AGENT SKILL

steering-matcher

Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.

License 许可
MIT
所属仓库
loriensleafs/brain
最近更新
2026-03-11
Stars
★ 0
Forks
0

01 前言 Front Matter

name
steering-matcher
model
claude-haiku-4-5
agents
[ "orchestrator" ]
license
MIT
metadata
{ "version": "1.0.0", "timelessness": "high" }
description
Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.

02 资源文件 1

03 SKILL.md 正文

Steering File Matcher Skill

Triggers

Trigger Phrase Operation
match steering for these files get_applicable_steering.ts
which steering applies to this task Pattern match against changed files
inject steering context Return applicable steering sorted by priority

Purpose

This skill helps orchestrator determine which steering files to inject into agent context based on the files being modified.

  • Match file paths against glob patterns in steering file front matter
  • Return applicable steering files sorted by priority
  • Enable token-efficient context injection (30%+ savings)

When to Use

Use this skill when:

  • Orchestrator needs to inject context-aware steering based on files being modified
  • You want to scope agent guidance to only relevant files (token optimization)
  • Matching file paths against applyTo glob patterns in steering front matter

Use manual file reading instead when:

  • You already know which steering file applies
  • The task affects a single known steering domain

Quick Usage

Using get_applicable_steering.ts Script

The script in scripts/get_applicable_steering.ts handles pattern matching.

# Match files against steering patterns
bun run ${CLAUDE_SKILL_DIR}/scripts/get_applicable_steering.ts \
    --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

Process

This skill integrates with the orchestrator workflow:

  1. Task Analysis: Orchestrator identifies files affected by task
  2. Pattern Matching: Use this skill to find applicable steering
  3. Context Injection: Include matched steering in agent prompt
  4. Token Optimization: Only inject relevant guidance

Standard Orchestrator Workflow

# 1. Identify files from task
# 2. Get applicable steering
bun run ${CLAUDE_SKILL_DIR}/scripts/get_applicable_steering.ts \
    --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

Implementation

See scripts/get_applicable_steering.ts for the TypeScript implementation.

Anti-Patterns

Avoid Why Instead
Hardcoding steering file paths Bypasses pattern matching, breaks on restructuring Use get_applicable_steering.ts
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

Verification

After execution:

  • [ ] Returned steering files match the applyTo patterns for the given files
  • [ ] Results are sorted by priority (highest first)
  • [ ] No duplicate steering entries in output

Scripts

get_applicable_steering.ts

Matches file paths against steering glob patterns and returns applicable guidance.

bun run ${CLAUDE_SKILL_DIR}/scripts/get_applicable_steering.ts --files <file1> [<file2> ...]

Related

04 同仓库更多 Skills

loriensleafs
loriensleafs/brain

validation-authority

Treat upstream validators as authoritative. Align local config to them. Use when validation fails unexpectedly, before modifying validator behavior, or when tempted to change upstream tool code.

★ 0
loriensleafs
loriensleafs/brain

using-brain-memory

Guidance for using Brain semantic memory effectively. Applies Zettelkasten atomic note principles with observations and relations. Use when deciding whether to query or create notes, structuring note content, or understanding the semantic knowledge graph.

★ 0
loriensleafs
loriensleafs/brain

threat-modeling

Structured security analysis using OWASP Four-Question Framework and STRIDE methodology. Generates threat matrices with risk ratings, mitigations, and prioritization. Use for attack surface analysis, security architecture review, or when asking what can go wrong.

★ 0
loriensleafs
loriensleafs/brain

taste-lints

Custom lints with agent-readable remediation instructions. Enforces taste invariants (file size, naming conventions, structured logging, complexity) and surfaces errors that agents can act on directly. Use when writing or reviewing code to catch style violations early.

Skill与智能体开发
★ 0
loriensleafs
loriensleafs/brain

style-enforcement

Validate code against style rules from .editorconfig, StyleCop.json, and Directory.Build.props. Detects line ending violations, naming convention issues, indentation problems, and charset mismatches across C#, Python, TypeScript, and JavaScript. Produces JSON reports for pre-commit hooks and CI pipelines.

★ 0
loriensleafs
loriensleafs/brain

slashcommandcreator

Autonomous meta-skill for creating high-quality custom slash commands using 5-phase workflow with multi-agent validation and quality gates. Use when user requests new slash command, reusable prompt automation, or wants to convert repetitive workflows into documented commands.

Skill与智能体开发
★ 0