Skip to content
Agent Orchestration
Skill

/status

Display current FIRE project status and validate integrity of intents, work items, and runs.

BOOST
From plugin
specsmd
22115 skills19 agents22 commands
Install
$ npx -y skills add fabriqaai/specs.md --skill status --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/status

Context preview

The summary Claude sees to decide when to auto-load this skill.

Display current FIRE project status and validate integrity of intents, work items, and runs.

SKILL.md

status.SKILL.md
name: status
description: Display current FIRE project status and validate integrity of intents, work items, and runs.
version: 2.0.0

<objective> Display current FIRE project status and validate integrity across state.yaml and file system. Detect inconsistencies and offer interactive resolution. </objective>

<triggers>

  • User runs `/specsmd-fire status`
  • User asks "what's the status?"
  • User asks to "check" or "validate" the project state

</triggers>

<degrees_of_freedom> **LOW** — Report facts accurately. Never auto-fix without user confirmation. </degrees_of_freedom>

<llm critical="true"> <mandate>NEVER auto-fix inconsistencies — ALWAYS ask user first</mandate> <mandate>ALWAYS scan file system — state.yaml may be incomplete</mandate> <mandate>Report ALL findings before offering fixes</mandate> <mandate>state.yaml is source of truth for status — frontmatter may be stale</mandate> </llm>

<flow> <step n="1" title="Read State"> <action>Read .specs-fire/state.yaml</action> <check if="state.yaml not found"> <output>No FIRE project found. Run `/specsmd-fire` to initialize.</output> <exit/> </check> </step>

<step n="2" title="Display Status"> <output>

FIRE Status

**Project**: {project.name} **Workspace**: {workspace.type} / {workspace.structure} **Autonomy**: {workspace.autonomy_bias} **Version**: {project.fire_version}

Intents

{for each intent}

{intent.title} [{intent.status}]

| Work Item | Status | Complexity | Mode | |-----------|--------|------------|------| {for each work_item} | {title} | {status} | {complexity} | {mode} | {/for}

{/for}

Active Runs

{if runs.active is array and has items} {for each active_run in runs.active}

  • **Run**: {active_run.id} | **Scope**: {active_run.scope}
  • **Current Item**: {active_run.current_item}
  • **Started**: {active_run.started}

{/for} {else if active_run exists (legacy singular)}

  • **Run**: {active_run.id}
  • **Work Item**: {active_run.work_item}
  • **Started**: {active_run.started}

{else} No active run. {/if}

Quick Stats

  • Intents: {total_intents} ({completed_intents} completed)
  • Work Items: {total_work_items} ({completed_work_items} completed)
  • Runs: {total_runs} completed

</output> </step>

<!-- ═══════════════════════════════════════════════════════════════════════════ --> <!-- INTEGRITY VALIDATION (NEW) --> <!-- ═══════════════════════════════════════════════════════════════════════════ -->

<step n="3" title="Scan File System"> <critical> File system may have artifacts not tracked in state.yaml. state.yaml may reference artifacts that no longer exist on disk. </critical>

<substep n="3a" title="Scan Intents"> <action>Glob: .specs-fire/intents/*/brief.md</action> <action>Extract intent IDs from directory names</action> <action>Store as: intents_on_disk[]</action> </substep>

<substep n="3b" title="Scan Work Items"> <action>Glob: .specs-fire/intents/*/work-items/*.md</action> <action>Exclude design docs (*-design.md)</action> <action>Extract work item IDs and parent intents</action> <action>Store as: work_items_on_disk[]</action> </substep>

<substep n="3c" title="Scan Runs"> <action>Glob: .specs-fire/runs/run-*/run.md</action> <action>Extract run IDs from directory names</action> <action>For each run, check which artifacts exist:</action> <substep>plan.md, test-report.md, review-report.md, walkthrough.md</substep> <action>Store as: runs_on_disk[] with artifact_flags</action> </substep> </step>

<step n="4" title="Compare File System vs State"> <substep n="4a" title="Find Orphaned Artifacts (on disk but not in state)"> <action>Compare intents_on_disk with state.intents</action> <action>Compare work_items_on_disk with state work_items</action> <action>Compare runs_on_disk with state.runs.completed + state.runs.active</action>

<check if="intent on disk but not in state"> <add_issue type="orphaned_intent" severity="warning"> Intent '{id}' exists on disk but not tracked in state.yaml </add_issue> </check>

<check if="work item on disk but not in state"> <add_issue type="orphaned_work_item" severity="warning"> Work item '{id}' exists on disk but not tracked in state.yaml </add_issue> </check>

<check if="run folder on disk but not in state"> <add_issue type="orphaned_run" severity="warning"> Run '{id}' exists on disk but not tracked in state.yaml </add_issue> </check> </substep>

<substep n="4b" title="Find Missing Files (in state but not on disk)"> <check if="intent in state but no brief.md on disk"> <add_issue type="missing_intent_file" severity="error"> Intent '{id}' tracked but brief.md not found on disk </add_issue> </check>

<check if="work item in state but no .md file on disk"> <add_issue type="missing_work_item_file" severity="error"> Work item '{id}' tracked but file not found on disk </add_issue> </check>

<check if="completed run in state but no folder on disk"> <add_issue type="missing_run_folder" severity="error"> Run '{id}' marked complete but folder not found on disk </add_issue> </check> </substep> </step>

<step n="5" title="Validate Status Cascade"> <critical> Status must cascade correctly:

  • Run completes work item → work item should be "completed"
  • All work items completed → intent should be "completed"
  • Any work item in_progress → intent should be "in_progress"

</critical>

<sub

Read more
Ships withspecsmd

AI-native development framework with pluggable flows for every use case. Choose the flow that matches your project needs: Ideation for creative brainstorming, Simple for quick specs, FIRE for adaptive execution, or AI-DLC for full methodology with DDD.

Get the whole plugin

Other skills on specsmd.