thierryn/fire-flow/commands
Claude Code and agent skill by thierryn/fire-flow
- community
Checking that the SKILL.md file is still in the repository.
Unified skill management CLI — create, import, test, list, stats, and export skills
Install
npx vskill@latest install thierryn/fire-flow/commandsSKILL.md
/fire-skill - Unified Skill Management CLI
One command for all skill operations. Inspired by npx skills, oh-my-zsh plugins, and the Agent Skills ecosystem — but designed for Dominion Flow's security-first approach.
Subcommands
/fire-skill create
Quick Mode (one-liner)
Interactive Mode (default when no --type given)
<step number="1">
Select Skill Type (Template)
Based on selection, load the corresponding template from: ${CLAUDE_PLUGIN_ROOT}/templates/skill-{type}.md
If type 6 (general), use the standard template from /fire-add-new-skill. </step>
<step number="2">
Collect Metadata
For Quick Mode, auto-fill from arguments. For Interactive Mode, prompt:
Auto-suggestion logic:
api-integrationtype → suggestsapi-patternsorintegrationscategorydebug-patterntype → suggestsquality-safetyor matching domain categoryui-componenttype → suggestsfrontendcategoryarchitecturetype → suggestspatterns-standardsormethodologydevops-recipetype → suggestsinfrastructureorautomation
</step>
<step number="3">
Fill Template Sections
Present each template section one at a time. For each section:
- Show the section header and placeholder description
- Collect user input or auto-extract from session context
- Allow skipping optional sections with
[skip] - Show running preview of completed sections
Smart defaults from session: If --from session is used, scan the current conversation for:
- Error messages and stack traces → populate Symptoms
- Code that was changed → populate Before/After
- Test commands run → populate Verification
- Comments about why → populate "Why This Works"
</step>
<step number="4">
Review, Security Scan, Save
Run the same review panel, security scan, and credential filter gates from /fire-add-new-skill (Steps 5.5, 4.5, 4.6).
Then save and update the index. </step>
Options for create
| Option | Description | |
|---|---|---|
--type {type} | Skip type selection: debug-pattern, api-integration, ui-component, architecture, devops-recipe, general | |
--category {cat} | Pre-fill category | |
--from session | Auto-extract from current conversation | |
--from summary | Auto-extract from most recent RECORD.md | |
--quick | Minimal prompts, fill defaults, skip optional sections | |
--dry-run | Preview the skill document without saving |
/fire-skill import
Import skills from external sources with mandatory security scanning.
<step number="1">
Fetch Source
Download or read the skill content from the specified source.
Supported sources:
| Prefix | Source | Example | |
|---|---|---|---|
github: | GitHub repo path | github:wshobson/commands/code-review | |
skills: | skills.sh registry | skills:vercel-labs/skills/find-skills | |
https:// | Raw URL | https://raw.githubusercontent.com/... | |
./ or path | Local file | ./patterns/retry.md |
For GitHub sources, fetch using:
For skills.sh sources, use the skills.sh API format. </step>
<step number="2">
Security Scan (MANDATORY — Deep Mode)
All imported skills get deep security scanning.
This is non-negotiable. The Snyk study found 13.4% of marketplace skills contained critical security issues. External skills run through ALL 6 layers of the security scanner in --deep mode:
- NFKC normalization
- Invisible Unicode characters
- Prompt injection signatures
- Credential harvesting patterns
- PII collection patterns
- Tool poisoning (exfiltration URLs, cross-tool manipulation)
If BLOCKED: Refuse import. Show findings. No override. If SUSPICIOUS: Show findings. Require explicit user confirmation. If CLEAN: Proceed. </step>
<step number="3">
Format Normalization
Convert imported skill to Dominion Flow format if needed:
- Add missing frontmatter fields (version, contributed, tags, difficulty)
- Normalize section headers to match our template structure
- Convert SKILL.md format (skills.sh) to our
.mdformat - Preserve original source attribution in References section
</step>
<step number="4">
Save with Quarantine Option
For imported skills, offer quarantine:
Quarantine saves to _quarantine/ with a quarantine_reason: "imported" field. Promote later with /fire-skill upgrade {name} --promote. </step>
/fire-skill test
Validate a skill's format, completeness, and internal consistency.
<step number="1">
Validation Checks
Run the following checks on each skill file:
</step>
Validation Levels
| Level | What's Checked | |
|---|---|---|
| Basic (default) | Frontmatter, required sections, format | |
Strict (--strict) | All template sections, code examples, references | |
Security (--security) | Full 6-layer security scan | |
All (--all --strict) | Everything on every skill |
/fire-skill list
Enhanced skill listing with filtering, sorting, and inline stats.
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcommands/fire-skill.md
Popularity
- Repository stars
- 75
- Repository forks
- 19
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 5 Jun 2026, 5 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/thierryn/fire-flow/commands)