rag-domain-integrity-gate
Fail-fast gate and domain integrity repair in the RAG graph.
Skill by ArkadiuszSieracki
Chalk Labs
Need help deploying rag-domain-integrity-gate?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/arkadiuszsieracki-rag-domain-integrity-gate
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/rag-domain-integrity-gate
What's inside
- Skill name
rag-domain-integrity-gate- Description
- Fail-fast gate and domain integrity repair in the RAG graph. Use for: path-like domain, domain noise, selective refresh safety, workflow-knowledge normalization.
- License
- Apache-2.0
- Instructions
- 83 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# rag-domain-integrity-gate
Goal: prevent corruption of the domain layer in RAG and halt the pipeline immediately upon regression detection.
## When to use
- `domain_path_like > 0` after refresh or build
- sudden increase in `domain` count without real domain changes
- domains look like file paths (`martous\controllers\x.cs`)
- after changes to `workflow-knowledge` or the incremental rebuild engine
## Quick diagnosis
1. Count path-like domains:
- `type=domain` and `title` contains `/` or `\`
- `code_file.domain` and `file_summary.domain` contains `/` or `\`
2. Check data sources:
- `workflow-summary-log.csv` field `domain`
- node creation sites `New-Node -Domain ...`
- normalization in `Get-DomainFromRelativePath`
3. Check selective refresh:
- whether `index-and-summaries` skips hash updates
- whether domain layer rebuild is deterministic
## Root causes (most common)
1. Missing normalization of `summary.domain` (CSV) before writing to node.
2. Incorrect backslash replacement in PowerShell (`Replace('\\','/')` instead of replacing a single `\`).
3. Different `path-like` definitions across scripts.
4. Missing fail-fast gate (only warnings, pipeline continues).
## Fix standard
1. Fix source normalization:
- If `domain` looks like a path (`[/\]`) -> recalculate via `Get-DomainFromRelativePath`.
2. Unify path-like definitions:
- One rule: path-like = contains `/` or `\`.
- Do not treat suffix `.cs/.ts` alone as path-like without a separator.
3. Add fail-fast to the validator:
- `validate-rag-graph.ps1` should return `path_like_domain_count` and optionally throw an exception (`-FailOnPathLikeDomain`).
4. Hook gate into entry points:
- `refresh-rag-summaries-only.ps1`
- `run-rag-maintenance.ps1`
- `workflow-metrics-core.ps1` (finalize)
5. Add Pester tests:
- path-like domain detection
- fail-fast throw with `-FailOnPathLikeDomain`
- Pester 3 syntax compatibility (`Should Throw`)
## Definition Of Done
- `domain_path_like = 0` after `index-and-summaries` refresh
- `validate-rag-graph -FailOnPathLikeDomain` blocks regressions
- Pester tests for gate pass
- no recurrence of path-like domain growth in subsequent iterations
## Output policy
- Run the integrity gate (`validate-rag-graph.ps1`) itself without `OutputMode`.
- When gate is run by finalize, run finalize by default in `OutputMode quiet`.
- On finalize failure: first read `.github/agents/diagnostics/*.json`, then retry finalize in `OutputMode diagnostic`.
## Result
- PASS: no path-like domains and no stale entries
- WARN: stale entries > 0, but path-like domains = 0
- BLOCK: path-like domains > 0 (fix mandatory before continuing)From ArkadiuszSieracki/mastermind-agentic-sdlc-vscode-copilot, Apache-2.0.
More from ArkadiuszSieracki/mastermind-agentic-sdlc-vscode-copilot
- 0.409score
graph-bootstrap-init
ArkadiuszSieracki
Bootstrap skill for graph initialization and refresh.
SkillDFreshness: DClaude Code +9 - 0.409score
groomer-roster-setup
ArkadiuszSieracki
Interactive bootstrap skill for building a project-specific grooming roster.
SkillDFreshness: DClaude Code +9 - 0.409score
repo-discovery-init
ArkadiuszSieracki
Bootstrap skill for repository discovery.
SkillDFreshness: DClaude Code +9 - 0.409score
preflight-profile-setup
ArkadiuszSieracki
Interactive bootstrap skill for preflight profiles.
SkillDFreshness: DClaude Code +9 - 0.409score
project-standards-capture
ArkadiuszSieracki
Interactive bootstrap skill for project-specific standards.
SkillDFreshness: DClaude Code +9 - 0.409score
powershell-strict-mode
ArkadiuszSieracki
Rules for writing reliable PowerShell with Set-StrictMode -Version Latest: mandatory @(), avoiding .Count on unknown type, safe null comparisons, variable…
SkillDFreshness: DClaude Code +9 - 0.406score
powershell-executor
ArkadiuszSieracki
Runner-first for PowerShell: every instruction is executed via .github/agents/invoke-isolated-powershell.ps1 (Mode detached by default), with…
SkillDFreshness: DClaude Code +9 - 0.406score
component-purity
ArkadiuszSieracki
Verify React component purity - components only render UI, all logic belongs in hooks.
SkillDFreshness: DClaude Code +9 - 0.406score
rag-anti-hallucination-workflow
ArkadiuszSieracki
Practical anti-hallucination workflow for RAG: deterministic vs retrieval, query_type/workflow_phase routing, top-k/scoring, grounding/freshness/waste…
SkillDFreshness: DClaude Code +9 - 0.406score
react-performance
ArkadiuszSieracki
React performance optimization - memoization, list virtualization, lazy loading, bundle size.
SkillDFreshness: DClaude Code +9 - 0.406score
agent-capability-routing
ArkadiuszSieracki
Detect missing capabilities and route to a subagent with proper access.
SkillDFreshness: DClaude Code +9 - 0.406score
db-optimization
ArkadiuszSieracki
PostgreSQL database optimization with EF Core - detect and fix N+1, missing indexes, missing pagination, and incorrect use of AsNoTracking.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 23, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ArkadiuszSieracki
- 0.409score
preflight-profile-setup
ArkadiuszSieracki
Interactive bootstrap skill for preflight profiles.
SkillDFreshness: DClaude Code +9 - 0.409score
project-standards-capture
ArkadiuszSieracki
Interactive bootstrap skill for project-specific standards.
SkillDFreshness: DClaude Code +9 - 0.409score
groomer-roster-setup
ArkadiuszSieracki
Interactive bootstrap skill for building a project-specific grooming roster.
SkillDFreshness: DClaude Code +9 - 0.409score
powershell-strict-mode
ArkadiuszSieracki
Rules for writing reliable PowerShell with Set-StrictMode -Version Latest: mandatory @(), avoiding .Count on unknown type, safe null comparisons, variable…
SkillDFreshness: DClaude Code +9 - 0.409score
graph-bootstrap-init
ArkadiuszSieracki
Bootstrap skill for graph initialization and refresh.
SkillDFreshness: DClaude Code +9 - 0.409score
repo-discovery-init
ArkadiuszSieracki
Bootstrap skill for repository discovery.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get rag-domain-integrity-gate running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
rag-domain-integrity-gate skill. Agent Mart. https://agentmart.dev/skills/arkadiuszsieracki-rag-domain-integrity-gate (last updated 2026-10-24)