opencode-skills-collection 4.0.51 → 4.0.53

package/bundled-skills/entropy-box/references/api.md

@@ -0,0 +1,196 @@
+# Entropy Box API reference
+
+Base URL: `https://xiangshang.ngrok.app`
+
+The public API requires no key. It accepts Chinese and English queries. These examples
+target API version 2.0.0 as reviewed on 2026-09-02. Inspect the live OpenAPI document
+when behavior changes.
+
+## Search the compiled knowledge base
+
+`POST /api/search`
+
+```bash
+curl --fail-with-body --silent --show-error \
+  --max-time 60 \
+  -X POST "https://xiangshang.ngrok.app/api/search" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": "mobile manipulation navigation and grasp planning",
+    "scope": "all",
+    "top_k": 10,
+    "mode": "hybrid",
+    "rerank": false
+  }'
+```
+
+Request fields:
+
+| Field | Required | Meaning |
+| --- | --- | --- |
+| `query` | yes | Natural-language need or technical terms |
+| `scope` | no | Search scope; default `all` |
+| `top_k` | no | Result count; default 20 |
+| `mode` | no | Retrieval mode; default `hybrid` |
+| `rerank` | no | Enable reranking; default `false` |
+
+The response contains `query` and a service-defined `results` object. Inspect result
+groups before selecting candidates.
+
+Quick response anatomy (verified against /api/search; the live schema wins):
+
+- `results` is grouped into three scopes — `assets` (implementation assets), `caps`
+  (capabilities), `topics` (topics) — each hit carries `record`, `matched`
+  (vec/lex/graph), and `score`;
+- `chains`: capability subgraphs (anchor + hierarchy/dependency edges) from retrieval,
+  useful for understanding structural relations between capabilities;
+- `dup_folded` / `dup_of` / `dup_group`: dedup-related — the same capability may appear
+  as multiple records; dedup by entity when presenting, do not count it twice;
+- when `low_confidence` is true, or `record.provenance` is `generated`, or the source
+  carries `[verify]`, treat the record as low-confidence: verify against an upstream
+  source before citing and label it "verified / to verify";
+- `score` / `rerank_score` are ranking scores, not factual confidence.
+
+## Search evidence
+
+`POST /api/evidence/search`
+
+```bash
+curl --fail-with-body --silent --show-error \
+  --max-time 60 \
+  -X POST "https://xiangshang.ngrok.app/api/evidence/search" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": "robot obstacle avoidance algorithms",
+    "top_k": 5,
+    "mode": "hybrid",
+    "rerank": true
+  }'
+```
+
+Request fields:
+
+| Field | Required | Meaning |
+| --- | --- | --- |
+| `query` | yes | Natural-language question or technical concept |
+| `topic` | no | Optional topic constraint |
+| `top_k` | no | Result count; default 10 |
+| `mode` | no | Retrieval mode; default `hybrid` |
+| `rerank` | no | Enable reranking; default `true` |
+
+The response contains `query`, a `results` array, and `latency_ms`. Preserve source and
+provenance fields from each result; do not cite a score as evidence.
+
+## Look up an entity
+
+Prefer `POST /api/lookup` for portable clients.
+
+```bash
+curl --fail-with-body --silent --show-error \
+  --max-time 60 \
+  -X POST "https://xiangshang.ngrok.app/api/lookup" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": "CAP_8a7a03ae",
+    "format": "json"
+  }'
+```
+
+Request fields:
+
+| Field | Required | Meaning |
+| --- | --- | --- |
+| `query` | yes | Keyword, Chinese name, `CAP_...`, or `AST_...` |
+| `type` | no | `topic`, `cap`, or `asset` |
+| `format` | no | `json` or `md`; default `json` |
+| `list` | no | Request a candidate list |
+| `first` | no | Select the first exact or ranked match |
+
+The response can contain `found`, `query`, `entity_type`, `record`, `markdown`, and
+`candidates`. Topic lookups may return summary metadata rather than bulk topic content.
+
+For an exact `CAP_...` or `AST_...` ID, the optional `type` filter can be omitted because
+the ID prefix already identifies the entity type. This form is also more portable across
+deployments. Use `type` to narrow name or keyword lookups.
+
+Note: Lookup's exact matching is not guaranteed for Chinese natural phrases (e.g.,
+"柔性控制", "柔顺控制") and may return `found: false` or an empty candidate list. This
+does not mean the concept is absent from the graph — confirm with `/api/search`. Prefer
+exact IDs or English/technical aliases for Lookup.
+
+## Generate a candidate workflow
+
+`POST /api/consult`
+
+By default, Consult runs hybrid retrieval (vector + BM25 + one-hop graph expansion +
+rerank) and returns the **structured knowledge graph** for the question — `results`
+(topics/caps/assets with full records and `graph_via` attribution edges), `task_steps`
+(LLM intent decomposition), and `chains` (capability subgraphs discovered during
+retrieval). This is fast and fully grounded; no LLM assembly is performed.
+
+Set `integrate: true` to additionally ask the backend to assemble the candidates into a
+visualization-ready technical chain via `integrate_planner` (the LLM "post-assembly"
+layer). Even then, the graph results are still returned alongside `synthesis`.
+
+```bash
+# Default: graph only (fast, grounded)
+curl --fail-with-body --silent --show-error \
+  --max-time 60 \
+  -X POST "https://xiangshang.ngrok.app/api/consult" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "question": "Design a simulation-first obstacle-avoidance workflow for a differential-drive ROS 2 robot using a 2D lidar, with 50 ms control latency and no cloud dependency.",
+    "top_k": 30,
+    "rerank": true
+  }'
+
+# With LLM assembly (slower; allow >= 180 s)
+curl --fail-with-body --silent --show-error \
+  --max-time 200 \
+  -X POST "https://xiangshang.ngrok.app/api/consult" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "question": "Design a simulation-first obstacle-avoidance workflow for a differential-drive ROS 2 robot using a 2D lidar, with 50 ms control latency and no cloud dependency.",
+    "top_k": 30,
+    "rerank": true,
+    "integrate": true
+  }'
+```
+
+Request fields:
+
+| Field | Required | Meaning |
+| --- | --- | --- |
+| `question` | yes | Complete robotics engineering question and constraints |
+| `top_k` | no | Candidate count from 10 to 100; default 30 |
+| `rerank` | no | Enable reranking; default `true` |
+| `prev_context` | no | Prior conclusion for a continuing design discussion |
+| `brief` | no | Return only a short chain skeleton; default `false` |
+| `integrate` | no | Enable LLM technical-chain assembly; default `false` (graph only). When `true`, `synthesis` is populated; the graph (`results`/`task_steps`/`chains`) is still returned |
+
+The response always contains `question`, `pool`, `results`, `task_steps`, `chains`, and
+`latency_ms`. When `integrate` is `false` (default), `synthesis` is `null` and the graph
+is the full answer. When `integrate` is `true`, `synthesis` is added (a normal run can
+take 30-180 seconds). The generated workflow is a candidate and must be validated against
+evidence, interfaces, and user constraints.
+
+`synthesis` (only present when `integrate=true`) is a visualization-ready chain structure
+(assembled by the backend integrate_planner):
+
+- `mode`: `chains` (task-chain solution) or `nodes_only` (capability/asset inventory and gaps);
+- `chains`: list of task chains; each step carries `caps` (real capability ID nodes) and may branch or merge; directly renderable as a task-chain graph;
+- `proposed_capabilities`: capabilities proposed by the LLM that are not yet defined in the registry (`NEW_CAP_*`);
+- `gap_annotations` / `summary` / `completeness`: ownership/gap statistics and completeness;
+- `explanation` / `warnings`: rationale and alerts (e.g., "LLM assembly failed, fell back", "all capability references were hallucinations").
+
+With `brief=true`, `synthesis` keeps only `mode` and each chain's `name`/`n_steps`
+skeleton.
+
+## Operational checks
+
+- Use `Content-Type: application/json`.
+- Set explicit timeouts; allow at least 180 seconds when `integrate=true`. Graph-only consult (default) is much faster.
+- Log request parameters and returned IDs, but do not log unrelated credentials or
+  private project data.
+- Avoid automatic repeated consult calls.
+- Recheck the live schema and official integration page after an API-version change.

package/bundled-skills/entropy-box/references/knowledge-compiler.md

@@ -0,0 +1,61 @@
+# Entropy Box knowledge compiler
+
+Use this reference when explaining the system, comparing it with RAG or conventional
+knowledge graphs, or adapting the compilation model to another technical domain.
+
+## Compilation model
+
+Entropy Box follows this conceptual path:
+
+```text
+papers, repositories, documentation, APIs, models, datasets, and benchmarks
+→ source acquisition and evidence records
+→ entity normalization and disambiguation
+→ topic-scoped research and typed assembly
+→ task chains, capabilities, assets, relations, and provenance
+→ bounded validation, deduplication, conflict handling, and admission
+→ persistent graph and indexes
+→ panorama exploration, retrieval, workflow assembly, and gap detection
+→ new compilation targets from observed gaps
+```
+
+The important design decision is to persist reusable structure. A normal query-time
+RAG system retrieves passages and generates an answer; Entropy Box front-loads part of
+the reasoning into a typed artifact that later queries and agents can reuse.
+
+## Main relation families
+
+- domain or topic `contains` subtopics, chains, and entities;
+- task steps use `next`, `branch`, and `merge` structure;
+- steps `require` capabilities;
+- capabilities use parent, child, and dependency relations;
+- assets `implement` or are `used_by` capabilities and topics;
+- records are `grounded_in` evidence and source documents.
+
+Treat relation names as typed claims, not visual decoration. Preserve direction,
+provenance, version, and confidence or validation status when available.
+
+## What it is not
+
+- Not only a web directory: assets are connected to capabilities and task contexts.
+- Not only RAG: the persistent graph exists before the user's query.
+- Not only a knowledge graph: the graph models engineering paths and reusable
+  capability structure.
+- Not a complete robot execution ontology: it does not fully represent live robot
+  state, action semantics, object affordances, or safety control.
+- Not autonomous truth: agents can create candidates, but admission, evidence,
+  conflict handling, and validation determine what becomes persistent.
+
+## Design principles
+
+- **Truth over opinion:** preserve sources, uncertainty, and negative evidence.
+- **Structure over collection:** connect knowledge into typed, usable relationships.
+- **Composition over reinvention:** reuse capabilities and assets across topics.
+- **Verification before intelligence:** do not treat generated structure as admitted
+  knowledge without checks.
+- **Evolution instead of replacement:** update the persistent artifact incrementally
+  and retain version or conflict context.
+
+When applying this model elsewhere, first define the domain's stable entities,
+relations, task structures, evidence rules, and admission gates. Do not copy robotics
+labels into a different domain without checking that they represent its real work.

package/bundled-skills/entropy-box/references/panorama.md

@@ -0,0 +1,72 @@
+# Embodied AI Panorama Graph
+
+Use this reference when the request is about field orientation, technical landscape
+analysis, topic discovery, or graph traversal. Do not load it for a simple exact-entity
+lookup.
+
+## The graph layers
+
+| Layer | Main question |
+| --- | --- |
+| Domain | Which major part of embodied AI does this concern? |
+| Vertical topic | What bounded technical problem is being solved? |
+| Task chain | What implementation steps, branches, or merges are involved? |
+| Capability | What must the system be able to do? |
+| Asset | What can implement, train, evaluate, or support that capability? |
+| Dependency | What ordering, interface, or prerequisite connects the parts? |
+| Evidence | What source supports or qualifies the technical choice? |
+
+The public graph currently spans Foundation Models; Human-Robot Interaction; Learning
+and Adaptation; Localization; Manipulation; Mapping and SLAM; Motion and Control;
+Multi-Robot Systems; Navigation; Perception; Planning and Decision; Reasoning and
+Agents; Safety and Trust; Simulation and Digital Twins; and System Infrastructure.
+
+## Traversal patterns
+
+### Field map
+
+Use when the user asks for an overview of a direction.
+
+1. Select the central domain and two to four adjacent domains.
+2. Identify representative vertical topics within each.
+3. Find capabilities reused across topics.
+4. Group assets by role rather than popularity.
+5. Trace major dependencies between groups.
+6. Report evidence coverage and missing regions.
+
+### Engineering path
+
+Use when the user wants to build a system.
+
+1. Translate requirements into one or more vertical topics.
+2. Inspect candidate task chains and branch conditions.
+3. Resolve required capabilities and prerequisites.
+4. Connect capabilities to compatible assets.
+5. Retrieve evidence for critical choices.
+6. Expose unresolved interfaces and validation gates.
+
+### Cross-domain dependency map
+
+Use when failure or complexity lies between subsystems.
+
+1. Identify the capability where the handoff occurs.
+2. Trace upstream data, model, hardware, and runtime prerequisites.
+3. Trace downstream consumers and evaluation requirements.
+4. Separate explicit graph dependencies from inferred relationships.
+5. Describe the smallest interface contract that connects the subsystems.
+
+## Recommended outputs
+
+A panorama answer should be selective rather than exhaustive. Include:
+
+- central and adjacent domains;
+- representative topics;
+- shared or bottleneck capabilities;
+- important task/dependency paths;
+- asset categories and examples;
+- available evidence and conflicts;
+- blind spots and open questions.
+
+Do not claim that graph size proves correctness or completeness. Counts describe the
+artifact's scale; evidence resolvability, semantic quality, coverage, and freshness are
+separate properties.

package/bundled-skills/laravel-development-workflow/SKILL.md

@@ -0,0 +1,106 @@
+---
+name: laravel-development-workflow
+description: "Build and fix existing Laravel applications through root-cause diagnosis, repository-native implementation, regression coverage, and risk-based verification."
+category: development
+risk: critical
+source: community
+source_repo: Junaid-PK/laravel-development-workflow
+source_type: community
+date_added: "2026-09-02"
+author: Junaid-PK
+tags: [laravel, php, debugging, testing, development]
+tools: [claude, codex, cursor, gemini]
+license: "MIT"
+license_source: "https://github.com/Junaid-PK/laravel-development-workflow/blob/main/LICENSE"
+---
+
+# Laravel Development Workflow
+
+Make the requested Laravel behavior correct, maintainable within the existing application, and supported by evidence that matches the change's risk.
+
+## When to Use
+
+- Use when implementing a feature in an existing Laravel application.
+- Use when diagnosing and fixing a Laravel bug at its actionable root cause.
+- Use when a Laravel change needs regression coverage and proportionate verification.
+- Use when the project already has architectural or testing conventions that must be preserved.
+
+## Establish the Contract
+
+Before editing:
+
+- Read the repository instructions and inspect the relevant routes, models, controllers, actions or services, requests, policies, jobs, events, tests, and schema.
+- Trace the current behavior far enough to identify the actual change boundary and existing conventions.
+- Turn the request into a compact set of scenarios, important edge cases, and verifiable acceptance criteria. Keep this analysis in the working notes unless the user requests a separate artifact.
+- Identify authorization, validation, transaction, queue, cache, and concurrency concerns only where they can affect this behavior.
+
+Scale the analysis to the task. A focused validation fix does not need the same ceremony as a new multi-role workflow.
+
+## Fix Bugs at the Cause
+
+For a bug:
+
+1. Reproduce the failure through the narrowest reliable path.
+2. Trace the data and control flow to the actionable root cause.
+3. Add or update a regression test that fails for that cause when practical.
+4. Implement the smallest fix that restores the intended invariant.
+5. Demonstrate that the regression test passes and that nearby behavior still works.
+
+Do not substitute retries, broad exception handling, disabled validation, extra timeouts, or error suppression for a root-cause fix. If the failure cannot be reproduced locally, state what evidence is missing and use the strongest available static or targeted verification.
+
+## Build Features in the Existing Shape
+
+- Reuse the application's established patterns and naming.
+- Keep business rules in the layer where this codebase already places comparable rules.
+- Use Eloquent relationships, form requests, policies, actions, services, events, or jobs when they improve this change or match local conventions—not as mandatory ceremony.
+- Treat authorization and validation as explicit behavior at the system boundary.
+- Preserve backwards compatibility unless the request requires a breaking change.
+- Keep migrations reversible and safe for the application's supported database engines.
+
+Create factories, seeders, fixtures, or a disposable command only when realistic data is needed for development or durable test coverage. Do not leave one-off scaffolding in the product solely to exercise a small change.
+
+## Verify Proportionately
+
+Discover the project's supported commands from its configuration and documentation. Prefer this order:
+
+1. Run the narrowest affected test or reproduce the original failure.
+2. Run the relevant feature, unit, or integration test group.
+3. Run static analysis, formatting, and linting configured by the repository.
+4. Run the broader suite when the change's reach or project policy warrants it.
+
+Cover the critical observable behavior, including the happy path and whichever edge cases, validation rules, permissions, database effects, events, notifications, jobs, or API contracts are actually affected. Avoid tests that only mirror implementation details.
+
+Common commands may include:
+
+```bash
+php artisan test --filter=RelevantTest
+vendor/bin/pest --filter=RelevantTest
+vendor/bin/phpstan analyse
+vendor/bin/pint --dirty
+```
+
+Use the commands the project provides; do not install or configure tools merely because they appear in this example.
+
+## Preserve the User's Environment
+
+- Keep the change inside the requested application behavior and preserve unrelated working-tree changes.
+- Do not run destructive database operations, production commands, deployments, credential changes, or external account actions unless the user or repository instructions explicitly place them in scope.
+- Avoid exposing secrets in commands, logs, test output, or completion evidence.
+- Prefer local, reversible verification and narrowly targeted data changes.
+
+## Completion Evidence
+
+Before handing off, verify each acceptance criterion against current behavior. Report:
+
+- what changed and why it fixes or implements the requested behavior;
+- the scenarios and important edge cases covered;
+- the exact checks run and their results;
+- any check that could not run, with the concrete reason and remaining risk.
+
+Do not claim completion from code inspection alone when executable verification is available.
+
+## Limitations
+
+- This workflow requires an existing Laravel application and adapts to that repository's architecture and tooling; it does not impose a complete project structure.
+- It cannot prove production behavior when the required services, data, credentials, or environment are unavailable, so any unverified risk must be reported explicitly.
+- It does not authorize destructive database work, production changes, deployments, credential changes, or external account actions.

package/bundled-skills/loki-mode/examples/todo-app-generated/backend/package-lock.json

@@ -857,9 +857,9 @@
       }
     },
     "node_modules/hasown": {
-      "version": "2.0.3",
-      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.3.tgz",
-      "integrity": "sha512-ej4AhfhfL2Q2zpMmLo7U1Uv9+PyhIZpgQLGT1F9miIGmiCJIoCgSmczFdrc97mWT4kVY72KA+WnnhJ5pghSvSg==",
+      "version": "2.0.4",
+      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.4.tgz",
+      "integrity": "sha512-T2UbfbBEF32wiepXIsMlTW9+dDYC6wMh/t/vYA4tuOMKqWz/n3vr1NFSxQiyP+zk2mXsoMA/i/7qV6LKut1t1A==",
       "license": "MIT",
       "dependencies": {
         "function-bind": "^1.1.2"
@@ -1193,12 +1193,13 @@
       }
     },
     "node_modules/qs": {
-      "version": "6.15.2",
-      "resolved": "https://registry.npmjs.org/qs/-/qs-6.15.2.tgz",
-      "integrity": "sha512-Rzq0KEyX/w/tEybncDgdkZrJgVUsUMk3xjh3t5bv3S1HTAtg+uOYt72+ZfwiQwKdysThkTBdL/rTi6HDmX9Ddw==",
+      "version": "6.16.0",
+      "resolved": "https://registry.npmjs.org/qs/-/qs-6.16.0.tgz",
+      "integrity": "sha512-h6fhOIaRrID2CbEY2fqs+7t+UXZo+MLAnU5gRIq85uFtdiUPCdsApMlHhXogKVM4HM2DVbIjGNTTYH2OcmP1vA==",
       "license": "BSD-3-Clause",
       "dependencies": {
-        "side-channel": "^1.1.0"
+        "es-define-property": "^1.0.1",
+        "side-channel": "^1.1.1"
       },
       "engines": {
         "node": ">=0.6"
@@ -1350,14 +1351,14 @@
       "license": "ISC"
     },
     "node_modules/side-channel": {
-      "version": "1.1.0",
-      "resolved": "https://registry.npmjs.org/side-channel/-/side-channel-1.1.0.tgz",
-      "integrity": "sha512-ZX99e6tRweoUXqR+VBrslhda51Nh5MTQwou5tnUDgbtyM0dBgmhEDtWGP/xbKn6hqfPRHujUNwz5fy/wbbhnpw==",
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/side-channel/-/side-channel-1.1.1.tgz",
+      "integrity": "sha512-6x6dK6zJdpTzF4sQeNYxwtvBzf6Eg4GtlesS94HOvTudUeyK2WXAaIfmDgsyslYrRBeFIlsi54AYsFGUuhmvrQ==",
       "license": "MIT",
       "dependencies": {
         "es-errors": "^1.3.0",
-        "object-inspect": "^1.13.3",
-        "side-channel-list": "^1.0.0",
+        "object-inspect": "^1.13.4",
+        "side-channel-list": "^1.0.1",
         "side-channel-map": "^1.0.1",
         "side-channel-weakmap": "^1.0.2"
       },

package/bundled-skills/loki-mode/examples/todo-app-generated/backend/package.json

@@ -25,6 +25,6 @@
   "overrides": {
     "diff": "4.0.4",
     "path-to-regexp": "0.1.13",
-    "qs": "^6.15.0"
+    "qs": "^6.16.0"
   }
 }