How-to guide covering the full description optimization workflow:
writing effective descriptions, designing trigger eval queries
(should-trigger and should-not-trigger with near-miss examples), testing
trigger rates with a bash eval script, train/validation splits to avoid
overfitting, and the iterative optimization loop.
The guide is client-agnostic by default but includes a working Claude
Code example in the `check_triggered` function using
`--output-format json` and `jq` to detect `Skill` tool calls.
Adds the page to the "For skill creators" navigation group in
`docs.json`.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add comprehensive "Integrating skills" guide for client implementors
Replace the existing `integrate-skills.mdx` page with a thorough,
research-backed guide at `client-implementation/integrating-skills.mdx`.
The guide covers the full Agent Skills integration lifecycle in five
steps: discover, parse, disclose, activate, and manage context. It was
developed from analysis of seven real-world implementations (OpenCode,
Pi, Gemini CLI, Codex, VS Code Copilot Chat, Goose, OpenHands) and
addresses the practical design decisions developers face: progressive
disclosure architecture, cross-client `.agents/skills/`
interoperability, lenient YAML parsing for compatibility, catalog XML
format, behavioral instruction templates (derived from Pi's production
prompts), file-read vs. dedicated tool activation, structured wrapping
for context compaction, and permission allowlisting for bundled
resources.
The guide is architecture-neutral — it covers local filesystem agents,
cloud-hosted/sandboxed agents, and agents with or without file-read
capabilities, framing these as independent design choices rather than
rigid categories.
Also adds a redirect from the old `/integrate-skills` URL and updates
all internal links (`docs.json`, `home.mdx`, `what-are-skills.mdx`).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Address PR review feedback on integrating skills guide
- Clarify that the XML catalog format is just one option — JSON or
bulleted lists work equally well
- Qualify "works with any model" to note it requires a file-reading tool
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Rename "Integrating skills" guide to "Adding skills support"
Addresses reviewer feedback that "Integrating" could be misread as
integrating skills into a workflow rather than into a client. Renames
`integrating-skills.mdx` to `adding-skills-support.mdx` and updates all
references in `docs.json`, `home.mdx`, and `what-are-skills.mdx`.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
A how-to guide for evaluating skill output quality using structured
evals. Covers the full eval workflow: designing test cases, running
with-skill vs. baseline comparisons, writing assertions, LLM-based
grading, aggregating benchmarks, analyzing patterns, human review, and
LLM-driven iterative improvement.
Derived from the workflow implemented by the `skill-creator` Skill, but
written as a standalone guide that readers can follow without using that
tool.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add package.json to docs for local mint dev dependency
Allow installing mint as a local dev dependency instead of requiring
a global install, making the setup more reproducible.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Use npx mint dev to avoid mint version bug
Address PR review feedback: the mint package has a bug that causes it
to use the wrong version when installed as an npm dependency. Switch to
npx mint dev, remove the devDependency and package-lock.json, and
simplify docs accordingly.
* Move `package.json` to repo root and clean up docs
Move the `package.json` from `docs/` to the repo root so `npm run dev`
works from anywhere in the repository. Update `CLAUDE.md` instructions
to match, trim boilerplate from `docs/README.md`, and link to the live
documentation site.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Jonathan Hefner <jonathan@hefner.pro>
* Add "Using scripts" guide for skill creators
New guide at `docs/skill-creation/using-scripts.mdx` covering how to use
commands and scripts in skills:
- One-off commands with `uvx`, `pipx`, `npx`, `bunx`, `go run`,
`deno run` (tabbed by ecosystem, with pinned version examples)
- Referencing bundled scripts from `SKILL.md` using relative paths
- Self-contained scripts with inline dependency declarations (PEP 723,
Deno `npm:` imports, Bun auto-install, Ruby `bundler/inline` — tabbed
with a common HTML-parsing example)
- Designing scripts for agentic use: non-interactive execution, `--help`
documentation, error messages, structured output, and a compressed
checklist of further considerations
Also updates `docs/docs.json` to organize navigation into groups ("For
skill creators" and "For client implementors").
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Address review feedback on "Using scripts" guide
Relative paths note: Clarify that the convention applies to support
files like `references/*.md`, and explain *why* (the agent runs commands
from the skill root).
Structured output: Reframe motivation around composability with both
agents and standard tools (`jq`, `cut`, `awk`) rather than LLM parsing
ambiguity. Shorten prose; let the code example's inline comments carry
the contrast.
Predictable output size: Add `--output` flag as an alternative strategy
for scripts whose output is large and not amenable to pagination. The
`--output` flag acts as a consent mechanism — the agent must explicitly
choose a file destination or pass `-` to opt in to stdout, preventing
accidental context-window flooding.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add OpenHands logo to adoption carousel
OpenHands is an AI software development platform that natively supports
Agent Skills, enabling users to extend agent capabilities with specialized
knowledge and workflows.
Changes:
- Added openhands-logo-light.svg and openhands-logo-dark.svg to /docs/images/logos/openhands/
- Added OpenHands entry to LogoCarousel.jsx
Website: https://www.all-hands.dev/
* Update OpenHands logos to full color versions
---------
Co-authored-by: jamiechicago312 <jamiechicago312@users.noreply.github.com>
Co-authored-by: openhands <openhands@all-hands.dev>
The `logo-scroll` keyframe translated by `-50%`, but flex `gap: 3rem`
means `2N` duplicated items have `2N - 1` gaps — so the track doesn't
split evenly at 50%. The seam between the two copies sits at
`50% + half a gap`. Adjusting to `calc(-50% - 1.5rem)` aligns the
animation endpoint with the start of the second copy, eliminating the
visible jump every 50 seconds.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file was originally copied from the modelcontextprotocol repo.
These styles were specific to MCP documentation pages and are not used
here:
- `#feature-support-matrix-wrapper` table styling
- `#schema-reference` TypeScript documentation styling
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* Create todo.md
* Add files via upload
* Delete docs/images/logos/mistral-vibe/todo.md
* add mistral ai vibe to doc
* added black and white versions
* update whiteblack logos
* add vibe to carousel
* swap light dark
---------
Co-authored-by: jaccolor <jac_color@protonmail.com>
Co-authored-by: Eric Harmeling <eric.harmeling@outlook.com>
* Add Firebender logo
Adds logo for android focused coding agent, Firebender that supports skills
Resolves#71🤖 Generated with [Firebender](https://firebender.com)
Co-Authored-By: Firebender <help@firebender.com>
* fix: replace low-res Firebender SVG logos with high-resolution versions
Updated both light and dark wordmark SVGs with high-resolution exports from Figma.
Old viewBox: ~145x18 / 161x20
New viewBox: 2151x267
This addresses the resolution concerns in PR feedback.
🤖 Generated with [Firebender](https://firebender.com)
Co-Authored-By: Firebender <help@firebender.com>
---------
Co-authored-by: Firebender <help@firebender.com>
Agentman is an agentic AI platform that natively supports Agent Skills,
enabling users to build AI agents with skill-based capabilities.
Co-authored-by: Eric Harmeling <eric.harmeling@outlook.com>