internal/templates/embedded/_guidelines/SKILL.md
# Guidelines: Skill Documents ## Purpose Skills are **disciplined workflows** written as documents (`DocType: skill`) that teach LLMs (and humans) *how to work*, not just what exists. A good skill turns “best practice” into a repeatable, enforceable process. Skills are meant to be discoverable via: - `docmgr skill list` (filter by topics, file/dir, ticket) - `docmgr skill show <query>` (load and apply a skill) ## Required Elements - **Frontmatter contract** - `DocType: skill` - `Title`: U
npx skillsauth add go-go-golems/docmgr internal/templates/embedded/_guidelinesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Skills are disciplined workflows written as documents (DocType: skill) that teach LLMs (and humans) how to work, not just what exists. A good skill turns “best practice” into a repeatable, enforceable process.
Skills are meant to be discoverable via:
docmgr skill list (filter by topics, file/dir, ticket)docmgr skill show <query> (load and apply a skill)DocType: skillTitle: Use the convention Skill: <Name> (recommended)Topics: Choose topics that match how developers will search (e.g. tdd, debugging, docs)WhatFor: 2–5 sentences describing the outcome this workflow ensuresWhenToUse: Clear trigger conditions (“Use when …”)Topics, WhatFor, and WhenToUse contain the words people will actually search for.bash block.pkg/doc/how-to-write-skills.md — Full guidance on writing and enforcing skillspkg/doc/using-skills.md — How to discover and load skills via CLIdocumentation
--- Title: "Skill: [Name]" Ticket: [TICKET-ID] DocType: skill Status: active Topics: [] WhatFor: "Brief description of what this skill is for" WhenToUse: "Brief description of when to use this skill" RelatedFiles: [] Intent: long-term Owners: [] ExternalSources: [] Summary: "" LastUpdated: [TIMESTAMP] --- # Skill: [Name] ## Overview [Brief overview of the skill] ## What This Skill Is For [Detailed description of what this skill is for] ## When To Use This Skill [Detailed description of wh
documentation
# Guidelines: Skill Plans ## Purpose Skills are packaged workflows defined by a `skill.yaml` plan and an exported `SKILL.md` body. The plan tells docmgr what to package (files, help output), while the body teaches LLMs (and humans) *how to work*, not just what exists. Skills are meant to be discoverable via: - `docmgr skill list` (filter by topics, file/dir, ticket) - `docmgr skill show <query>` (load and apply a skill plan) ## Required Elements - **skill.yaml metadata** - `skill.name`: low
documentation
--- Title: {{TITLE}} Ticket: {{TICKET}} Status: draft Topics: {{TOPICS}} DocType: skill Intent: long-term Owners: {{OWNERS}} RelatedFiles: [] ExternalSources: [] Summary: > {{SUMMARY}} LastUpdated: {{DATE}} WhatFor: > <!-- 2–5 sentences: what outcome does this workflow enforce? --> WhenToUse: > <!-- Trigger conditions: "Use when ..." --> --- # {{TITLE}} ## Overview <!-- 2–5 sentences: why this skill matters and what it enforces --> ## When to Use <!-- concrete triggers + examples -->
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.