Updated 2w ago
by dmoka
skills
Agent skills by Daniel Moka — battle-tested practices your coding agent can execute. First up: mutation-testing.
20 GitHub stars (20)
+7 in 10 days
| Period | New stars |
|---|---|
| Oct 24 | +3 |
| Oct 25 | +1 |
| Oct 26 | +1 |
| Oct 27 | 0 |
| Oct 28 | 0 |
| Oct 29 | 0 |
| Oct 30 | 0 |
| Oct 31 | 0 |
| Nov 1 | +1 |
| Nov 2 | +1 |
- 14 skills (14 skills found in its SKILL.md files)
- 2 forks (2 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add dmoka/skills
Asks which skills and agents to install. Just one: npx skills add dmoka/skills --skill adversarial-tester — add -g for every project.
Claude Code
git clone https://github.com/dmoka/skillscp -r "skills/skills/adversarial-tester" ~/.claude/skills/
Copies the adversarial-tester skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add dmoka/skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
adversarial-tester
Attack a PR or green suite in a fresh agent to break it. Use when asked to 'review this PR' before a merge, 'attack this PR', 'find what is wrong with this change', or on a green test suite before trusting it, especially AI-written code with AI-written tests. Hands the brief below to a separate agent with its own context, so it does not share the author's blind spots. Checks the change against th…
skills/adversarial-tester/SKILL.md on GitHub (opens in a new tab) -
agent-safety-audit
Audit an AI agent setup: can one email leak your data? Use when someone asks whether their agent is safe, before letting an agent run unattended, or after adding a connector, MCP server, tool, token, inbox, webhook or network rule. Works on a Claude Code repo (settings, hooks, devcontainer), a Claude Code routine, a Hermes install, or an agent in GitHub Actions. Checks the lethal trifecta (privat…
skills/agent-safety-audit/SKILL.md on GitHub (opens in a new tab) -
bug-triage
Fix a reported bug: failing test first, then fix and PR. Use when a bug report arrives (a customer email, an issue, alert text) and the task is to investigate and fix it. Turns one report into a reproduced, fixed, tested pull request, or an honest 'could not reproduce'. Works in any repo: the project's AGENTS.md or CLAUDE.md says where regression tests go and how to run them. The report is untrus…
skills/bug-triage/SKILL.md on GitHub (opens in a new tab) -
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
skills/grill-me/SKILL.md on GitHub (opens in a new tab) -
legacy-testing
Test legacy code: assess first, then propose a plan. Use when a codebase or module has few or no tests and you need to change it safely: adding tests to untested code, getting a safety net before a refactor, taking over code you did not write. Looks at the stack, the dependencies and the code no test touches, proposes which steps this repo needs (make it testable, characterize, approve, property…
skills/legacy-testing/SKILL.md on GitHub (opens in a new tab) -
mutation-testing
Mutation-test a repo: find tests that would miss bugs. Measure test quality with mutation testing and close the gaps it finds. Use when asked whether tests are any good, when coverage is high but confidence is low, after AI wrote or changed tests, or when the user mentions mutation testing, mutation score, surviving mutants, or names a mutation tool (Stryker, Pitest, mutmut, Infection, cargo-muta…
skills/mutation-testing/SKILL.md on GitHub (opens in a new tab) -
pr-tour
Review one PR as a guided tour, in a sane reading order. Turn one pull request into a guided reading tour — the author's intent, which files that intent explains and which it does not, and checkable claims first, then where to look and why (script-computed facts plus line-checked pointers), then the files in the order a reviewer should read them with each test next to its code, and noise (lockfil…
skills/pr-tour/SKILL.md on GitHub (opens in a new tab) -
pr-triage
Triage open PRs: which need attention first, and why. Read every open pull request in a repo, judge how much of a reviewer's attention each one needs (critical, high, medium, low) from what the change actually does, and order the queue most-attention-first — each judgement pointing at the line that drives it, each PR linked to a full reading tour. Renders one self-contained HTML queue plus JSON f…
skills/pr-triage/SKILL.md on GitHub (opens in a new tab) -
write-great-skill
Write or improve an agent skill (SKILL.md + scripts). Use when someone wants to create, write, build or draft a skill; turn a checklist, runbook, procedure, how-to or a prompt they keep repeating into a skill or slash command; make the agent do a task the same way every time; or fix a skill that does not fire, fires at the wrong time, or runs differently each run. Interviews first (the trigger, w…
skills/write-great-skill/SKILL.md on GitHub (opens in a new tab) -
Bad_Skill
Helps with releases.
tests/fixtures/write-great-skill/bad-skill/SKILL.md on GitHub (opens in a new tab) -
folded-skill
Rotate the API keys for the billing service. Use when a key leaks, expires, or the quarterly rotation is due.
tests/fixtures/write-great-skill/folded-skill/SKILL.md on GitHub (opens in a new tab) -
good-skill
Cut a release of the web app. Use when the user says release, ship, cut a version, tag a release or publish. Builds, tests, tags and pushes through scripts/release.sh; dry run first, never pushes without approval.
tests/fixtures/write-great-skill/good-skill/SKILL.md on GitHub (opens in a new tab) -
spec-length
Check the spec length limit. Use when testing. xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx…
tests/fixtures/write-great-skill/spec-length/SKILL.md on GitHub (opens in a new tab) -
too-long
Check the Claude Code cap. Use when testing. yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy…
tests/fixtures/write-great-skill/too-long/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
skillsby anthropics Public repository for Agent Skills