agentleFS
studiogadgetstudiogadget/skills/kiro-steering/SKILL.md

kiro-steering

Skill3 starsChanged 6 months agoApache-2.0View on GitHub

Manage docs/steering/ as persistent project knowledge

3 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 7 are common, 2 are distinctive, and 1 is very specific to this project.

  • 7

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Sync Mode: All core files exist

    line 31
  2. Distinctive:

    If multi-agent is enabled, spawn sub-agents for each area above.

    line 47
  3. Common:

    After all parallel research completes, synthesize patterns for steering files.

    line 49
  4. Common:

    Custom files: Check relevance

    line 70
  5. Common:

    Update Philosophy: Add, don't replace. Preserve user sections.

    line 74
  6. Common:

    Document patterns and principles, not exhaustive lists.

    line 84
  7. Distinctive:

    Read: Read steering, docs, configs

    line 94
  8. Common:

    Security: Never include keys, passwords, secrets (see principles)

    line 143
  9. Common:

    Preservation: Add rather than replace when in doubt

    line 145
  10. Very specific:

    Avoid documenting agent-specific tooling directories (e.g.

    line 153

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Kiro Steering Management

<background_information> Role: Maintain docs/steering/ as persistent project memory.

Mission:

  • Bootstrap: Generate core steering from codebase (first-time)
  • Sync: Keep steering and codebase aligned (maintenance)
  • Preserve: User customizations are sacred, updates are additive

Success Criteria:

  • Steering captures patterns and principles, not exhaustive lists
  • Code drift detected and reported
  • All docs/steering/*.md treated equally (core + custom) </background_information>
<instructions> ## Scenario Detection

Check docs/steering/ status:

Bootstrap Mode: Empty OR missing core files (product.md, tech.md, structure.md) Sync Mode: All core files exist


Bootstrap Flow

  1. Load templates from docs/settings/templates/steering/
  2. Analyze codebase (JIT):

Parallel Research

The following research areas are independent and can be executed in parallel:

  1. Product analysis: README, package.json, documentation files for purpose, value, core capabilities
  2. Tech analysis: Config files, dependencies, frameworks for technology patterns and decisions
  3. Structure analysis: Directory tree, naming conventions, import patterns for organization

If multi-agent is enabled, spawn sub-agents for each area above. Otherwise execute sequentially.

After all parallel research completes, synthesize patterns for steering files.

  1. Extract patterns (not lists):
    • Product: Purpose, value, core capabilities
    • Tech: Frameworks, decisions, conventions
    • Structure: Organization, naming, imports
  2. Generate steering files (follow templates)
  3. Load principles from rules/steering-principles.md from this skill's directory
  4. Present summary for review

Focus: Patterns that guide decisions, not catalogs of files/dependencies.


Sync Flow

  1. Load all existing steering (docs/steering/*.md)
  2. Analyze codebase for changes (JIT)
  3. Detect drift:
    • Steering → Code: Missing elements → Warning
    • Code → Steering: New patterns → Update candidate
    • Custom files: Check relevance
  4. Propose updates (additive, preserve user content)
  5. Report: Updates, warnings, recommendations

Update Philosophy: Add, don't replace. Preserve user sections.


Granularity Principle

From rules/steering-principles.md (in this skill's directory):

"If new code follows existing patterns, steering shouldn't need updating."

Document patterns and principles, not exhaustive lists.

Bad: List every file in directory tree Good: Describe organization pattern with examples

</instructions>

Tool guidance

  • Glob: Find source/config files
  • Read: Read steering, docs, configs
  • Grep: Search patterns
  • Bash with ls: Analyze structure

JIT Strategy: Fetch when needed, not upfront.

Output description

Chat summary only (files updated directly).

Bootstrap:

✅ Steering Created

## Generated:
- product.md: [Brief description]
- tech.md: [Key stack]
- structure.md: [Organization]

Review and approve as Source of Truth.

Sync:

✅ Steering Updated

## Changes:
- tech.md: React 18 → 19
- structure.md: Added API pattern

## Code Drift:
- Components not following import conventions

## Recommendations:
- Consider api-standards.md

Examples

Bootstrap

Input: Empty steering, React TypeScript project Output: 3 files with patterns - "Feature-first", "TypeScript strict", "React 19"

Sync

Input: Existing steering, new /api directory Output: Updated structure.md, flagged non-compliant files, suggested api-standards.md

Safety & Fallback

  • Security: Never include keys, passwords, secrets (see principles)
  • Uncertainty: Report both states, ask user
  • Preservation: Add rather than replace when in doubt

Notes

  • All docs/steering/*.md loaded as project memory
  • Templates and principles are external for customization
  • Focus on patterns, not catalogs
  • "Golden Rule": New code following patterns shouldn't require steering updates
  • Avoid documenting agent-specific tooling directories (e.g. .cursor/, .gemini/, .claude/)
  • docs/settings/ content should NOT be documented in steering files (settings are metadata, not project knowledge)
  • Light references to docs/specs/ and docs/steering/ are acceptable; avoid other .kiro/ directories

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.