opencode-skills-collection 4.1.2 → 4.1.3

package/bundled-skills/tech-writing-proofread/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: tech-writing-proofread
+description: "Proofreads English technical writing for typos, grammar, punctuation, terminology consistency, jargon, and structure; returns an itemized Original → Suggestion → Reason list without rewriting the document. Use when asked to proofread or polish a technical doc, README, or blog draft."
+category: writing
+risk: safe
+source: https://github.com/alapha888/agent-skills-en
+source_repo: alapha888/agent-skills-en
+source_type: community
+date_added: "2026-10-01"
+author: alapha888
+tags: [proofreading, technical-writing, editing]
+tools: [claude, cursor, gemini, codex]
+license: MIT
+license_source: https://github.com/alapha888/agent-skills-en/blob/main/LICENSE
+---
+
+# Technical Writing Proofreading
+
+Take an English technical document from "understandable" to "publishable." Proofread only — never rewrite content. Flag suspected factual errors; do not silently fix them.
+
+## When to Use
+
+- Use when the user asks to proofread, polish, or review an English technical doc, README, or blog draft.
+- Use when terminology consistency or jargon needs checking across a document.
+
+## Workflow
+
+1. **Read for tone first**: Read the whole document and identify its type (tutorial / API reference / blog post / README). Tutorials tolerate a conversational voice; API references must be precise.
+2. **Build a terminology list**: Scan for key terms (e.g. "callback" vs "callback function", "sign in" vs "log in") and check whether one concept is named several ways. Standardize on the most frequent form and note it in the checklist.
+3. **Check paragraph by paragraph**, but only for these six categories — do not drift into "is this paragraph well written":
+   - Typos and spelling: transposed letters, doubled words ("the the"), commonly confused pairs ("affect/effect", "its/it's", "complement/compliment").
+   - Grammar: subject-verb agreement, verb tense consistency within a procedure, dangling modifiers, missing articles before singular countable nouns.
+   - Punctuation: consistent serial (Oxford) comma usage; hyphens in compound adjectives ("command-line tool"); no double spaces after periods; consistent use of em dashes vs parentheses.
+   - Inline code and proper nouns: inline code, commands, file names, and paths in backticks; proper nouns in their official casing (`GitHub`, not `github`; `JavaScript`, not `Javascript`).
+   - Sentence style: prefer active voice ("The system calls the function" over "The function is called by the system"); cut filler ("basically", "simply", "just", "very"); one idea per sentence.
+   - Structure: headings in parallel form; lists use parallel items; steps in a procedure are imperative and numbered; acronyms are expanded on first use.
+4. **Output the checklist**: list items as "Original → Suggestion → Reason", with line numbers or short quotes. Mark uncertain items `[verify]` instead of forcing a change.
+5. **Close with statistics**: N items total, of which typos x, grammar y, terminology z, style w — so the author sees the distribution at a glance.
+
+## Rules
+
+- Fix language, not facts. A suspected factual error becomes `[verify] This contradicts the usual definition — please confirm`, never a silent "correction."
+- Do not rewrite whole paragraphs. Even a wordy paragraph gets only specific, fixable sentences flagged; keep the author's voice.
+- One pass only. Do not keep "polishing another round" — the deliverable is a "no-defects" checklist, not a perfect text.
+
+## Minimal example
+
+Input snippet:
+
+```text
+This function will be called by the system after the data is ready, you can use it to basically handle the registration of the callback, the timeout is 5 s, examples on github can be referenced.
+```
+
+Output checklist:
+
+```text
+1. [Style] "will be called by the system" → "the system calls" (passive → active)
+2. [Style] "basically handle" → "handle" (cut filler word)
+3. [Terminology] "callback" — if written elsewhere as "callback function", unify on one form (most frequent wins)
+4. [Grammar] run-on sentence: split after "ready." into two sentences
+5. [Proper noun] "github" → "GitHub" (official casing)
+
+Statistics: 5 items — style 2, terminology 1, grammar 1, proper noun 1.
+```
+
+## Limitations
+
+- Proofreads; it does not rewrite. Voice, structure and argument are preserved, so a document that is poorly argued stays poorly argued after review.
+- The technical claims themselves are out of scope: an uncertain statement is left intact rather than silently "corrected" into a different fact.
+- Terminology consistency is judged against the document's own dominant usage, not against an external glossary unless the user supplies one.
+- Only English proofreading is claimed. Other languages, translation quality and localisation review are outside this skill.
+
+## Anti-patterns
+
+- ❌ Turning proofreading into rewriting: tearing a paragraph down so the author's voice and structure are lost.
+- ❌ Hallucinated "corrections": changing an uncertain technical statement as if it were a typo, introducing a factual error.
+- ❌ Typos-only checks: inconsistent terminology and sloppy structure are the real defects in technical docs.
+- ❌ Endless iteration: the user says "polish it once more" and it never ends — the deliverable is the checklist, not a perfect text.

package/bundled-skills/typescript-expert/scripts/ts_diagnostic.py

@@ -10,21 +10,42 @@ import os
 import json
 from pathlib import Path
 
-def run_cmd(cmd: str) -> str:
-    """Run shell command and return output."""
+def run_cmd(args):
+    """Run a command as an argument list (no shell) and return its output."""
     try:
-        result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
+        result = subprocess.run(args, capture_output=True, text=True)
         return result.stdout + result.stderr
     except Exception as e:
         return str(e)
 
+def grep_source_count(pattern: str, exclude: str | None = None) -> tuple[int, list[str]]:
+    """Count and sample lines containing ``pattern`` under ``src/``.
+
+    Pure-Python replacement for ``grep -r ... src/`` so no shell is involved.
+    """
+    root = Path("src")
+    if not root.is_dir():
+        return 0, []
+    matches: list[str] = []
+    for path in sorted(root.rglob("*")):
+        if path.suffix not in (".ts", ".tsx") or not path.is_file():
+            continue
+        try:
+            text = path.read_text(encoding="utf-8", errors="replace")
+        except OSError:
+            continue
+        for lineno, line in enumerate(text.splitlines(), start=1):
+            if pattern in line and (exclude is None or exclude not in line):
+                matches.append(f"{path}:{lineno}:{line}")
+    return len(matches), matches
+
 def check_versions():
     """Check TypeScript and Node versions."""
     print("\n📦 Versions:")
     print("-" * 40)
     
-    ts_version = run_cmd("npx tsc --version 2>/dev/null").strip()
-    node_version = run_cmd("node -v 2>/dev/null").strip()
+    ts_version = run_cmd(["npx", "tsc", "--version"]).strip()
+    node_version = run_cmd(["node", "-v"]).strip()
     
     print(f"  TypeScript: {ts_version or 'Not found'}")
     print(f"  Node.js: {node_version or 'Not found'}")
@@ -134,11 +155,12 @@ def check_type_errors():
     print("\n🔍 Type Check:")
     print("-" * 40)
     
-    result = run_cmd("npx tsc --noEmit 2>&1 | head -20")
+    result = run_cmd(["npx", "tsc", "--noEmit"])
+    lines = result.splitlines()
     if "error TS" in result:
         errors = result.count("error TS")
         print(f"  ❌ {errors}+ type errors found")
-        print(result[:500])
+        print("\n".join(lines[:20])[:500])
     else:
         print("  ✅ No type errors")
 
@@ -147,13 +169,11 @@ def check_any_usage():
     print("\n⚠️ 'any' Type Usage:")
     print("-" * 40)
     
-    result = run_cmd("grep -r ': any' --include='*.ts' --include='*.tsx' src/ 2>/dev/null | wc -l")
-    count = result.strip()
-    if count and count != "0":
+    count, matches = grep_source_count(": any")
+    if count:
         print(f"  ⚠️ Found {count} occurrences of ': any'")
-        sample = run_cmd("grep -rn ': any' --include='*.ts' --include='*.tsx' src/ 2>/dev/null | head -5")
-        if sample:
-            print(sample)
+        if matches:
+            print("\n".join(matches[:5]))
     else:
         print("  ✅ No explicit 'any' types found")
 
@@ -162,9 +182,8 @@ def check_type_assertions():
     print("\n⚠️ Type Assertions (as):")
     print("-" * 40)
     
-    result = run_cmd("grep -r ' as ' --include='*.ts' --include='*.tsx' src/ 2>/dev/null | grep -v 'import' | wc -l")
-    count = result.strip()
-    if count and count != "0":
+    count, _ = grep_source_count(" as ", exclude="import")
+    if count:
         print(f"  ⚠️ Found {count} type assertions")
     else:
         print("  ✅ No type assertions found")
@@ -174,9 +193,11 @@ def check_performance():
     print("\n⏱️ Type Check Performance:")
     print("-" * 40)
     
-    result = run_cmd("npx tsc --extendedDiagnostics --noEmit 2>&1 | grep -E 'Check time|Files:|Lines:|Nodes:'")
-    if result.strip():
-        for line in result.strip().split('\n'):
+    result = run_cmd(["npx", "tsc", "--extendedDiagnostics", "--noEmit"])
+    keys = ("Check time", "Files:", "Lines:", "Nodes:")
+    lines = [line for line in result.splitlines() if any(k in line for k in keys)]
+    if lines:
+        for line in lines:
             print(f"  {line}")
     else:
         print("  ⚠️ Could not measure performance")

package/bundled-skills/youtube-summarizer/SKILL.md

@@ -312,10 +312,10 @@ echo "[████████████████████] 100% - Step
 ```markdown
 # [Video Title]
 
-**Canal:** [Channel Name]  
-**Duração:** [Duration]  
+**Channel:** [Channel Name]  
+**Duration:** [Duration]  
 **URL:** [https://youtube.com/watch?v=VIDEO_ID]  
-**Data de Publicação:** [Date if available]
+**Published:** [Date if available]
 
 
 ## 📝 Detailed Summary

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-collection",
-  "version": "4.1.2",
+  "version": "4.1.3",
   "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

@@ -18860,6 +18860,37 @@
       "reasons": []
     }
   },
+  {
+    "id": "deep-research-framework",
+    "path": "skills/deep-research-framework",
+    "category": "research",
+    "name": "deep-research-framework",
+    "description": "Framework for deep research reports: define the question and tier sources first, cross-verify, then write conclusion-first reports with explicit uncertainty statements. Use when the user asks for a research report, topic investigation, or competitive analysis.",
+    "risk": "safe",
+    "source": "https://github.com/alapha888/agent-skills-en",
+    "date_added": "2026-10-01",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "community",
+    "source_repo": "alapha888/agent-skills-en",
+    "license": "MIT",
+    "license_source": "https://github.com/alapha888/agent-skills-en/blob/main/LICENSE",
+    "tags": [
+      "research-reports",
+      "source-verification",
+      "analysis"
+    ]
+  },
   {
     "id": "deepapi",
     "path": "skills/deepapi",
@@ -24612,6 +24643,37 @@
       "reasons": []
     }
   },
+  {
+    "id": "five-axis-code-review",
+    "path": "skills/five-axis-code-review",
+    "category": "development",
+    "name": "five-axis-code-review",
+    "description": "Five-axis code review checklist (correctness, security, readability, performance, test coverage) producing actionable comments instead of style nitpicks. Use when the user asks to review code, a diff, or a pull request.",
+    "risk": "safe",
+    "source": "https://github.com/alapha888/agent-skills-en",
+    "date_added": "2026-10-01",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "community",
+    "source_repo": "alapha888/agent-skills-en",
+    "license": "MIT",
+    "license_source": "https://github.com/alapha888/agent-skills-en/blob/main/LICENSE",
+    "tags": [
+      "code-review",
+      "code-quality",
+      "pull-requests"
+    ]
+  },
   {
     "id": "fix-review",
     "path": "skills/fix-review",
@@ -27412,6 +27474,37 @@
       "reasons": []
     }
   },
+  {
+    "id": "git-commit-message",
+    "path": "skills/git-commit-message",
+    "category": "development",
+    "name": "git-commit-message",
+    "description": "Generates conventional-commit messages from staged changes: type prefix + English imperative subject (≤50 chars) + optional body explaining why. Use when the user asks to write, generate, or polish a git commit message.",
+    "risk": "safe",
+    "source": "https://github.com/alapha888/agent-skills-en",
+    "date_added": "2026-10-01",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "community",
+    "source_repo": "alapha888/agent-skills-en",
+    "license": "MIT",
+    "license_source": "https://github.com/alapha888/agent-skills-en/blob/main/LICENSE",
+    "tags": [
+      "git",
+      "commit-messages",
+      "conventional-commits"
+    ]
+  },
   {
     "id": "git-hooks-automation",
     "path": "skills/git-hooks-automation",
@@ -32197,6 +32290,41 @@
     "license": "MIT",
     "license_source": "https://github.com/addyosmani/agent-skills/blob/main/LICENSE"
   },
+  {
+    "id": "idea-to-blueprint",
+    "path": "skills/idea-to-blueprint",
+    "category": "planning",
+    "name": "idea-to-blueprint",
+    "description": "Turn a raw product, app, bot or feature idea into one evidence-backed build blueprint (researched stack, epics, Given/When/Then criteria, tests) that coding agents build one epic per session.",
+    "risk": "safe",
+    "source": "self",
+    "date_added": "2026-09-30",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "self",
+    "source_repo": "iniesohidham/idea-to-blueprint",
+    "license": "MIT",
+    "license_source": "https://github.com/iniesohidham/idea-to-blueprint/blob/main/LICENSE",
+    "tags": [
+      "prd",
+      "specification",
+      "product-planning",
+      "user-stories",
+      "acceptance-criteria",
+      "tech-stack",
+      "agentic-engineering"
+    ]
+  },
   {
     "id": "identity-access-management",
     "path": "skills/identity-access-management",
@@ -39115,6 +39243,37 @@
       "corporate"
     ]
   },
+  {
+    "id": "meeting-notes",
+    "path": "skills/meeting-notes",
+    "category": "productivity",
+    "name": "meeting-notes",
+    "description": "Turns raw meeting notes into structured minutes: conclusion first, then decisions / action items / open questions; every action item must have an owner and a deadline. Use when the user pastes meeting transcripts or rough notes and asks for minutes or a summary.",
+    "risk": "safe",
+    "source": "https://github.com/alapha888/agent-skills-en",
+    "date_added": "2026-10-01",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "community",
+    "source_repo": "alapha888/agent-skills-en",
+    "license": "MIT",
+    "license_source": "https://github.com/alapha888/agent-skills-en/blob/main/LICENSE",
+    "tags": [
+      "meetings",
+      "minutes",
+      "action-items"
+    ]
+  },
   {
     "id": "meme-coin-audit",
     "path": "skills/meme-coin-audit",
@@ -50176,6 +50335,38 @@
       "reasons": []
     }
   },
+  {
+    "id": "repo-foundation",
+    "path": "skills/repo-foundation",
+    "category": "development",
+    "name": "repo-foundation",
+    "description": "Implement features, fixes, modules, contract migrations, and resumed work while preserving user edits and authorized public contracts.",
+    "risk": "critical",
+    "source": "https://github.com/Natchannnn/repository-engineering-skills",
+    "date_added": "2026-09-30",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "community",
+    "source_repo": "Natchannnn/repository-engineering-skills",
+    "license": "MIT",
+    "license_source": "https://github.com/Natchannnn/repository-engineering-skills/blob/e55b378158d5134a77af3b8dace4a2a1b17e41e2/LICENSE",
+    "tags": [
+      "repository-engineering",
+      "feature-development",
+      "contract-migration",
+      "continuity"
+    ]
+  },
   {
     "id": "repo-maintainer",
     "path": "skills/repo-maintainer",
@@ -50202,6 +50393,38 @@
     "license": "MIT",
     "license_source": "https://github.com/Wolfe-Jam/faf-skills/blob/main/LICENSE"
   },
+  {
+    "id": "repo-native-refactor",
+    "path": "skills/repo-native-refactor",
+    "category": "development",
+    "name": "repo-native-refactor",
+    "description": "Review diffs without editing, or perform evidence-based cleanup while preserving authorized behavior, public contracts, and domain ownership.",
+    "risk": "critical",
+    "source": "https://github.com/Natchannnn/repository-engineering-skills",
+    "date_added": "2026-09-30",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "community",
+    "source_repo": "Natchannnn/repository-engineering-skills",
+    "license": "MIT",
+    "license_source": "https://github.com/Natchannnn/repository-engineering-skills/blob/e55b378158d5134a77af3b8dace4a2a1b17e41e2/LICENSE",
+    "tags": [
+      "repository-engineering",
+      "code-review",
+      "refactoring",
+      "public-contracts"
+    ]
+  },
   {
     "id": "report-writing",
     "path": "skills/report-writing",
@@ -58067,6 +58290,37 @@
       "reasons": []
     }
   },
+  {
+    "id": "tech-writing-proofread",
+    "path": "skills/tech-writing-proofread",
+    "category": "writing",
+    "name": "tech-writing-proofread",
+    "description": "Proofreads English technical writing for typos, grammar, punctuation, terminology consistency, jargon, and structure; returns an itemized Original → Suggestion → Reason list without rewriting the document. Use when asked to proofread or polish a technical doc, README, or blog draft.",
+    "risk": "safe",
+    "source": "https://github.com/alapha888/agent-skills-en",
+    "date_added": "2026-10-01",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "community",
+    "source_repo": "alapha888/agent-skills-en",
+    "license": "MIT",
+    "license_source": "https://github.com/alapha888/agent-skills-en/blob/main/LICENSE",
+    "tags": [
+      "proofreading",
+      "technical-writing",
+      "editing"
+    ]
+  },
   {
     "id": "technical-change-tracker",
     "path": "skills/technical-change-tracker",