid or missing frontmatter, name and folder mismatches, vague or overlapping descriptions that never trigger or trigger wrongly, oversized files, missing referenced scripts, and possible embedded secrets, using a linter script, then proposes fixes. Use when the user asks to lint, check, debug, clean up, or audit their skills or a skills folder such as ~/.claude/skills, or asks why a skill isn't triggering.
Using skill-builder-pack in Claude Code
Skills need no command. Claude reads them when your request matches what they describe.
Update, turn off or remove
- Update the plugin (shell)
- claude plugin update skill-builder-pack@milad-agent-skills
- Refresh the marketplace
- /plugin marketplace update milad-agent-skills
- Turn it off for now
- /plugin disable skill-builder-pack@milad-agent-skills
- Remove it
- /plugin uninstall skill-builder-pack@milad-agent-skills
Skills in skill-builder-pack
- agent-memory-keepermilad-ahmd/agent-skills
Carries a coding agent's context across sessions with two files. MEMORY.md holds durable project lessons (verified commands, conventions, decisions, gotchas, user preferences); it is loaded at the start of work and updated whenever the user corrects the agent. HANDOFF.md holds the state of the current task (goal, status checklist, exact next step, failed attempts, open questions, branch and uncommitted files); it is written when a session ends mid-task and checked against git when the next session resumes. Use when the user says "remember this", "don't forget", "forget that note" or "what do you remember", says "write a handoff", "I'm running out of context", "continue this in a new session", "pick up where we left off", or "hand this to another agent or a teammate", and at the start of any session in a repo with MEMORY.md or HANDOFF.md.
4 files5stars - prompt-injection-scannermilad-ahmd/agent-skills
Scans an AI agent's instruction and tool-config files (CLAUDE.md, AGENTS.md, skills, slash commands, subagents, Cursor and Cline rules, hooks, MCP server configs) for prompt injection, hidden Unicode or HTML-comment instructions, exfiltration commands, and risky permissions or unpinned MCP packages, then recommends what to remove or quarantine. Use when the user installs third-party skills or plugins, clones an unfamiliar repo, adds an MCP server, or asks whether their agent setup is safe to trust.
3 files5stars - skill-creator-promilad-ahmd/agent-skills
Designs and writes new Agent Skills (SKILL.md) from a described workflow. It produces a precise trigger description, a step-by-step workflow, rules, an output format, optional helper scripts, and a README, then checks the new skill before handing it over. Use when the user wants to create, write, improve, or package an agent skill, SKILL.md, Claude skill, or reusable agent workflow.
3 files5stars - skill-findermilad-ahmd/agent-skills
Answers "is there a skill for X?" and "find me a skill" requests by recommending an existing agent skill for the job, so nobody rebuilds what already exists. Notes which ones are already present so it never suggests a duplicate, ranks this collection's bundled catalog with a BM25 search script, and falls back to the skills.sh directory and leaderboard with `npx skills find`. Presents the best 1 to 3 matches with the reason it fits, its publisher and popularity, and the exact command to add it, then adds it only after the user says yes. Use it first whenever the user asks "is there a skill for this", even when a matching skill seems to be on hand already, or wants to find, look up, discover, browse or get a recommendation for a skill or plugin that does some job, asks which skill to use for a task, or asks which skills they already have.
4 files5stars - skills-doctormilad-ahmd/agent-skills
Audits installed Agent Skills (SKILL.md) for problems that stop them from working, such as invalid or missing frontmatter, name and folder mismatches, vague or overlapping descriptions that never trigger or trigger wrongly, oversized files, missing referenced scripts, and possible embedded secrets, using a linter script, then proposes fixes. Use when the user asks to lint, check, debug, clean up, or audit their skills or a skills folder such as ~/.claude/skills, or asks why a skill isn't triggering.
4 files5stars
skill-builder-pack plugin questions
How do I install the skill-builder-pack plugin?
In Claude Code run /plugin marketplace add milad-ahmd/agent-skills, then /plugin install skill-builder-pack@milad-agent-skills.
What does the skill-builder-pack plugin include?
skill-builder-pack bundles 5 skills.
How do I update or remove the skill-builder-pack plugin?
Update it with claude plugin update skill-builder-pack@milad-agent-skills in your shell, or from the Installed tab of /plugin. Remove it with /plugin uninstall skill-builder-pack@milad-agent-skills.