runkids/feature-radar/feature-radar-validate

Validate Feature Radar

Run skills/feature-radar-validate/scripts/validate.sh from the project root to check SKILL.md frontmatter and .feature-radar/ SPEC compliance, then fix any issues found.

Why This Matters

The description field in SKILL.md has a 1024-character limit in the Agent Skills spec (agentskills.io/specification, checked 2026-09-29). Agents that enforce the spec may reject a longer description; Claude Code instead truncates the skill listing at 1,536 characters, cutting off trigger text. Similarly, .feature-radar/ files must follow SPEC.md naming and metadata conventions or downstream tools can't parse them. This skill catches these issues before they cause problems.

Workflow

Step 1: Run Validation

bash skills/feature-radar-validate/scripts/validate.sh

Read the full output. Note the exit code:

• Exit 0: all checks passed (may still have warnings)
• Exit 1: errors found — must be fixed

Step 2: Report Results

Present the results clearly:

── Feature Radar: Validate ──
 
Errors:   {n}
Warnings: {n}
 
{List each error/warning with file path and issue}

If everything passes, say so and stop. No further action needed.

Step 3: Auto-Fix (if errors or warnings found)

For each issue, apply the appropriate fix:

After fixing, re-run bash skills/feature-radar-validate/scripts/validate.sh to confirm all errors are resolved.

Step 4: Completion Summary

── Feature Radar: Validate Complete ──
 
Files fixed:   ~ {path} ({what changed})
Errors fixed:  {n}
Warnings fixed: {n}
Remaining:     {n} (need user input)

Proactive Triggering

When you notice yourself editing skills/*/SKILL.md or .feature-radar/**/*.md, run validation afterward without being asked. A quick bash skills/feature-radar-validate/scripts/validate.sh check takes seconds and prevents silent breakage.