sync-horizon
Sync eve-skillpacks with latest eve-horizon changes. Goes deep into plans, code, and commits to understand what shipped — then cascades to skills and reference docs.
What this skill does
# Sync Horizon Synchronize eve-skillpacks with the latest state of the eve-horizon repository. ## Core Insight System docs often lag behind implementation. Features ship via feat commits with plans marked "Implemented" — but `docs/system/` may not update for weeks. This sync goes to the source: **plans, code changes, and commit messages** tell us what actually shipped. System docs are one signal among many, not the primary driver. ## Prerequisites - The eve-horizon repo must be at `../eve-horizon` (sibling directory) - `.sync-state.json` must exist in the repo root (create from template if missing) - `.sync-map.json` must exist in the repo root ## Architecture: Orchestrator + Parallel Workers You (the orchestrator) discover what shipped and dispatch focused workers. Each worker handles one update in isolation with its own context budget. The orchestrator reads **lightweight signals** (commit log, plan headers, file stats, CLI module list). Workers read the **heavy content** (plan bodies, code diffs, source docs, target files). ## Output Standards - Distill only shipped platform behavior. Plans marked Implemented/Complete describe shipped features. - Do not carry roadmap content into skillpacks. Ignore plans marked Proposed/Draft and sections like `Planned (Not Implemented)`, `What's next`, or "current vs planned" framing. - Keep `eve-work/eve-read-eve-docs/SKILL.md` task-first: route by intent, load only the minimal reference files needed. - Keep reference docs scoped and actionable — curated distillations, not copies. ## Workflow ### Phase 1: Deep Discovery (orchestrator) Read lightweight signals from multiple dimensions to understand what actually shipped. #### 1a. Commit log ```bash cd ../eve-horizon && git log --oneline <last_synced_commit>..HEAD ``` Categorize commits: - `feat:` — new capabilities (primary interest) - `fix:` — bugfixes that may affect documented behavior - `docs:` — documentation changes (check if they describe already-shipped features) - `chore:` / `refactor:` — usually no skillpack impact, but note removals #### 1b. Plan intelligence This is the richest signal. Plans describe what shipped, why, and how. ```bash cd ../eve-horizon && git diff --stat <last_synced_commit>..HEAD -- docs/plans/ ``` For each changed plan, read its **header only** (first 15-20 lines) to extract status: ```bash cd ../eve-horizon && head -20 docs/plans/<plan-file>.md ``` Categorize: - **Shipped**: Status contains `Implemented`, `Complete`, or `Done` — these are the primary source of truth for new capabilities - **In progress**: Status contains `In Progress`, `Partially Implemented` — note for awareness but don't distill unfinished work - **Proposed/Draft**: Status contains `Proposed`, `Plan`, `Draft`, `Ready to build` — skip entirely - **Removed**: Plan files deleted in this range — something was deprecated or abandoned **IMPORTANT**: Do not read full plan bodies. Just headers. Workers will read the plans they need. #### 1c. Code signal New CLI commands, DB migrations, and package changes confirm what shipped and reveal capabilities that plans may not fully describe. ```bash # New/changed/removed CLI commands cd ../eve-horizon && git diff --stat <last_synced_commit>..HEAD -- packages/cli/src/commands/ # New DB migrations (table/column names reveal capability shape) cd ../eve-horizon && git diff --stat <last_synced_commit>..HEAD -- packages/db/migrations/ # Key package changes (new modules, removed modules) cd ../eve-horizon && git diff --stat <last_synced_commit>..HEAD -- packages/shared/src/ packages/api/src/ packages/worker/src/ packages/gateway/src/ --stat-name-width=120 | head -50 ``` #### 1d. System doc changes Still a useful signal — especially for removals and corrections. ```bash cd ../eve-horizon && git diff --stat <last_synced_commit>..HEAD -- docs/system/ AGENTS.md ``` #### 1e. Current CLI surface Snapshot the current CLI command modules. This is the ground truth for what agents can invoke. ```bash cd ../eve-horizon && ls packages/cli/src/commands/*.ts ``` ### Phase 2: Capability Synthesis (orchestrator) **STOP and think.** This is the critical step. Cross-reference all signals to build a capability map. For each **shipped plan** (Implemented/Complete), create a capability entry: ``` Capability: <name> Plan: docs/plans/<file>.md (status: Implemented) Feat commits: <matching commit hashes> Code signal: <new CLI commands, new migrations, new/removed modules> System doc: <updated/created/unchanged> Scope: <which platform areas this touches> One-line summary: <what this capability does, from the plan header> ``` Also create entries for capabilities evidenced by feat commits that have **no corresponding plan** — these are smaller features or fixes that shipped directly. Also note **removals**: plans deleted, CLI commands removed, modules deleted. These need to be cleaned from our skills too. ### Phase 3: Cascade Analysis (orchestrator) For each capability in the map, determine its impact on `eve-read-eve-docs`: #### 3a. Reference doc impact For each capability, ask: 1. Does an existing reference already cover this area? → Worker updates it 2. Is this a new primitive that needs its own reference? → Worker creates it 3. Was something removed? → Worker cleans stale content from affected references Cross-reference against the current reference index in `eve-work/eve-read-eve-docs/SKILL.md` and the `reference_docs` section of `.sync-map.json`. #### 3b. SKILL.md routing impact Check if `eve-work/eve-read-eve-docs/SKILL.md` needs: - New entries in the Task Router - New entries in the Index - New rows in the Intent Coverage Matrix - New trigger keywords in the frontmatter - Removal of stale entries for deprecated capabilities #### 3c. Other skill impact Check `.sync-map.json` `skill_triggers` and `composite_triggers` for other skills affected. Also consider: - `eve-se/eve-manifest-authoring` — if manifest shape changed - `eve-se/eve-deploy-debugging` — if deploy/infra behavior changed - `eve-se/eve-auth-and-secrets` — if auth model changed - `eve-work/eve-agent-memory` — if storage primitives changed - `eve-design/eve-fullstack-app-design` — if app patterns changed ### Phase 4: Plan Work Items (orchestrator) For each update identified in Phase 3, create a work item: - **Title**: `Update <target-file>: <capability name>` - **Description** — everything a worker needs to operate independently: - The eve-horizon repo path (`../eve-horizon`) - The commit range: `<last_synced_commit>..HEAD` - Which plan(s) to read (the shipped plans relevant to this update) - Which source files to diff or read (code, system docs) - The target file path to update or create - Whether this is a reference doc update, skill update, new reference, or removal - The appropriate worker instructions from below Add a final work item: `Update sync state and produce report` — blocked until all updates finish. If any work item touches `eve-work/eve-read-eve-docs`, also add: - `Run state-today compliance scan for eve-read-eve-docs` - `Validate progressive-access routing in eve-read-eve-docs/SKILL.md` - `Update .sync-map.json with any new reference doc mappings` ### Phase 5: Dispatch Workers (parallel) Spawn one background worker per work item. Launch them all at once. **Each worker prompt must be self-contained.** The worker has no access to the orchestrator's conversation. Include: 1. The plan file(s) to read — these are the primary source of truth 2. The git diff command for relevant code/doc changes 3. The target file to read and modify 4. The capability summary from Phase 2 5. The appropriate worker instructions from below #### Worker Instructions: Reference Doc Update > Your primary sources are **shipped plans** (marked Implemented/Complete) and **code changes**. > System docs are secondary — they may lag behind or be absent. > > 1. Read the plan(s) listed in your task — understand what shipped and w
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.