Updated 2d ago
by eai-org
agent-toolkit
Minimalistic, project-agnostic skills and rules for AI coding agents
82 GitHub stars (82)
+27 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | +3 |
| Oct 14 | 0 |
| Oct 15 | +1 |
| Oct 16 | 0 |
| Oct 17 | +1 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | +1 |
| Oct 21 | 0 |
| Oct 22 | +1 |
| Oct 23 | +2 |
| Oct 24 | +1 |
| Oct 25 | 0 |
| Oct 26 | +2 |
| Oct 27 | +7 |
| Oct 28 | +1 |
| Oct 29 | 0 |
| Oct 30 | +3 |
| Oct 31 | 0 |
| Nov 1 | +1 |
| Nov 2 | 0 |
| Nov 3 | 0 |
| Nov 4 | 0 |
| Nov 5 | +1 |
| Nov 6 | +1 |
- 30 skills (30 skills found in its SKILL.md files)
- 18 forks (18 forks)
- 2d ago last update (Last updated 2d ago)
Install
Skills CLI
npx skills add eai-org/agent-toolkit
Asks which skills and agents to install. Just one: npx skills add eai-org/agent-toolkit --skill agentify-project — add -g for every project.
Claude Code
git clone https://github.com/eai-org/agent-toolkitcp -r "agent-toolkit/skills/agentify-project" ~/.claude/skills/
Copies the agentify-project skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add eai-org/agent-toolkit
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 — showing the first 30 of 46 files.
-
agentify-project
Make a project agent-ready by converging it toward a canonical agent-neutral structure. Re-runnable, and doubles as an audit.
skills/agentify-project/ on GitHub (opens in a new tab)SKILL.md -
attach-to-ticket
Attach pasted images, files or URLs to a fetched ticket, saved beside its ticket file and referenced from it, or fill an attachment the fetch could not download. Local only — never queries or edits the tracker.
skills/attach-to-ticket/ on GitHub (opens in a new tab)SKILL.md -
check-ticket-implementation
Check how much of a ticket is already implemented and save a per-requirement status report.
skills/check-ticket-implementation/ on GitHub (opens in a new tab)SKILL.md -
compact-docs-writer
Draft, rewrite, or refine a doc for maximum token economy without losing any rule or intent. Use for docs kept in version control and regularly re-read by agents; skip throwaway docs like plans.
skills/compact-docs-writer/ on GitHub (opens in a new tab)SKILL.md -
compact-skill-creator
Author or refine a skill for maximum token economy without losing intent. Use when creating any new skill or editing an existing `SKILL.md`.
skills/compact-skill-creator/ on GitHub (opens in a new tab)SKILL.md -
context-checkup
Audit what auto-loads into an agent session's context window and suggest lean, reversible fixes to cut startup tokens.
skills/context-checkup/ on GitHub (opens in a new tab)SKILL.md -
create-implementation-plan
Turn a refined requirements document into a structured implementation PLAN.md a fresh session can execute. Planning only — decides the "how", not the "what". Invoke manually only.
skills/create-implementation-plan/ on GitHub (opens in a new tab)SKILL.md -
create-manual-test-instructions
Turn a ticket, requirements document or code change (branch, PR, commit range, diff) into a concise QA manual-test file a non-author can follow. Invoke manually only.
skills/create-manual-test-instructions/ on GitHub (opens in a new tab)SKILL.md -
execute-plan-tasks
Execute one task of a plan's task breakdown, then stop for review.
skills/execute-plan-tasks/ on GitHub (opens in a new tab)SKILL.md -
explain-in-simple-language
Explain code, a decision, a recap, or a question to the user, or write a document a human reads, so a fluent but often non-native reader understands it on the first read. Use when explaining or asking the user anything, when writing a review, report, or brief a human reads (never text sent under the user's name), or when the user asks for simpler words or says they did not understand.
skills/explain-in-simple-language/ on GitHub (opens in a new tab)SKILL.md -
extract-pr-review-rules
Extract the conventions a repo's reviewers enforce in inline PR review comments into a per-reviewer rules doc; re-runs resume from a checkpoint.
skills/extract-pr-review-rules/ on GitHub (opens in a new tab)SKILL.md -
fetch-pr-review
Fetch all reviewer comments left on your own pull request (GitHub, Azure DevOps, …) and save them as a self-contained markdown PR-REVIEW file in the task's planning directory. Fetch only — no fixing or replying.
skills/fetch-pr-review/ on GitHub (opens in a new tab)SKILL.md -
fetch-ticket
Fetch one or more tickets/issues from their tracker (Azure DevOps, Jira, GitHub, …) and save each as a self-contained markdown ticket file. Fetch only — no analysis or planning.
skills/fetch-ticket/ on GitHub (opens in a new tab)SKILL.md -
fresh-eyes-review
Fresh-eyes review of a changeset by a fresh-context agent — catches what the authoring context reads past.
skills/fresh-eyes-review/ on GitHub (opens in a new tab)SKILL.md -
grill-me
Interview the user relentlessly about a plan, design, or idea until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, validate an idea, get grilled on their design, or says "grill me".
skills/grill-me/ on GitHub (opens in a new tab)SKILL.md -
handover
Use when handing finished work over to code review — writing a PR description or packaging a change for review by a human, an agent, or both.
skills/handover/ on GitHub (opens in a new tab)SKILL.md -
harden-artifact
Harden a REQUIREMENTS or PLAN document against its ticket and the code before the next phase picks it up.
skills/harden-artifact/ on GitHub (opens in a new tab)SKILL.md -
maintainer-review
Review someone else's pull request as the maintainer deciding whether it merges.
skills/maintainer-review/ on GitHub (opens in a new tab)SKILL.md -
memory-doctor
Drain the agent's project memory block by block, relocating each entry into a home the user controls or archiving it.
skills/memory-doctor/ on GitHub (opens in a new tab)SKILL.md -
prepare-prompt
Prepare a prompt that hands this session's work to a fresh agent session — to continue it, check it, or pick up what was left open. Use when asked for a prompt or brief for the next session.
skills/prepare-prompt/ on GitHub (opens in a new tab)SKILL.md -
refine-pr-review
Triage a fetched PR review with the user, comment by comment, drafting each reply and producing a REQUIREMENTS file for the accepted code changes. Takes the PR-REVIEW file produced by fetch-pr-review, or a PR URL. Invoke manually only.
skills/refine-pr-review/ on GitHub (opens in a new tab)SKILL.md -
refine-ticket
Refine a development ticket — or brainstorm a raw idea — into a validated, self-contained REQUIREMENTS document — the "what", verified against the codebase. Invoke manually only.
skills/refine-ticket/ on GitHub (opens in a new tab)SKILL.md -
review-code-assistant
Assist a human reviewing a pull request or branch locally, read-only and never posting.
skills/review-code-assistant/ on GitHub (opens in a new tab)SKILL.md -
review-ticket
Triage a ticket or ticket set before work starts, saving a review with the questions worth raising.
skills/review-ticket/ on GitHub (opens in a new tab)SKILL.md -
run-nx-checks
Run nx format, lint, typecheck, test, and build on affected or specified projects, then fix unambiguous failures
skills/run-nx-checks/ on GitHub (opens in a new tab)SKILL.md -
self-improve
Capture durable user feedback into the governing skill, doc or check, or propose creating a new skill when no suitable one exists, so future sessions don't repeat the mistake. Use when the user rejects, reverts, or overrides the agent's output or approach on something a skill, doc or check covers or should cover, and when manually invoked to improve or create guidance.
skills/self-improve/ on GitHub (opens in a new tab)SKILL.md -
self-review
Self-review your changeset until merge-ready, with a fresh-context reviewer and a compact report for the PR.
skills/self-review/ on GitHub (opens in a new tab)SKILL.md -
split-plan-tasks
Split a plan into PR-sized groups of small, reviewable tasks appended to the plan file.
skills/split-plan-tasks/ on GitHub (opens in a new tab)SKILL.md -
use-conversational-language
Voice rules for text published under a person's name and read as if a person typed it, such as chat messages to colleagues, PR comments and descriptions, commit messages, review replies, and code comments. Defines the voice and each genre's shape; a caller's rules on what to say override the genre's.
skills/use-conversational-language/ on GitHub (opens in a new tab)SKILL.md -
verify-understanding
Verify the engineer is ready to implement a feature through a teach-back conversation over its ticket review.
skills/verify-understanding/ on GitHub (opens in a new tab)SKILL.md
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
-
archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
-
awesome-agent-skillsby VoltAgent A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Curso…
-
video-shotcraftby Vincentwei1021 AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat…
-
elephant-goldfish-modelby google Open-source skills for designing and reviewing software with AI agents
-
social-media-research-skillsby ScrapeCreators AI agent skills for social media research. Outlier posts, comment mining, competitor teardowns, ad libraries & trends across TikTok, Instag…
-
appllama-skillsby Appllama A builder, not just a researcher. Agent skills that turn top-grossing app patterns into native-quality mobile screens.