repo-syncing-with-ose-primer

Classifier parsing, clone management, transform implementations, noise suppression, significance bucketing, report formatting, and extraction-scope enumeration for the two maker agents that sync content between `ose-public` (upstream) and `ose-primer` (downstream template). Keeps both agents aligned to a single authoritative classifier and a single per-mode report schema.

9 stars

Best use case

repo-syncing-with-ose-primer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Classifier parsing, clone management, transform implementations, noise suppression, significance bucketing, report formatting, and extraction-scope enumeration for the two maker agents that sync content between `ose-public` (upstream) and `ose-primer` (downstream template). Keeps both agents aligned to a single authoritative classifier and a single per-mode report schema.

Teams using repo-syncing-with-ose-primer should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/repo-syncing-with-ose-primer/SKILL.md --create-dirs "https://raw.githubusercontent.com/wahidyankf/open-sharia-enterprise/main/.claude/skills/repo-syncing-with-ose-primer/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/repo-syncing-with-ose-primer/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How repo-syncing-with-ose-primer Compares

Feature / Agentrepo-syncing-with-ose-primerStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Classifier parsing, clone management, transform implementations, noise suppression, significance bucketing, report formatting, and extraction-scope enumeration for the two maker agents that sync content between `ose-public` (upstream) and `ose-primer` (downstream template). Keeps both agents aligned to a single authoritative classifier and a single per-mode report schema.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Syncing with ose-primer

## Purpose

This Skill consolidates every procedure both `repo-ose-primer-adoption-maker` and `repo-ose-primer-propagation-maker` need to run safely. Embedding the procedures once, in one place, avoids divergence between the two agents and lets the classifier evolve without agent-definition edits.

**Consumed by:**

- `repo-ose-primer-adoption-maker` — reads classifier rows tagged `adopt` or `bidirectional`; compares primer → `ose-public`.
- `repo-ose-primer-propagation-maker` — reads classifier rows tagged `propagate` or `bidirectional`; compares `ose-public` → primer. Supports three modes: `dry-run`, `apply`, `parity-check`.

**Authoritative data source**: [`repo-governance/conventions/structure/ose-primer-sync.md`](../../../repo-governance/conventions/structure/ose-primer-sync.md) — the classifier table, transforms, and safety invariants live there; this Skill only describes how to consume them.

## Classifier lookup

Parse the classifier table from the convention doc. Exact procedure: see [`reference/classifier-parsing.md`](./reference/classifier-parsing.md).

Summary:

1. Locate H3 "Classifier table" heading in the convention doc.
2. Read the next markdown table.
3. Each row = `(pattern, direction, transform, rationale)`.
4. Resolve glob patterns against the target path.
5. Orphan paths default to `neither`.

## Clone management

Pre-flight, worktree mechanics, and cleanup for the primer clone. Exact procedure: see [`reference/clone-management.md`](./reference/clone-management.md).

Summary:

- Clone path: resolved from `OSE_PRIMER_CLONE`; convention default `~/ose-projects/ose-primer`.
- Pre-flight: env-var check, `.git` present, origin remote URL verified, `fetch --prune`, clean-tree check, main-branch check.
- Apply mode: works inside a git worktree at `$OSE_PRIMER_CLONE/.claude/worktrees/sync-<ts>-<uuid>/` on branch `sync/<ts>-<uuid>`. Never mutates the primer's main working tree.
- Every primer mutation reaches GitHub through a draft pull request — no escape hatch.

## Transform implementations

`identity` (no-op copy) and `strip-product-sections` (remove H2/H3 sections referencing product apps). Exact algorithms: see [`reference/transforms.md`](./reference/transforms.md).

When a `bidirectional` path needs a transform not yet implemented, the agent reports the file as a **transform-gap** and abstains. The convention doc's transform vocabulary is the contract.

## Noise-suppression rules

Findings are emitted only when they represent meaningful divergence. Drop:

- Differences purely in trailing whitespace, line-ending style, or EOL-at-end-of-file.
- Timestamp-only changes in frontmatter (`updated: YYYY-MM-DD`) unless accompanied by body changes.
- Ephemeral artifacts under `generated-reports/`, `local-temp/`, `node_modules/`, `obj/`, `.nx/`, `.venv/` — never diffed.
- Paths that fall under `.gitignore` in either repo.
- Changes to lockfiles (`package-lock.json`, `go.work.sum`) when no corresponding manifest change exists.

## Significance classification

Every surfaced finding carries one of three buckets:

| Bucket   | Meaning                                                                                                          |
| -------- | ---------------------------------------------------------------------------------------------------------------- |
| `high`   | Content-bearing changes (new paragraphs, new steps, renamed commands, new agents, new skills, new conventions).  |
| `medium` | Structural changes (heading reordering, list reshuffling, link retargeting, table schema changes).               |
| `low`    | Style-only (capitalisation, punctuation, filler-word edits, formatting tweaks beyond the noise-suppression cut). |

Findings are grouped by bucket in the report so reviewers can triage.

## Report format summary

Every invocation writes exactly one report. Exact schema: see [`reference/report-schema.md`](./reference/report-schema.md).

Filename patterns:

- Sync (`adoption-maker`, `propagation-maker` in `dry-run`/`apply`): `<agent-name>__<uuid-chain>__<utc+7-timestamp>__report.md`.
- Parity (`propagation-maker` in `parity-check`): `parity__<uuid-chain>__<utc+7-timestamp>__report.md`.

Body sections: Summary, Classifier coverage, Findings (grouped by direction + significance), Excluded paths appendix, Next steps. Parity reports have a distinct body: per-path equal/newer/missing table plus a single-line verdict.

## Extraction scope summary

Frozen list for the Phase 7 parity check and Phase 8 extraction. Exact path list: see [`reference/extraction-scope.md`](./reference/extraction-scope.md).

Scope covers all 17 `apps/a-demo-*` directories plus `specs/apps/a-demo/`. Frozen at plan authoring time; future extractions (if any) add new scope documents rather than editing this one.

## Invocation patterns

### `repo-ose-primer-adoption-maker`

- **Mode**: dry-run (default; only mode).
- **Inputs**: none required. Reads `OSE_PRIMER_CLONE` from env.
- **Writes**: one report under `generated-reports/repo-ose-primer-adoption-maker__*__report.md`.
- **Side effects**: none outside the report file.

### `repo-ose-primer-propagation-maker`

- **Mode**: `dry-run` (default), `apply`, `parity-check`.
- **Inputs**:
  - `dry-run`: optional scope filter.
  - `apply`: operator's explicit approval of a prior `dry-run` proposal.
  - `parity-check`: reads `reference/extraction-scope.md` path list.
- **Writes**:
  - `dry-run`/`apply`: `generated-reports/repo-ose-primer-propagation-maker__*__report.md`.
  - `apply` additionally: git worktree under `$OSE_PRIMER_CLONE/.claude/worktrees/`, branch + draft PR.
  - `parity-check`: `generated-reports/parity__*__report.md`.
- **Side effects**:
  - `dry-run`, `parity-check`: none outside the report file.
  - `apply`: mutates the primer worktree (not main), pushes branch, opens draft PR.

## Safety checklist (every mode)

Before writing any file, the agent confirms:

1. Pre-flight passed (clone present, clean, on `main`, up to date).
2. Every enumerated path was classified (orphan-default accepted silently; no orphans emit findings).
3. No `neither` path appears in the findings list — `neither` paths are dropped, not transformed.
4. Transform-gap files are reported but not modified.
5. Mode-specific side effects are opted into by the operator (dry-run does not mutate anything; apply mode requires explicit approval; parity-check is read-only).

A violation of any of these is a Skill-level defect, not a per-agent judgement call.

Related Skills

repo-understanding-repository-architecture

9
from wahidyankf/open-sharia-enterprise

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.

repo-practicing-trunk-based-development

9
from wahidyankf/open-sharia-enterprise

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 default behavior (assume main). Essential for understanding repository git workflow and preventing unnecessary branch proliferation

repo-generating-validation-reports

9
from wahidyankf/open-sharia-enterprise

Guidelines for generating validation/audit reports with UUID chains, progressive writing, and UTC+7 timestamps

repo-defining-workflows

9
from wahidyankf/open-sharia-enterprise

Workflow pattern standards for creating multi-agent orchestrations including YAML frontmatter (name, goal, termination, inputs, outputs), execution phases (sequential/parallel/conditional), agent coordination patterns, and Gherkin success criteria. Essential for defining reusable, validated workflow processes.

repo-assessing-criticality-confidence

9
from wahidyankf/open-sharia-enterprise

Universal classification system for checker and fixer agents using orthogonal criticality (CRITICAL/HIGH/MEDIUM/LOW importance) and confidence (HIGH/MEDIUM/FALSE_POSITIVE certainty) dimensions. Covers priority matrix (P0-P4), execution order, dual-label pattern for verification status, standardized report format, and domain-specific examples. Essential for implementing checker/fixer agents and processing audit reports

repo-applying-maker-checker-fixer

9
from wahidyankf/open-sharia-enterprise

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.

nx-workspace

9
from wahidyankf/open-sharia-enterprise

Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.

nx-run-tasks

9
from wahidyankf/open-sharia-enterprise

Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.

nx-plugins

9
from wahidyankf/open-sharia-enterprise

Find and add Nx plugins. USE WHEN user wants to discover available plugins, install a new plugin, or add support for a specific framework or technology to the workspace.

nx-import

9
from wahidyankf/open-sharia-enterprise

Import, merge, or combine repositories into an Nx workspace using nx import. USE WHEN the user asks to adopt Nx across repos, move projects into a monorepo, or bring code/history from another repository.

nx-generate

9
from wahidyankf/open-sharia-enterprise

Generate code using nx generators. INVOKE IMMEDIATELY when user mentions scaffolding, setup, structure, creating apps/libs, or setting up project structure. Trigger words - scaffold, setup, create a ... app, create a ... lib, project structure, generate, add a new project. ALWAYS use this BEFORE calling nx_docs or exploring - this skill handles discovery internally.

monitor-ci

9
from wahidyankf/open-sharia-enterprise

Monitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", wants to track CI status, or needs help with self-healing CI fixes. Prefer this skill over native CI provider tools (gh, glab, etc.) for CI monitoring — it integrates with Nx Cloud self-healing which those tools cannot access.