Claude Code skills: 140 skills in 16 plugins, one repository

One repository with every Claude Code skill maintained by Muhammad Basit Ali: 140 skills in 16 plugins, synced daily from 11 source repositories. It is also a single Claude Code plugin marketplace. New to skills? Read how to install Claude Code skills (three ways).

Install

Add the marketplace in Claude Code, then install the plugins you want:

/plugin marketplace add basitalisandhu/claude-skills
/plugin install aws-security@claude-skills

Or clone once and copy every skill into ~/.claude/skills/:

git clone https://github.com/basitalisandhu/claude-skills
cd claude-skills
python3 install.py --user

Plugins

PluginSkillsVersionDescription
agent-identity-governance90.4.0Nine skills that treat AI agents, service principals, workload identities, API keys and MCP connectors as identities with an inventory, owners, recertification, expiry and an off switch: one inventory across Entra ID, AWS IAM, GitHub and a hand-kept register; a review of Entra agent identities; quarterly recertification sheets per owner; an expiry radar for secrets, certificates, keys and tokens; a register check for MCP servers and connectors; a timeline of one agent's actions from audit exports; a kill switch runbook with a coverage check; a leaked credential response pack with hashed evidence; and a hash chain that makes an agent audit log tamper-evident and shows actions it never recorded. Standard-library scripts over saved exports, no network.
agent-security100.6.0Security skills for LLM agents: threat model a codebase, audit agent configuration, review MCP servers, trace prompt injection to tool calls, check consequential tools for human approval gates, look up incident precedents, run security evals, scan with Semgrep, and review agent session logs for injection, misuse, egress and loops. Includes guard hooks for Bash and an optional incident-database MCP server.
aws-security110.6.1AWS security skills for Claude Code: read-only account audit, SCP guardrail builder and linter, landing zone blast-radius design, IAM least-privilege review, Security Hub and GuardDuty triage, least-privilege access for AI agents with a kill switch, incident response runbooks, spend guardrails, a sandbox OU guardrail pack an audit of what an agent role session did, from CloudTrail, and a mapper from failing Security Hub controls to the SCPs, settings and IaC checks that prevent them. Scripts are standard-library Python and work offline on specs and saved aws CLI output.
cc-setup-tooling140.5.0Fourteen skills that keep a Claude Code setup safe and tidy: review a third-party skill or plugin before installing it (skill-scan-gate, cc-plugin-lock and an offline inventory), lint SKILL.md front matter and fix its quoting, score descriptions against labelled prompts, estimate what a project loads on every turn, merge least-privilege permission rules and test them with claude-perm-sim, review the sandbox settings across scopes and flag what leaves it open, list the tool calls that would stop an unattended run on a permission prompt, show what each subagent can reach, add up the API usage in session transcripts and show which part moved, count shell commands that failed because of zsh, PowerShell or the Windows length limit, check what each compaction summary dropped, scaffold and test hooks with cc-hooks, find skills that collide or shadow each other, and find what breaks on other hosts and operating systems. Standard-library scripts, no network.
code-quality80.4.1Eight skills for keeping a codebase healthy: a review checklist, refactor planning, dead code and complexity reports, naming and error-handling audits, type coverage for Python and TypeScript, and a test gap finder.
compliance-evidence110.7.0Compliance evidence skills for Claude Code: build integrity-checked evidence packs from GitHub, AWS and Microsoft 365 exports, map them to ISO 27001 and SOC 2 control identifiers, draft auditor narratives and security questionnaire answers that cite evidence or say not assessable, map a pack to the Essential Eight maturity levels, digest vendor SOC 2 reports, ISO certificates and bridge letters, map Maester results to control identifiers, plan the evidence to collect per control as a PBC list that shows what is stale, missing or overdue, and check an ISO 27001:2022 Statement of Applicability for missing controls, unjustified decisions, status, evidence and review dates. Standard-library Python scripts read exports already on disk and make no network calls.
data60.4.1Six skills for data and API work: SQL query review, schema migration planning, CSV profiling, JSON Schema inference from samples, regex building with test cases, and OpenAPI 3 contract review.
debugging60.4.1Six skills for finding the cause of a failure: minimise a bug reproduction, cluster log lines, find flaky tests in JUnit XML, explain a stack trace, summarise a py-spy, pprof or cProfile profile, and work a memory leak checklist.
devops90.4.1Nine skills for shipping and operating software: Dockerfile hardening, GitHub Actions workflow authoring and validation, Kubernetes manifest review, Terraform review, a Terraform apply gate against a written policy, crontab diagnosis, .env key diffs, release notes from git history and a semver advisor.
docs60.4.1Six skills for writing documentation that stays accurate: README author, ADR writer, changelog keeper, onboarding doc, API docs extracted from docstrings and JSDoc, and a postmortem writer.
github-manager40.4.0Engineering manager skills that compute from exported GitHub data: a stuck-PR and review-queue digest with next actions, an iteration report with shipped, carried-over and newly opened work plus cycle time and review turnaround, a blameless incident postmortem timeline, and an issue triage digest (unlabelled, unanswered, possible duplicates, stale, popular, suggested labels). Every number and row cites the PR, issue, comment or event it came from; team level only, no per-person scoring.
m365-governance100.6.0Microsoft 365 governance skills for Claude Code: Graph permission preflight for apps and connectors, Entra ID posture review, Conditional Access gap analysis, privileged access review, guest and external sharing review, licence and service plan audit, Intune baseline check, Teams and group sprawl report, a quarterly access review pack, and a Copilot oversharing readiness score with fixes by site owner. Scripts are standard-library Python and evaluate exported Microsoft Graph JSON offline.
mac-maintenance30.2.0Mac cleanup skills: survey what takes space and memory without changing anything, remove only the caches and leftovers that programs recreate, find byte-identical duplicate files and park the obvious copies in the Trash, and find data, login items and launch agents left by uninstalled apps. Every deletion of user data is a decision the user makes from a written list.
repo-engineering130.6.0Repository engineering skills: verify documentation claims against the working tree, run an audit whose every finding cites a resolvable path:line, write AGENTS.md and CLAUDE.md that hold only what code cannot say, check a README's first screen, rank untested functions and entry points, write onboarding guides only from cited facts, plan restructures from the import graph, mine ADRs from git history, run offline hygiene checks with SARIF, check release notes against the commits between two tags, sweep stale branches with delete commands printed for review, check an implementation plan for required sections and unanswered questions, and check an MCP server's server.json and package files against the MCP Registry's publish rules before publishing.
security-basics70.4.1Seven lightweight security skills for everyday development: secrets hygiene scan, npm audit and pip-audit reader, HTTP security header check, JWT inspector, CORS review, auth flow review and a security review of a diff. Agent and MCP security lives in the agent-security-skills marketplace.
ways-of-working130.5.0Thirteen ways-of-working skills that compute from files you already have: a CAB-style change record from a Terraform plan or PR export, one action ledger across meeting notes, a security exception register lint, a quarterly risk register refresh against findings exports, an RFC writer with a lifecycle lint, a one-file-per-decision log, a weekly status note from git and gh exports, a private 1:1 ledger, meeting load and focus blocks from a calendar export, a weighted vendor scorecard with a sensitivity check, a check of a team's working agreement against GitHub settings exports, a shift handover note from incident and alert exports, and one ranked do-next list from saved mail and chat exports across work and personal accounts. Standard-library scripts, no network, no rating of people.

All skills

agent-identity-governance

agent-security

aws-security

cc-setup-tooling

code-quality

compliance-evidence

data

debugging

devops

docs

github-manager

m365-governance

mac-maintenance

repo-engineering

security-basics

ways-of-working

Questions

What is this repository?

It is one repository with every Claude Code skill maintained by Muhammad Basit Ali, and it is also a single Claude Code plugin marketplace. Each skill is a SKILL.md file, and most bundle a small Python script.

How do I install the skills?

In Claude Code, run /plugin marketplace add basitalisandhu/claude-skills and then /plugin install <plugin>@claude-skills. Or clone the repository and run python3 install.py --user to copy every skill into ~/.claude/skills/. The install guide on this site covers both routes and a third one for other agents.

Is anything sent anywhere?

No. install.py, the validator and the site builder make no network calls, and the installer sends no telemetry. Only the daily sync clones the public source repositories from GitHub. What a skill's own script does is described on that skill's page.

Where do I report a bug in a skill?

Open an issue in the skill's source repository. Each skill page and each row of the catalog links to it. Problems with the installer or the site go to the issues of claude-skills on GitHub.

How does the catalog stay in sync with the source repositories?

Skills are edited in their source repositories. A workflow in this repository copies them in every day, regenerates the catalog and the site, and records the source commit of each plugin in SOURCES.json.

Can other agents use these skills?

Agents that read the open Agent Skills format can use them, because every skill is a folder with a SKILL.md that has name and description front matter. The command npx skills add basitalisandhu/claude-skills found every skill on 2026-10-04. This repository tests them with Claude Code only.

What licence are the skills under?

MIT. The vendored plugins are MIT too, by the same author.

Machine-readable: llms.txt, llms-full.txt, feed.xml, catalog.json.