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
- aiproxer/aiproxertheir own version, first seen Nov 8, 2026
- growilabs/growiedited, first seen Oct 8, 2026
- kyuki3rain/cc-sdd-adredited, first seen Jul 27, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- growilabs/growi★ 1.5k77% same
- kyuki3rain/cc-sdd-adr★ 077% same
Wrote their own version · 1
- aiproxer/aiproxer★ 22same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- cc-sdd-restack-after-mergeSkill
- cc-sdd-review-slice-stackSkill
- ci-stable-log-testingSkill
- create-issueSkill
- docker-deployment-guideSkill
- hibernate-pcSkill
- kiro-debugSkill
- kiro-discoverySkill
- kiro-implSkill
- kiro-reviewSkill
- kiro-spec-batchSkill
- kiro-spec-designSkill
- kiro-spec-initSkill
- kiro-spec-quickSkill
- kiro-spec-requirementsSkill
- kiro-spec-statusSkill
- kiro-spec-tasksSkill
- kiro-steering-customSkill
- kiro-validate-designSkill
- kiro-validate-gapSkill
- kiro-validate-implSkill
- kiro-verify-completionSkill
- notion-pdfSkill
- playwright-scraperSkill
- pptx-slides-creatorSkill
- pr-creatorSkill
- pytest-marksSkill
- python-readable-codeSkill
- resolve-pr-review-threadsSkill
- sec-diff-reviewSkill
- sec-full-scanSkill
- sec-runtime-scanSkill
- skill-creatorSkill
- storage-stateSkill
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
- Common: line 31
Sync Mode: All core files exist
- Distinctive: line 47
If multi-agent is enabled, spawn sub-agents for each area above.
- Common: line 49
After all parallel research completes, synthesize patterns for steering files.
- Common: line 70
Custom files: Check relevance
- Common: line 74
Update Philosophy: Add, don't replace. Preserve user sections.
- Common: line 84
Document patterns and principles, not exhaustive lists.
- Distinctive: line 94
Read: Read steering, docs, configs
- Common: line 143
Security: Never include keys, passwords, secrets (see principles)
- Common: line 145
Preservation: Add rather than replace when in doubt
- Very specific: line 153
Avoid documenting agent-specific tooling directories (e.g.
“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.
Files
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/*.mdtreated equally (core + custom) </background_information>
<instructions>
## Scenario DetectionCheck docs/steering/ status:
Bootstrap Mode: Empty OR missing core files (product.md, tech.md, structure.md) Sync Mode: All core files exist
Bootstrap Flow
- Load templates from
docs/settings/templates/steering/ - Analyze codebase (JIT):
Parallel Research
The following research areas are independent and can be executed in parallel:
- Product analysis: README, package.json, documentation files for purpose, value, core capabilities
- Tech analysis: Config files, dependencies, frameworks for technology patterns and decisions
- 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.
- Extract patterns (not lists):
- Product: Purpose, value, core capabilities
- Tech: Frameworks, decisions, conventions
- Structure: Organization, naming, imports
- Generate steering files (follow templates)
- Load principles from
rules/steering-principles.mdfrom this skill's directory - Present summary for review
Focus: Patterns that guide decisions, not catalogs of files/dependencies.
Sync Flow
- Load all existing steering (
docs/steering/*.md) - Analyze codebase for changes (JIT)
- Detect drift:
- Steering → Code: Missing elements → Warning
- Code → Steering: New patterns → Update candidate
- Custom files: Check relevance
- Propose updates (additive, preserve user content)
- 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.mdExamples
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/*.mdloaded 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/anddocs/steering/are acceptable; avoid other.kiro/directories
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
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.

