feat: add spark skill and SKILL.md validation CI

[glebedel]

Summary

• Adds skills/spark/SKILL.md — detects PR/project context, proposes the single highest-leverage non-obvious addition, then offers to build it
• Adds .github/scripts/validate_skills.py — validates all SKILL.md files have required YAML frontmatter (name + description)
• Splits the existing CI job into two: validate-manifest (existing) + validate-skills (new)
• Fixes pre-existing $schema key in marketplace.json that was causing the manifest validator to fail

Installing after merge

/plugin marketplace add stackonehq/agent-plugins-marketplace
/plugin install stackone@stackone-marketplace

Then invoke with /spark or "what's the most impactful thing you could add to this PR?"

Test plan

• python3 .github/scripts/validate_skills.py — all 7 SKILL.md files pass
• npx @anthropic-ai/claude-code plugin validate . — manifest passes
• CI runs both jobs on this PR

🤖 Generated with Claude Code

---

Summary by cubic

Add the spark skill to propose and build the single highest-impact addition for a PR/branch or project. Add CI to validate SKILL.md, split validation into separate jobs, fix manifest validation, and address review feedback to improve default branch detection and validator reliability.

• New Features

  • Add skills/spark/SKILL.md to detect PR/project context and propose one non-obvious, high-value change, then offer to implement it.
  • Add .github/scripts/validate_skills.py and a validate-skills job to enforce name and description in each SKILL.md; split CI from the manifest check.

• Bug Fixes

  • Remove $schema from .claude-plugin/marketplace.json to pass @anthropic-ai/claude-code manifest validation.
  • Spark: detect the actual default branch via origin/HEAD instead of hard-coding main.
  • Validator: resolve the skills/ path from the repo root, not the current working directory.

^{Written for commit 218c8ae. Summary will update on new commits.}

[Copilot]

Pull request overview

This PR adds a new "spark" skill that analyzes the current PR/project context to propose the single highest-leverage addition, along with a CI validation script for SKILL.md frontmatter and a fix for a $schema key in marketplace.json that was breaking manifest validation.

Changes:

• New skills/spark/SKILL.md skill that detects PR/project context and proposes impactful additions
• New .github/scripts/validate_skills.py CI script to validate SKILL.md frontmatter (requires name + description)
• Split CI workflow into validate-manifest and validate-skills jobs; removed invalid $schema key from marketplace.json

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
skills/spark/SKILL.md	New skill: context-aware ideation and implementation workflow
.github/scripts/validate_skills.py	New validation script checking SKILL.md frontmatter for required fields
.github/workflows/validate.yml	Split into two jobs; added validate-skills job
.claude-plugin/marketplace.json	Removed $schema key that was failing manifest validation
README.md	Updated skill count to 7 and added spark to the skills table

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[cubic-dev-ai]

2 issues found across 5 files

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="skills/spark/SKILL.md">

<violation number="1" location="skills/spark/SKILL.md:32">
P2: Determine the repository's actual default branch instead of hard-coding `main`; otherwise PR-mode context can be wrong or empty in many repos.</violation>
</file>

<file name=".github/scripts/validate_skills.py">

<violation number="1" location=".github/scripts/validate_skills.py:34">
P1: Resolve `skills/` relative to the repository instead of the current working directory; otherwise this validator can pass without checking any files.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

1 issue found across 2 files (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="skills/spark/SKILL.md">

<violation number="1" location="skills/spark/SKILL.md:32">
P1: The fallback to `main` is ineffective here because the pipeline still succeeds when `origin/HEAD` is missing, leaving `BASE` empty and breaking the diff/log range.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[cubic-dev-ai]

P1: The fallback to main is ineffective here because the pipeline still succeeds when origin/HEAD is missing, leaving BASE empty and breaking the diff/log range.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At skills/spark/SKILL.md, line 32:

<comment>The fallback to `main` is ineffective here because the pipeline still succeeds when `origin/HEAD` is missing, leaving `BASE` empty and breaking the diff/log range.</comment>

<file context>
@@ -29,9 +29,10 @@ Triggers when: on a non-default branch (`main`/`master`/`develop`/`trunk`) OR wh
-git diff main...HEAD --stat        # What files changed?
-git diff main...HEAD               # Full diff (skim for intent)
-git log main...HEAD --oneline      # Commits in this branch
+BASE=$(git rev-parse --abbrev-ref origin/HEAD 2>/dev/null | sed 's|origin/||' || echo main)
+git diff $BASE...HEAD --stat       # What files changed?
+git diff $BASE...HEAD              # Full diff (skim for intent)
</file context>

Suggested change

	BASE=$(git rev-parse --abbrev-ref origin/HEAD 2>/dev/null | sed 's|origin/||' || echo main)
	BASE=$(git rev-parse --abbrev-ref origin/HEAD 2>/dev/null | sed 's|origin/||')
	BASE=${BASE:-main}