Updated today
by Chemaclass
agnostic-ai
One source to rule them all: write agents, skills, rules, and hooks once, then sync them to your AI tools.
25 GitHub stars (25)
+7 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | +1 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | +2 |
| Oct 5 | 0 |
| Oct 6 | +1 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | +2 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 23 skills (23 skills found in its SKILL.md files)
- 5 forks (5 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add Chemaclass/agnostic-ai
Asks which skills and agents to install. Just one: npx skills add Chemaclass/agnostic-ai --skill agent-context — add -g for every project.
Claude Code
git clone https://github.com/Chemaclass/agnostic-aicp -r "agnostic-ai/.agnostic-ai/skills/agent-context" ~/.claude/skills/
Copies the agent-context skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Chemaclass/agnostic-ai
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 23 of 112 files.
-
agent-context
Set up or review project agent instructions from an evidence-based context inventory. Use when adding or trimming files under .agnostic-ai/.
.agnostic-ai/skills/agent-context/SKILL.md on GitHub (opens in a new tab) -
cut-release
Cut a new agnostic-ai release end to end. Use when the user wants to ship a new version (tag + GitHub Release).
.agnostic-ai/skills/cut-release/SKILL.md on GitHub (opens in a new tab) -
gh-issue
Take one GitHub issue from branch to merged PR with TDD. Use when asked to work, fix, or implement an issue by number.
.agnostic-ai/skills/gh-issue/SKILL.md on GitHub (opens in a new tab) -
gh-issues
Work the open issues that are unassigned or assigned to you, one at a time through gh-issue. Use when asked to work the backlog.
.agnostic-ai/skills/gh-issues/SKILL.md on GitHub (opens in a new tab) -
memory-curator
Curate this tool's auto memory. Use when the memory index is near its load limit or the stored notes look duplicated or stale.
.agnostic-ai/skills/memory-curator/SKILL.md on GitHub (opens in a new tab) -
playground-rebuild
Rebuild and serve the WASM playground at docs/playground/. Use after editing the playground source or any code reachable from cmd/agnostic-ai-wasm.
.agnostic-ai/skills/playground-rebuild/SKILL.md on GitHub (opens in a new tab) -
pr-sweep
Review every open PR with the code-reviewer agent and an adversarial review, apply the findings, and merge each one once CI is green. Use when asked to ship, sweep, or merge open PRs.
.agnostic-ai/skills/pr-sweep/SKILL.md on GitHub (opens in a new tab) -
regen-schema
Regenerate docs/schemas/config.schema.json from the Config struct. Use after editing internal/config/config.go.
.agnostic-ai/skills/regen-schema/SKILL.md on GitHub (opens in a new tab) -
run-sync-check
Run agnostic-ai sync --check, interpret the diff, and pick the right next step. Use after editing specs or adapters.
.agnostic-ai/skills/run-sync-check/SKILL.md on GitHub (opens in a new tab) -
spec-author
Author a new agnostic-ai spec (agent, skill, rule, or hook). Use when the user wants to add a new prompt, convention, or hook to their project.
.agnostic-ai/skills/spec-author/SKILL.md on GitHub (opens in a new tab) -
target-audit
Audit every agnostic-ai target against current vendor docs, report evidence-backed drift, and surface project capability changes. Use for the recurring adapter truth check or when a tool ships a new surface.
.agnostic-ai/skills/target-audit/SKILL.md on GitHub (opens in a new tab) -
import
Adopt a project's existing AI config (CLAUDE.md, AGENTS.md, .cursor/rules, and friends) into agnostic-ai specs, then fan it out to every other tool. Use when the project already has config for one AI CLI and should feed the rest.
plugins/agnostic-ai/skills/import/SKILL.md on GitHub (opens in a new tab) -
init
Set up agnostic-ai in a project by scaffolding the spec directories, picking target AI CLIs, and producing the first generated config. Use when a project has no .agnostic-ai/ directory yet.
plugins/agnostic-ai/skills/init/SKILL.md on GitHub (opens in a new tab) -
install
Install or upgrade the agnostic-ai CLI on this machine, picking the route that fits the OS and what is already installed. Use when agnostic-ai is missing, when `agnostic-ai --version` fails, or before any other agnostic-ai skill runs.
plugins/agnostic-ai/skills/install/SKILL.md on GitHub (opens in a new tab) -
sync
Regenerate every AI tool's config from the agnostic-ai specs, or check for drift without writing. Use after editing anything under .agnostic-ai/, when a generated file looks stale, or when CI reports a drift failure.
plugins/agnostic-ai/skills/sync/SKILL.md on GitHub (opens in a new tab) -
release
Cut a release and verify it.
tests/integration/fixtures/compare/.agnostic-ai/skills/release/SKILL.md on GitHub (opens in a new tab) -
sample-skill
A sample skill for golden snapshot tests.
tests/integration/fixtures/golden/.agnostic-ai/skills/sample-skill/SKILL.md on GitHub (opens in a new tab) -
dos
dos
internal/adapters/amp/testdata/kitsink/.agents/skills/dos/SKILL.md on GitHub (opens in a new tab) -
tres
tres
internal/adapters/amp/testdata/kitsink/.agents/skills/tres/SKILL.md on GitHub (opens in a new tab) -
uno
uno
internal/adapters/amp/testdata/kitsink/.agents/skills/uno/SKILL.md on GitHub (opens in a new tab) -
s1
skill 1
internal/adapters/antigravity/testdata/kitsink/.agents/skills/s1/SKILL.md on GitHub (opens in a new tab) -
s2
skill 2
internal/adapters/antigravity/testdata/kitsink/.agents/skills/s2/SKILL.md on GitHub (opens in a new tab) -
s3
skill 3
internal/adapters/antigravity/testdata/kitsink/.agents/skills/s3/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.