Write or revise a project skill for a Harness Anything Agent — a SKILL.md with frontmatter, real trigger conditions, executable steps, and an explicit deletion budget, discovered from the workspace or harness skill roots. Use when a user wants to add a skill, teach an Agent a procedure, turn a repeated manual sequence into a skill, or audit an existing skill for entropy.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Create a Skill
A skill is not documentation. It is a **procedure an Agent loads before acting**, discovered by
name, and injected as a path plus a `SKILL.md` the Agent will open. If the Agent could follow the
same steps from the task plan, the skill should not exist. If the Agent must be told the same thing
on every dispatch, that belongs in `instructions`, not a skill.
## Where skills come from
Before writing a path, confirm which root the serving node actually scans. The authoritative reader
is `packages/daemon/src/agent-skills.ts` (`discoverAgentSkills` / `resolveAgentSkills`); it scans,
in order:
| Root (relative to the project or home) | Source | Notes |
| --- | --- | --- |
| `~/.claude/skills`, `~/.agents/skills`, `~/.codex/skills` | user | shared across projects |
| `<project>/.claude/skills` | project | |
| `<project>/skills` | project | where this repository keeps its shipped skills |
| `<project>/.agents/skills` | project | symlinks followed |
| `<harness authored root>/skills` | project | the private ledger's skill root |
A directory is a skill when it contains a **regular** `SKILL.md` — a symlinked `SKILL.md` is
…
The line at the top of this page pins the label git:20261026.06196ea, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_q63an7ghpa5nlc6l
GET https://markdownregistry.com/api/v1/resolve?ref=fairladyz625/harness-anything/create-skill
GET https://markdownregistry.com/api/v1/blob/603c7f6d7adc8d1262d3b9904198aecfef1415b8a7e9d24e0dae4ae185937788
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
fairladyz625/harness-anything · skills/codex-unattended-turn/SKILL.md · Codex ends its turn on the first assistant message with no tool call, and an unattended dispatch never sends another…
fairladyz625/harness-anything · skills/create-agent/SKILL.md · Create or update a Harness Anything business Agent — a declared identity with its own instructions, prompts, skills…
fairladyz625/harness-anything · skills/gate-customization/SKILL.md · Define domain completion sources and task gates in vertical and preset packages, including artifact-only command…
fairladyz625/harness-anything · skills/harness-ceo/SKILL.md · Coordinate Harness Anything work from task creation through direct or delegated execution, durable supervision…
fairladyz625/harness-anything · skills/harness-contributing/SKILL.md · Contribute a public change to Harness Anything from a GitHub issue through an isolated worktree, scoped tests…
fairladyz625/harness-anything · skills/harness-issue/SKILL.md · File a public issue in FairladyZ625/harness-anything from a finding — decide whether it is public, collect command and…
fairladyz625/harness-anything · skills/harness-migration/SKILL.md · Diagnose and migrate a Harness Anything ledger from a machine that does not have the current Harness installed. Use…
fairladyz625/harness-anything · skills/harness-reckoning/SKILL.md · Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism…
cherryhq/cherry-studio · .agents/skills/create-skill/SKILL.md · Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a…
tailcallhq/forgecode · crates/forge_repo/src/skills/create-skill/SKILL.md · Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an…
dotnet/skills · .agents/skills/create-skill/SKILL.md · Scaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files…
sethgammon/citadel · skills/create-skill/SKILL.md · Creates new skills from the user's repeating patterns. Interview-driven: discovers the task, analyzes failure modes…
coco-research/coco · adapters/cursor/skills/create-skill/SKILL.md · Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a…
affitor/affiliate-skills · skills/meta/create-skill/SKILL.md · Turn a repeatable AI prompt or workflow into a structured, shareable skill for the affiliate-skills GitHub repository…
aiskillstore/marketplace · skills/0xmsc/create-skill/SKILL.md · Guide for creating new Agent Skills. Use this skill when you need to create a new skill.
tobihagemann/turbo · codex/skills/create-skill/SKILL.md · Create a new skill or update an existing skill that extends Codex's capabilities with specialized knowledge, workflows…
