software-concept-architect-guardrailsKeep Specs and Code Aligned
Install via ClawdBot CLI:
clawdbot install agenticweb4/software-concept-architect-guardrailsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/ontology-of-everything/concept-skillsAudited Oct 9, 2026 · audit v1.0
Generated Oct 16, 2026
A platform team inherits a large undocumented Node.js monolith and needs contracts captured before a decomposition effort. They run the guardrails skill in backfill mode over key source paths to reconstruct evidenced CONCEPT.md contracts, marking inferred purposes and current defects rather than legitimizing accidental coupling. The resulting specifications become the baseline for refactoring decisions.
An engineering org suspects its concept specs have drifted from implementation after rapid feature delivery. A tech lead invokes drift mode periodically to compare each module's implementation against its stated contract and produces a read-only report naming scan scope and repair direction. Findings feed a spec-first bugfix queue.
A fintech company coordinates onboarding flows shared across identity, KYC, and ledger services. Using sync mode, architects create SYNCS.md packages grouped by flow to record app/include/sync coordination, triggers, and failure semantics. Synchronizations may restrict behavior but never extend contracts, so violating coordination across teams is flagged instead of silently accepted.
A startup preparing a greenfield payments service uses create mode with a natural-language description to generate concept candidates for purpose, state, actions, and operational principle. The draft is reviewed and diffed before any writes, and follow-up pipeline mode documents sources, stages, invariants, and data boundaries. Derived navigation maps are rebuilt after the specifications stabilize.
A consultancy onboarding new engineers to a complex client codebase runs map mode to derive ARCHITECTURE.md navigation maps from specification content rather than file timestamps. The maps help newcomers trace product dependencies from the PRD and locate authoritative specs per concept. Read-only audit mode first discovers candidate modules with no existing specifications.
The guardrails skill is published openly under a permissive license on GitHub, with paid support, migration assistance, and priority fixes for enterprises adopting concept-driven development. Revenue comes from consulting engagements and support contracts rather than the skill itself.
The skill is bundled as a free guardrail layer inside a broader AI coding platform or IDE extension, driving adoption and retention. Teams that standardize on concept specs are upsold to team dashboards, drift monitoring, and CI integrations.
Large organizations license a governed distribution that includes audit trails, policy enforcement around spec-first workflows, and integration with change management. The skill's read-only audit and drift reports become compliance evidence in regulated environments.
💬 Integration Tip
Invoke only explicitly via $software-concept-architect-guardrails, starting with audit mode when no specs exist, and read references/spec-format.md before creating or reading CONCEPT/SYNCS to avoid mixing legacy wyx dialect with the Jackson dialect.
Scored Oct 9, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.