thierryn/fire-flow/commands

Claude Code and agent skill by thierryn/fire-flow

Trust tier 3
  • community
Source check pending

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/commands

SKILL.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 [name] Create a new skill (quick or wizard mode)
/fire-skill import [source] Import skill from URL, file, or marketplace
/fire-skill test [name] Validate and dry-run a skill
/fire-skill list [filter] List skills with filtering and stats
/fire-skill stats [name] Usage analytics for one or all skills
/fire-skill export [name] Export skill for sharing
/fire-skill browse Interactive skill browser with preview
/fire-skill upgrade [name] Upgrade skill to latest template format

/fire-skill create

Quick Mode (one-liner)
bash
# Minimal — just a name and type, fills defaults
/fire-skill create "retry-backoff" --type api-integration --category api-patterns
# From current session — auto-extracts the pattern you just solved
/fire-skill create --from session
# From a RECORD.md summary
/fire-skill create --from summary
Interactive Mode (default when no --type given)
bash
/fire-skill create "retry-backoff"

<step number="1">

Select Skill Type (Template)
=============================================================
SKILL CREATION — SELECT TYPE
=============================================================
What kind of skill is this?
1. debug-pattern Diagnose & fix a specific bug
Has: symptoms, detection, elimination checklist,
before/after, verification steps
2. api-integration Connect to an external API or service
Has: env vars, client setup, retry/resilience,
webhook handling, test mocks
3. ui-component Reusable UI pattern or component
Has: wireframe, props API, responsive behavior,
accessibility checklist, state management
4. architecture Structural/design pattern
Has: Mermaid diagram, principles, trade-offs,
migration path, decision criteria
5. devops-recipe Infrastructure, CI/CD, deployment
Has: prerequisites, step-by-step, verification,
rollback plan, monitoring metrics
6. general Standard problem/solution skill
Has: problem, solution, code example, when to
use/not use (current default format)
Select type (1-6): > _
=============================================================

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:

-------------------------------------------------------------
METADATA
-------------------------------------------------------------
Category: [auto-suggested from type, or select from list]
Scope: [General | Project] (default: General)
Tags: [auto-suggested from type + category, editable]
Difficulty: [easy | medium | hard]
-------------------------------------------------------------

Auto-suggestion logic:

  • api-integration type → suggests api-patterns or integrations category
  • debug-pattern type → suggests quality-safety or matching domain category
  • ui-component type → suggests frontend category
  • architecture type → suggests patterns-standards or methodology
  • devops-recipe type → suggests infrastructure or automation

</step>

<step number="3">

Fill Template Sections

Present each template section one at a time. For each section:

  1. Show the section header and placeholder description
  2. Collect user input or auto-extract from session context
  3. Allow skipping optional sections with [skip]
  4. 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
OptionDescription
--type {type}Skip type selection: debug-pattern, api-integration, ui-component, architecture, devops-recipe, general
--category {cat}Pre-fill category
--from sessionAuto-extract from current conversation
--from summaryAuto-extract from most recent RECORD.md
--quickMinimal prompts, fill defaults, skip optional sections
--dry-runPreview the skill document without saving

/fire-skill import

Import skills from external sources with mandatory security scanning.

bash
# Import from a GitHub repo (skills.sh format)
/fire-skill import github:owner/repo/skill-name
# Import from a URL (raw markdown)
/fire-skill import https://example.com/skills/retry-pattern.md
# Import from a local file
/fire-skill import ./my-pattern.md
# Import from skills.sh marketplace
/fire-skill import skills:vercel-labs/skills/find-skills
# Import and assign to category
/fire-skill import github:owner/repo/skill --category api-patterns

<step number="1">

Fetch Source

Download or read the skill content from the specified source.

Supported sources:

PrefixSourceExample
github:GitHub repo pathgithub:wshobson/commands/code-review
skills:skills.sh registryskills:vercel-labs/skills/find-skills
https://Raw URLhttps://raw.githubusercontent.com/...
./ or pathLocal file./patterns/retry.md

For GitHub sources, fetch using:

bash
curl -sL "https://raw.githubusercontent.com/{owner}/{repo}/main/{path}/SKILL.md"

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:

  1. NFKC normalization
  2. Invisible Unicode characters
  3. Prompt injection signatures
  4. Credential harvesting patterns
  5. PII collection patterns
  6. Tool poisoning (exfiltration URLs, cross-tool manipulation)
-------------------------------------------------------------
IMPORT SECURITY SCAN (Deep Mode)
-------------------------------------------------------------
Source: {source_url}
Size: {file_size} bytes
Scanning...
Layer 1: Invisible characters ... {CLEAN | FOUND}
Layer 2: Prompt injection ... {CLEAN | FOUND}
Layer 3: Credential harvesting ... {CLEAN | FOUND}
Layer 4: PII collection ... {CLEAN | FOUND}
Layer 5: Tool poisoning ... {CLEAN | FOUND}
Layer 6: Exfiltration URLs ... {CLEAN | FOUND}
Verdict: {CLEAN | SUSPICIOUS | BLOCKED}
-------------------------------------------------------------

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 .md format
  • Preserve original source attribution in References section
-------------------------------------------------------------
FORMAT NORMALIZATION
-------------------------------------------------------------
Original format: {SKILL.md | .cursorrules | plain markdown}
Converted to: Dominion Flow skill format
Added fields:
+ version: 1.0.0
+ contributed: {today}
+ contributor: imported:{source}
+ difficulty: medium (default — edit if needed)
+ tags: [extracted, from, content]
-------------------------------------------------------------

</step>

<step number="4">

Save with Quarantine Option

For imported skills, offer quarantine:

-------------------------------------------------------------
SAVE OPTIONS
-------------------------------------------------------------
1. Save directly → skills-library/{category}/{name}.md
2. Save to quarantine → skills-library/_quarantine/{name}.md
(review before promoting to library)
3. Preview only → Display without saving
4. Cancel → Discard
Select (1-4): > _
-------------------------------------------------------------

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.

bash
# Test a specific skill
/fire-skill test database-solutions/connection-pool-timeout
# Test all skills in a category
/fire-skill test --category api-patterns
# Test all skills
/fire-skill test --all
# Test with strict mode (all optional sections required)
/fire-skill test --strict database-solutions/connection-pool-timeout

<step number="1">

Validation Checks

Run the following checks on each skill file:

=============================================================
SKILL VALIDATION: {skill-name}
=============================================================
Format Checks:
[PASS] YAML frontmatter present
[PASS] Required fields: name, category, version
[PASS] Tags field is an array
[WARN] Missing field: difficulty (default: medium)
[PASS] Version follows semver
Content Checks:
[PASS] # Title heading present
[PASS] ## Problem section present
[PASS] ## Solution Pattern section present
[WARN] ## Code Example section empty
[PASS] ## When to Use section present
[FAIL] ## When NOT to Use section missing
Template Conformance:
[INFO] Skill type: debug-pattern
[WARN] Missing template sections: Detection, Elimination Checklist
[PASS] All required template sections present
Cross-Reference Checks:
[PASS] Category directory exists
[WARN] Related skill "retry-backoff" not found in library
[PASS] No duplicate skill name detected
Security Quick-Scan:
[PASS] No credential patterns detected
[PASS] No suspicious URLs detected
[PASS] No prompt injection signatures
-------------------------------------------------------------
RESULT: 5 PASS | 3 WARN | 1 FAIL
-------------------------------------------------------------
Recommendations:
1. Add "## When NOT to Use" section (required)
2. Consider adding code examples
3. Verify related skill reference "retry-backoff"
=============================================================

</step>

Validation Levels
LevelWhat'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.

bash
# List all skills (compact view)
/fire-skill list
# Filter by category
/fire-skill list --category frontend
# Filter by type
/fire-skill list --type debug-pattern

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

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/thierryn/fire-flow/commands/badge)](https://verified-skill.com/skills/thierryn/fire-flow/commands)

Something wrong with this skill or its page? Tell us.