From copilot-cli-toolkit
Matches file paths against steering file glob patterns to identify applicable guidance. Use for orchestrators to inject context-aware steering based on modified files, optimizing tokens.
npx claudepluginhub rjmurillo/ai-agentsThis skill uses the workspace's default tool permissions.
| Trigger Phrase | Operation |
Matches file paths against glob patterns in steering files to identify applicable guidance. Enables orchestrators to inject context-aware steering based on modified files for token efficiency.
Creates custom steering documents for domain-specific guidance on file types, modules, or workflows like API design standards and test patterns. Supports ALWAYS, CONDITIONAL, and MANUAL inclusion modes. Invoke via /sdd-steering-custom.
Designs, creates, and reviews custom instructions files like .github/copilot-instructions.md (always-on), .instructions.md (file-based with YAML frontmatter/glob patterns), AGENTS.md, and CLAUDE.md for VS Code/GitHub Copilot.
Share bugs, ideas, or general feedback.
| Trigger Phrase | Operation |
|---|---|
match steering for these files | get_applicable_steering.py |
which steering applies to this task | Pattern match against changed files |
inject steering context | Return applicable steering sorted by priority |
This skill helps orchestrator determine which steering files to inject into agent context based on the files being modified.
Use this skill when:
applyTo glob patterns in steering front matterUse manual file reading instead when:
The script in .claude/skills/steering-matcher/scripts/get_applicable_steering.py handles pattern matching.
# Match files against steering patterns
python3 .claude/skills/steering-matcher/scripts/get_applicable_steering.py \
--files "src/claude/analyst.md" ".agents/security/TM-001-auth-flow.md" \
--steering-path ".agents/steering"
# Output: JSON array of objects with name, path, apply_to, priority
This skill integrates with the orchestrator workflow:
# 1. Identify files from task
# 2. Get applicable steering
python3 .claude/skills/steering-matcher/scripts/get_applicable_steering.py \
--files "src/claude/security.md" ".agents/security/SR-001-oauth-review.md"
# 3. Inject into agent context
# Output: JSON with name, path, apply_to, priority sorted by priority descending
See scripts/get_applicable_steering.py for the Python implementation.
Run pytest to verify pattern matching:
pytest .claude/skills/steering-matcher/tests/
| Avoid | Why | Instead |
|---|---|---|
| Hardcoding steering file paths | Bypasses pattern matching, breaks on restructuring | Use get_applicable_steering.py |
| Injecting all steering files | Token bloat, irrelevant context | Match against changed files only |
| Ignoring priority ordering | Lower-priority guidance may contradict higher | Process results in priority order |
After execution:
applyTo patterns for the given filesMatches file paths against steering glob patterns and returns applicable guidance.
python3 .claude/skills/steering-matcher/scripts/get_applicable_steering.py --files <file1> [<file2> ...]