opencode-skills-collection 3.0.46 → 3.0.48

package/bundled-skills/sharp-coder/SKILL.md

@@ -0,0 +1,131 @@
+---
+name: sharp-coder
+description: >
+  Two-layer performance skill combining disciplined THINK layer (surgical edits, simplicity) and terse SPEAK layer (caveman compression). Triggers on requests for brevity, token efficiency, or disciplined coding.
+risk: safe
+source: self
+source_type: self
+---
+
+# Sharp Coder
+
+Two orthogonal layers. Both always active. Neither overrides the other.
+
+| Layer | Governs | When active |
+|---|---|---|
+| **THINK** | Reasoning & coding behavior | Before/during any code task |
+| **SPEAK** | Prose output style | Every response |
+
+Shared philosophy: **no bloat**. Not in code. Not in words.
+
+## When to Use
+
+Use when the user explicitly requests brevity ("caveman mode", "less tokens", "be brief") OR requests disciplined coding ("karpathy guidelines", "think before coding"). This skill combines extreme token efficiency in prose with rigorous engineering discipline in code generation.
+
+---
+
+## SPEAK Layer — Caveman Compression
+
+Default: **full** mode. Switch: `/caveman lite|full|ultra`. Off: `stop caveman` / `normal mode`.
+
+**Drop:** articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Pattern: `[thing] [action] [reason]. [next step].`
+
+**Keep exact:** technical terms, code blocks, error strings, API names, function names, symbols.
+
+### Intensity levels
+
+| Level | Rules |
+|---|---|
+| **lite** | Drop filler/hedging. Keep articles + full sentences. Tight but professional. |
+| **full** | Drop articles, fragments OK, short synonyms. Classic caveman. |
+| **ultra** | Abbreviate prose words (DB/auth/config/req/res/fn/impl), strip conjunctions, arrows for causality (X → Y). Code symbols/names/errors: never abbreviate. |
+| **wenyan-lite** | Classical Chinese register, light compression. Drop filler/hedging, keep grammar. |
+| **wenyan-full** | Full 文言文. 80-90% character reduction. Classical particles (之/乃/為/其), verbs before objects, subjects often omitted. |
+| **wenyan-ultra** | Extreme classical compression. Maximum terseness. |
+
+### Quick example — "Why React component re-render?"
+- **lite:** "Component re-renders because you create a new object reference each render. Wrap it in `useMemo`."
+- **full:** "New obj ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`."
+- **ultra:** "Inline obj prop → new ref → re-render. `useMemo`."
+
+### Auto-clarity — drop compression for:
+- Security warnings
+- Irreversible action confirmations (deletions, drops, overwrites)
+- Clarifying questions when confused (see THINK layer — always full prose)
+- Multi-step sequences where fragment order risks misread
+- When compression itself creates technical ambiguity
+
+Resume caveman immediately after the clear section ends.
+
+**Persistence:** Active every response until explicitly stopped. No drift back to verbose after many turns.
+
+---
+
+## THINK Layer — Coding Discipline
+
+### 1. Think Before Coding
+
+State assumptions explicitly before writing code. If multiple interpretations exist, present them — don't pick silently. If something is unclear, **stop and ask in full prose** (Auto-clarity applies here always).
+
+Ask: "Is there a simpler approach?" If yes, say so. Push back when warranted.
+
+### 2. Simplicity First
+
+Min code that solves the problem. Nothing speculative.
+
+- No features beyond what was asked
+- No abstractions for single-use code
+- No unrequested "flexibility" or "configurability"
+- No error handling for impossible scenarios
+
+If output is 200 lines and could be 50, rewrite it.
+
+### 3. Surgical Changes
+
+Touch only what the request requires.
+
+- Don't improve adjacent code, comments, or formatting
+- Don't refactor things that aren't broken
+- Match existing style even if you'd do it differently
+- Notice unrelated dead code → mention it, don't delete it
+
+When your changes create orphans: remove imports/variables/functions that **your** changes made unused. Don't remove pre-existing dead code unless asked.
+
+Every changed line must trace directly to the user's request.
+
+### 4. Goal-Driven Execution
+
+Transform tasks into verifiable goals before starting:
+
+```
+"Add validation"  →  write tests for invalid inputs, then make them pass
+"Fix the bug"     →  write a test that reproduces it, then make it pass
+"Refactor X"      →  ensure tests pass before and after
+```
+
+For multi-step tasks, state a terse plan first (SPEAK layer applies):
+
+```
+1. [step] → verify: [check]
+2. [step] → verify: [check]
+3. [step] → verify: [check]
+```
+
+Strong success criteria = loop independently. Weak criteria ("make it work") = constant clarification.
+
+---
+
+## Interaction Between Layers
+
+| Situation | THINK | SPEAK |
+|---|---|---|
+| Writing code | Active — discipline applies | Code blocks always normal; prose around them compressed |
+| Stating a plan | Active — terse plan format | Compressed (full mode) |
+| Asking a clarifying question | Active — stop and ask | **Full prose always** |
+| Security / destructive op warning | Active | **Full prose always** |
+| Explaining a concept | Not applicable | Compressed per level |
+
+Code and commits are always written normally regardless of SPEAK level. Only prose is compressed.
+
+## Limitations
+- Over-compression may lead to ambiguity. Use full mode if the context is lost.

package/bundled-skills/unship/SKILL.md

@@ -2,7 +2,7 @@
 name: unship
 description: "Compare AI agent-made UI variants locally in a real app, then keep one and clean up unused temporary code."
 category: development
-risk: safe
+risk: critical
 source: community
 source_repo: mbenhard/unship
 source_type: community
@@ -12,6 +12,10 @@ tags: [ui-variants, frontend, local-first, coding-agents]
 tools: [claude-code, antigravity, cursor, gemini-cli, codex-cli, opencode]
 license: "MIT"
 license_source: "https://github.com/mbenhard/unship/blob/main/LICENSE"
+plugin:
+  targets:
+    codex: blocked
+    claude: blocked
 ---
 
 # Unship
@@ -44,16 +48,17 @@ Prefer the project-local binary when it exists:
 ./node_modules/.bin/unship doctor --json --no-update-check
 ```
 
-Otherwise use the npm package without assuming a global binary:
+Otherwise install a reviewed, exact CLI version into the project and then run the local binary:
 
 ```bash
-npx -y @unship/cli@latest doctor --json --no-update-check
+npm install --save-dev @unship/cli@<reviewed-version>
+./node_modules/.bin/unship doctor --json --no-update-check
 ```
 
 If setup is needed for the local picker, run:
 
 ```bash
-npx -y @unship/cli@latest setup --json
+./node_modules/.bin/unship setup --json
 ```
 
 Patch only the smallest development-only mount point required to load the picker in the local preview.
@@ -95,7 +100,7 @@ When the user picks a winner, keep that option's real source and remove losing o
 For final cleanup before shipping, remove all Unship artifacts and run:
 
 ```bash
-npx -y @unship/cli@latest check --json
+./node_modules/.bin/unship check --json
 ```
 
 Do not claim cleanup is complete until the check reports clean.
@@ -117,6 +122,7 @@ Do not claim cleanup is complete until the check reports clean.
 ## Security & Safety Notes
 
 - Run commands only in a local project the user has authorized you to modify.
+- Do not run `npx @unship/cli@latest` or any unpinned remote CLI in automated agent workflows. Pin and review the package version first, then execute the project-local binary.
 - Treat generated variants as temporary code that must be cleaned before release.
 - Before destructive cleanup, confirm the selected option label when the user's choice is ambiguous.
 - If a baseline build or typecheck already fails before Unship edits, report that baseline state and keep variant work isolated.

package/bundled-skills/uv-package-manager/resources/implementation-playbook.md

@@ -54,7 +54,7 @@ Comprehensive guide to using uv, an extremely fast Python package installer and
 tmpdir="$(mktemp -d)"
 trap 'rm -rf "$tmpdir"' EXIT
 curl -LsSf https://astral.sh/uv/install.sh -o "$tmpdir/uv-install.sh"
-sed -n '1,160p' "$tmpdir/uv-install.sh"
+cat "$tmpdir/uv-install.sh"  # review the full installer before executing
 sh "$tmpdir/uv-install.sh"
 
 # Windows (PowerShell)

package/bundled-skills/varlock/SKILL.md

@@ -91,7 +91,7 @@ curl -H "Authorization: Bearer $API_KEY" https://api.example.com
 tmpdir="$(mktemp -d)"
 trap 'rm -rf "$tmpdir"' EXIT
 curl -sSfL https://varlock.dev/install.sh -o "$tmpdir/varlock-install.sh"
-sed -n '1,160p' "$tmpdir/varlock-install.sh"
+cat "$tmpdir/varlock-install.sh"  # review the full installer before executing
 sh "$tmpdir/varlock-install.sh" --force-no-brew
 
 # Add to PATH (add to ~/.zshrc or ~/.bashrc)
@@ -249,7 +249,7 @@ varlock load
 # Install Varlock in container
 RUN tmpdir="$(mktemp -d)" \
     && curl -sSfL https://varlock.dev/install.sh -o "$tmpdir/varlock-install.sh" \
-    && sed -n '1,160p' "$tmpdir/varlock-install.sh" \
+    && cat "$tmpdir/varlock-install.sh" \
     && sh "$tmpdir/varlock-install.sh" --force-no-brew \
     && rm -rf "$tmpdir" \
     && ln -s /root/.varlock/bin/varlock /usr/local/bin/varlock

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-collection",
-  "version": "3.0.46",
+  "version": "3.0.48",
   "description": "OpenCode CLI plugin that automatically downloads and keeps skills up to date.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/skills_index.json

@@ -307,6 +307,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "accint-solve",
+    "path": "skills/accint-solve",
+    "category": "ai-agents",
+    "name": "accint-solve",
+    "description": "Route agent work through AccInt's MCP memory loop: retrieve prior outcomes, resolve frames, and close commitments with evidence.",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-06-15",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "active-directory-attacks",
     "path": "skills/active-directory-attacks",
@@ -1483,6 +1505,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "android-cli",
+    "path": "skills/android-cli",
+    "category": "tools",
+    "name": "android-cli",
+    "description": "Orchestrates Android development tasks including project creation, deployment, SDK management, and environment diagnostics using the `android` command-line tool.",
+    "risk": "safe",
+    "source": "self",
+    "date_added": "2026-06-15",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "android-dev",
     "path": "skills/android-dev",
@@ -8567,6 +8611,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "codex-fable5",
+    "path": "skills/codex-fable5",
+    "category": "agent-behavior",
+    "name": "codex-fable5",
+    "description": "Apply Fable-inspired discipline to Codex work: inspect first, track goals and findings, ground conclusions in evidence, verify before completion, and adapt Claude/Fable prompt guidance without identity or provider claims.",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-06-15",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "codex-review",
     "path": "skills/codex-review",
@@ -11475,6 +11541,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "dos-verify-done-claims",
+    "path": "skills/dos-verify-done-claims",
+    "category": "quality",
+    "name": "dos-verify-done-claims",
+    "description": "Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's `dos verify` and `dos commit-audit` \u2014 never the agent's own narration.",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-06-12",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "dotnet-architect",
     "path": "skills/dotnet-architect",
@@ -11717,6 +11805,50 @@
       "reasons": []
     }
   },
+  {
+    "id": "ecl-harness-engineer",
+    "path": "skills/ecl-harness-engineer",
+    "category": "development",
+    "name": "ecl-harness-engineer",
+    "description": "Create or audit ECL Agent Harness infrastructure: AGENTS.md, change tracking, repository guidance, lint checks, CI gates, and agent handoff docs.",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-06-13",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
+  {
+    "id": "efficient-web-research",
+    "path": "skills/efficient-web-research",
+    "category": "uncategorized",
+    "name": "efficient-web-research",
+    "description": "Protocol for token-efficient web research. Use when accessing URLs, GitHub repos, or running search queries. Prevents full-page fetching waste.",
+    "risk": "safe",
+    "source": "unknown",
+    "date_added": null,
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "ejentum-reasoning-harness",
     "path": "skills/ejentum-reasoning-harness",
@@ -18815,6 +18947,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "lovable-cleanup",
+    "path": "skills/lovable-cleanup",
+    "category": "uncategorized",
+    "name": "lovable-cleanup",
+    "description": "Audits and strips Lovable scaffolding from Vite + React projects \u2014 removes lovable-tagger, swaps placeholder assets, prunes unused Radix deps, and cleans generated docs so the codebase ships as yours.",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-06-13",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "luna",
     "path": "skills/agent-squad/luna",
@@ -20365,6 +20519,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "monopoly",
+    "path": "skills/monopoly",
+    "category": "architecture",
+    "name": "monopoly",
+    "description": "MONOPOLY is a Senior System Design Engineer skill for architecting, reviewing, and scaling systems. Triggers on requests involving architecture, databases, scaling, microservices, or infrastructure design. Proactively engages to design resilient backend systems.",
+    "risk": "unknown",
+    "source": "unknown",
+    "date_added": null,
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "monorepo-architect",
     "path": "skills/monorepo-architect",
@@ -22592,6 +22768,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "pagespeed-enhancer",
+    "path": "skills/pagespeed-enhancer",
+    "category": "uncategorized",
+    "name": "pagespeed-enhancer",
+    "description": "Scan, audit, and fix web performance issues across all four Lighthouse/PageSpeed Insights pillars \u2014 Performance, Accessibility, Best Practices, and SEO \u2014 in structured batches.",
+    "risk": "safe",
+    "source": "personal",
+    "date_added": "2026-06-14",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "paid-ads",
     "path": "skills/paid-ads",
@@ -22680,6 +22878,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "patterns",
+    "path": "skills/monopoly/patterns",
+    "category": "monopoly",
+    "name": "patterns",
+    "description": "Reference document for monopoly patterns.",
+    "risk": "safe",
+    "source": "unknown",
+    "date_added": null,
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "payment-integration",
     "path": "skills/payment-integration",
@@ -25962,6 +26182,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "scale-benchmarks",
+    "path": "skills/monopoly/scale-benchmarks",
+    "category": "monopoly",
+    "name": "scale-benchmarks",
+    "description": "Reference document for monopoly scale-benchmarks.",
+    "risk": "safe",
+    "source": "unknown",
+    "date_added": null,
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "scanning-tools",
     "path": "skills/scanning-tools",
@@ -26314,6 +26556,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "security-checklist",
+    "path": "skills/monopoly/security-checklist",
+    "category": "monopoly",
+    "name": "security-checklist",
+    "description": "Reference document for monopoly security-checklist.",
+    "risk": "safe",
+    "source": "unknown",
+    "date_added": null,
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "security-compliance-compliance-check",
     "path": "skills/security-compliance-compliance-check",
@@ -27642,6 +27906,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "sharp-coder",
+    "path": "skills/sharp-coder",
+    "category": "uncategorized",
+    "name": "sharp-coder",
+    "description": "Two-layer performance skill combining disciplined THINK layer (surgical edits, simplicity) and terse SPEAK layer (caveman compression). Triggers on requests for brevity, token efficiency, or disciplined coding.\n",
+    "risk": "safe",
+    "source": "self",
+    "date_added": null,
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "sharp-edges",
     "path": "skills/sharp-edges",
@@ -29968,6 +30254,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "tech-matrix",
+    "path": "skills/monopoly/tech-matrix",
+    "category": "monopoly",
+    "name": "tech-matrix",
+    "description": "Reference document for monopoly tech-matrix.",
+    "risk": "safe",
+    "source": "unknown",
+    "date_added": null,
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "technical-change-tracker",
     "path": "skills/technical-change-tracker",
@@ -31584,20 +31892,22 @@
     "category": "development",
     "name": "unship",
     "description": "Compare AI agent-made UI variants locally in a real app, then keep one and clean up unused temporary code.",
-    "risk": "safe",
+    "risk": "critical",
     "source": "community",
     "date_added": "2026-06-07",
     "plugin": {
       "targets": {
-        "codex": "supported",
-        "claude": "supported"
+        "codex": "blocked",
+        "claude": "blocked"
       },
       "setup": {
         "type": "none",
         "summary": "",
         "docs": null
       },
-      "reasons": []
+      "reasons": [
+        "explicit_target_restriction"
+      ]
     }
   },
   {