Open source platform for researching and building trustworthy, Sharia-compliant enterprise products.
This repository also configures its own agents. See what ose-public tells them →
Skill Claude Code
Guides Python work under the Python standard: annotating every signature for Pyright in strict mode, handling paths as pathlib values, placing tests by the boundary they touch, and judging data shapes, failures, and async code.
Skill Claude Code
Guides shell work under the shell standards: checking the declared dialect first, deciding whether logic belongs in shell at all, tracing where exit-on-error does not reach, and testing the script as its callers run it.
Skill Claude Code
Guides the procedure for writing or changing TypeScript: loading the TypeScript standard first, driving each increment test-first, finding which rule a decision falls under, and confirming the gates before handing off.
Skill Claude Code
How readme-fixer re-validates readme-checker findings, assesses HIGH/MEDIUM/FALSEPOSITIVE confidence for README-specific issues, and applies fixes only for objective/verifiable problems. Use when re-validating or applying README quality fixes.
Skill Claude CodeCodex
README quality standards for engaging, accessible, scannable content including problem-solution hooks, plain language (no unexplained jargon), acronym context, paragraph limits (≤5 lines), benefits-focused language, visual hierarchy, and progressive disclosure. Essential for creating effective README files that…
Skill Claude CodeCodex
Three-stage content quality workflow pattern (Maker creates, Checker validates, Fixer remediates) with detailed execution workflows. Use when working with content quality workflows, validation processes, audit reports, or implementing maker/checker/fixer agent roles.
Skill Claude CodeCodex
Universal classification system for checker and fixer agents using orthogonal criticality (CRITICAL/HIGH/MEDIUM/LOW importance) and confidence (HIGH/MEDIUM/FALSEPOSITIVE certainty) dimensions. Covers priority matrix (P0-P4), execution order, dual-label pattern for verification status, standardized report format, and…
Skill Claude CodeCodex
Workflow pattern standards for creating multi-agent orchestrations including two-key frontmatter with the goal, termination, inputs and outputs contract in body sections, execution phases (sequential/parallel/conditional), agent coordination patterns, and success criteria. Essential for defining reusable, validated…
Skill Claude CodeCodex
Guidelines for generating validation/audit reports with UUID chains, progressive writing, and UTC+7 timestamps.
Skill Claude Code
The task-list obligation every agent carries — open the harness's native task list before any task, conversational ones included, and keep it in sync with actual progress. Auto-loads whenever work is about to begin.
Skill Claude CodeCodex
Trunk Based Development workflow - all development on main branch with small frequent commits, minimal branching, and continuous integration. Covers when branches are justified (exceptional cases only), commit patterns, feature flag usage for incomplete work, environment branch rules (deployment only), and AI agent…
Skill Claude Code
Run the rules-propagation workflow whenever a repository rule is being created, updated, superseded, or deleted. TRIGGERS on "add rule", "new rule", "update the rule", "change the convention", "adjust the rule", "delete that rule", "make it a rule that…", "from now on we should…", "we should always/never…", or any…
Skill Claude CodeCodex
Six-layer governance hierarchy (Vision → Principles → Conventions → Development → Agents → Workflows). Use when understanding repository structure, tracing rules to foundational values, explaining architectural decisions, or navigating layer relationships.
Skill Claude Code
Shared repository vocabulary — what "repo rules", the four content trees, delivery units, and governance surfaces actually cover. Auto-loads when a task involves repository rules, governance scope, plans, delivery units, agent or skill boundaries, or any judgement about whether a rule reaches a given file.
Skill Claude CodeCodex
Complete validation methodology for repository-wide governance consistency — file naming/linking/emoji, agent-Skill and Skill-to-Skill duplication/consolidation, governance word budgets, rules-governance contradictions/traceability/licensing/dependency-bump-policy, and software-engineering documentation quality. Used…
Skill Claude Code
Mechanics for social-linkedin-post-maker — the LinkedIn character-limit measurement rule, the no-vanity-metrics rule, the post file format, and the establish-window/gather/draft/measure/write workflow.
Skill Claude Code
Mechanics for specs-maker — the four surface-profile directory trees, README/feature-file/C4-diagram content generation, and the PM-readability/placement/structure conventions every scaffolded file follows.
Skill Claude CodeCodex
Validation methodology for specs/ folders — nine categories covering README/feature-file structural completeness, Gherkin format compliance, cross-folder consistency, C4 diagrams, cross-references, spec-to-implementation alignment, tree-shape compliance, and BDD/contracts adoption gaps. Used by specs-checker and…
Skill Claude Code
Guides Nx workspace work under the Nx standard: selecting projects by the graph, adding a target only where a capability exists, tracing a stale cached pass to its missing input, and answering a module-boundary finding.
Skill Claude CodeCodex
Complete methodology for design-aware live-site evaluation — inputs, the swe-reviewer boundary, non-destructive constraint, design-fidelity + design-practice evaluation, the five ground-truth sources, dimensions checklist, mandatory systematic checks, browser driving, finding anatomy, and output modes. Backs the…
Skill Claude Code
Spec-aware session-based exploratory testing methodology for swe-web-tester (exploratory charter) — charter framing, testing tours, SFDIPOT/CRUSSPIC STMPL coverage models, the test dimensions checklist, three mandatory systematic sweeps, specs-as-ground-truth comparison and spec-gap detection, defect anatomy, and the…
Skill Claude Code
Spec-blind heuristic usability evaluation methodology for swe-usability-tester — Nielsen's 10 heuristics, cognitive walkthrough, first-click/information-scent analysis, the usability dimensions checklist, four mandatory systematic probes, URL naturalness, responsive usability, finding anatomy, and the three output…
Skill Claude CodeCodex
Playwright E2E testing standards from authoritative docs/explanation/software-engineering/automation-testing/tools/playwright/ documentation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: