Automated summary
Creates a lightweight specification in a dedicated docs/specs directory and opens the matching GitHub issue with tracking labels.
Strengths
- Auto-generates a three-digit spec number and a kebab-case slug from the description
- Opens the GitHub issue with spec and spec:draft labels and links the spec file as a comment
- Fits into a wider skill pipeline (/clarify, /spec-status, /create-pr) plus a GitHub Action that archives specs
- Prints clear next steps from switching to spec:implementing to referencing the issue in the PR
Limitations
- Tightly coupled to the cloud-native-ref repository layout and its existing docs/specs template
- Requires an authenticated gh CLI and pre-existing GitHub labels
- Does not author the spec content itself: it copies the template and leaves sections to be filled in
Use it for non-trivial changes such as new Crossplane compositions, major infrastructure work, or security changes that need upfront design.
Avoid it for version bumps, documentation-only edits, single-file bug fixes, or minor configuration tweaks.
Security analysis
SafeThe skill only creates a spec directory/file and opens a GitHub issue via scoped gh commands. There are no destructive operations, no curl|sh, no secret/token exfiltration, and no obfuscated payloads. The mkdir -p and find/sed usage is benign filesystem work limited to docs/specs. The main inconsistency is that several bash snippets invoke commands outside the declared Bash(gh:*) scope, but this is a functional limitation rather than a safety concern.
- •Bash block uses non-gh commands (find, sed, mkdir, printf) despite allowed-tools restricting to Bash(gh:*), which may cause execution failures but is not a security risk
Examples
/spec composition "Add Valkey caching"/spec infrastructure "Add GPU node pool"/spec "Introduce network policies for the tenant namespaces"name: spec description: Create a specification for non-trivial changes. Creates GitHub issue + spec file in a dedicated directory. allowed-tools: Read, Write, Bash(gh:*), Glob
Spec Skill
Create lightweight specifications for changes that benefit from upfront design.
Usage
/spec "description"
/spec composition "Add Valkey caching"
/spec infrastructure "Add GPU node pool"
Types (optional): composition | infrastructure | security | platform
If type is omitted, infer from description or ask.
When to Use
- New Crossplane compositions
- Major infrastructure changes (VPC, EKS, IAM)
- Security changes (network policies, RBAC, PKI)
- Multi-component platform features
When NOT to Use
- Version bumps, documentation-only, single-file bug fixes, minor config tweaks
Workflow
1. Generate Identifiers
# Next spec number (3 digits)
MAX_NUM=$(find docs/specs -name "spec.md" -path "*/[0-9]*" 2>/dev/null | \
sed 's|.*/\([0-9]*\)-.*|\1|' | sort -rn | head -1)
SPEC_NUM=$(printf "%03d" $((10#${MAX_NUM:-0} + 1)))
# Slug from description (3-4 meaningful words, kebab-case)
# Filter stop words, take meaningful words, join with hyphens
2. Create GitHub Issue
ISSUE_URL=$(gh issue create \
--title "[SPEC] ${TITLE}" \
--label "spec,spec:draft" \
--body "## Summary
${DESCRIPTION}
## Spec Directory
\`docs/specs/${SPEC_NUM}-${SLUG}/\`
---
_Lightweight spec. See spec file for details._")
ISSUE_NUM=$(echo "$ISSUE_URL" | grep -oP 'issues/\K\d+$')
Labels used:
spec- All specification issuesspec:draft- Initial state (add manually:spec:implementingwhen work starts,spec:donewhen archived)
3. Create Spec Directory and File
SPEC_DIR="docs/specs/${SPEC_NUM}-${SLUG}"
mkdir -p "$SPEC_DIR"
Copy template from docs/specs/templates/spec.md and fill:
SPEC-XXX→SPEC-${SPEC_NUM}#XXX→#${ISSUE_NUM}YYYY-MM-DD→ current date[Title]→ from description
4. Link in Issue
gh issue comment ${ISSUE_NUM} --body "Spec created: [\`${SPEC_DIR}/spec.md\`](${SPEC_DIR}/spec.md)"
5. Output
Spec created:
Issue: https://github.com/Smana/cloud-native-ref/issues/XXX (label: spec:draft)
Spec: docs/specs/XXX-slug/spec.md
Next:
1. Fill in the spec (use /clarify for [NEEDS CLARIFICATION] sections)
2. Run /spec-status to see pipeline overview
3. When starting work: gh issue edit XXX --remove-label "spec:draft" --add-label "spec:implementing"
4. Implement the changes
5. Reference in PR: "Implements #XXX"
6. After merge: spec is auto-archived by GitHub Action
Template Location
docs/specs/templates/spec.md (~80 lines)
Clarifications
Use /clarify to resolve [NEEDS CLARIFICATION: ...] markers with structured options, or discuss conversationally with Claude.
Integration
/speccreates spec + issue withspec:draftlabel (this skill)/spec-statusshows pipeline overview (Draft/Implementing/Done counts)/clarifyresolves [NEEDS CLARIFICATION] markers with structured options/create-prauto-detects specs and references issue/commitfor commits- GitHub Action auto-archives specs on PR merge
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/technical-specification-creator-mm5t89br/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/technical-specification-creator-mm5t89br' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/technical-specification-creator-mm5t89br/download' --output '.skill-downloads/technical-specification-creator-mm5t89br/SKILL.md.part' && mv '.skill-downloads/technical-specification-creator-mm5t89br/SKILL.md.part' '.skill-downloads/technical-specification-creator-mm5t89br/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Write, Bash(gh:*), Glob
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/technical-specification-creator-mm5t89br/SKILL.md' && test -s '.skill-downloads/technical-specification-creator-mm5t89br/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/spec' && cp -R '.skill-downloads/technical-specification-creator-mm5t89br' '.claude/skills/spec'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/technical-specification-creator-mm5t89br'openskills read 'technical-specification-creator-mm5t89br'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/technical-specification-creator-mm5t89br/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.