Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/carloshpdoc-knowledge
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
knowledge- Description
- None
- License
- Apache-2.0
- Instructions
- 258 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- invalid YAML frontmatter: Nested mappings are not allowed in compact mappings at line 2, column 14:
- name: missing
- description: missing
- body: contains an absolute path from the author's machine
Files (1)
- SKILL.md
SKILL.md (first lines)
# /knowledge — federa busca + lifecycle em docs `.md` Voce eh um "bibliotecario" pros docs `.md` do usuario. Tres fontes: 1. **`~/Desktop/knowledge/`** — cross-cutting docs (ideias, playbooks, audits, learnings) 2. **Repo do projeto atual** — `find . -name "*.md" -not -path "*/node_modules/*"` (cwd atual) 3. **Memory do Claude** — `~/.claude/projects/<projeto>/memory/` se aplicavel ## Subcomandos `$1` define o que fazer. Se vazio, default eh `index`. ### `/knowledge index` (default) Imprime visao organizada de tudo. Format: ``` Knowledge base summary ====================== CENTRAL (~/Desktop/knowledge/) - ideas/ (N docs, X stale) - playbooks/ (N docs) - audits/ (N docs, X stale) - learnings/ (N docs) - archive/ (N docs) PROJECT (cwd) - doc1.md (last_review: 2026-05-17, status: active) - doc2.md (last_review: 2026-04-12, STALE) ... MEMORY (~/.claude/projects/.../memory) - memory1.md (type: feedback) - memory2.md (type: project) CONTENT DRAFTS - 2026-05-17-claude-mcp-bigquery-ga4/ (4 platforms, status: drafted) - ... ``` Format limpo, ordenado, status visiveis. Maximo ~50 linhas — se passar, agrupa por tag. ### `/knowledge stale [days]` Lista docs onde `last_review` > N dias atras (default 60). Para cada `.md` em todas as fontes: 1. Le frontmatter, extrai `last_review` (ou usa file mtime se frontmatter ausente) 2. Calcula dias desde ultima review 3. Se > threshold, inclui na lista 4. Ordena por staleness (mais velho primeiro) Output: ``` Docs stale (last_review > 60 dias): 1. ~/Desktop/knowledge/audits/ga4-audit-2025-q4.md last_review: 2025-11-20 (178 dias atras) tags: [analytics, ga4] sugestao: re-validar com dado atual ou archive 2. /Users/.../mysite/PORTFOLIO_STRUCTURE_RESEARCH.md last_review: ausente, mtime: 2026-02-10 (96 dias atras) sugestao: adicionar frontmatter ou archive ``` ### `/knowledge drafts` Lista content drafts nao publicados. Scaneia `<project>/content/drafts/` no repo atual. Pra cada subdir: - Le os 4 .md (linkedin/twitter/instagram/article) - Checa se tem checklist `[x]` indicando posted ou se ainda esta `[ ]` - Lista grouped por status Output: ``` Content drafts: UNPOSTED (todas checkboxes pendentes) - 2026-05-17-claude-mcp-bigquery-ga4/ (4 platforms) - 2026-05-17-site-audit-bot-discovery/ (4 platforms) - 2026-05-17-claude-content-machine/ (4 platforms) PARTIALLY POSTED (nenhum) POSTED (>=1 checkbox checked) (nenhum) ``` ### `/knowledge related <topico>` Faz grep semântico atraves de todas as fontes. Procura `<topico>` em: - Frontmatter tags - Titulos H1/H2 - Body content (ranqueado por densidade) Retorna lista ordenada por relevancia (max 10). Output: ``` Docs relacionados a "analytics": [CENTRAL/audits] ga4-audit-2025-q4.md (5 hits) [PROJECT] ENGAGEMENT_AUDIT.md (12 hits, recent) [PROJECT] ANALYTICS_CLEANUP.md (8 hits, recent) [PROJECT] ANALYTICS_DB_SETUP.md (6 hits, recent) [PROJECT] MCP_ANALYTICS_SETUP.md (4 hits, recent) [MEMORY] skill-content.md (1 hit) ``` Se 0 resultados, sugere criar novo: "Nenhum doc sobre 'X'. Quer criar um com `/knowledge new`?" ### `/knowledge suggest` Modo proativo: analisa o que foi trabalhado na sessao atual (git diff recente, commits, arquivos modificados) e sugere docs existentes relacionados.
From carloshpdoc/ios-workflow-claude, Apache-2.0.
More from carloshpdoc/ios-workflow-claude
- 0.539score
xcode-build-benchmark
carloshpdoc
Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts.
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
xcode-compilation-analyzer
carloshpdoc
Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level…
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
spm-build-analysis
carloshpdoc
Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode builds.
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
xcode-project-analyzer
carloshpdoc
Audit Xcode project configuration, build settings, scheme behavior, and script phases to find build-time improvements with explicit approval gates.
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
xcode-build-fixer
carloshpdoc
Implement approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement.
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
xcode-build-orchestrator
carloshpdoc
Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval…
SkillCFreshness: C★ 7Claude Code +9 - 0.534score
create-tasks
carloshpdoc
Creates Jira tasks from meeting notes, specs, or feature descriptions.
SkillCFreshness: C★ 7Claude Code +9 - 0.523score
local-smart
carloshpdoc
Use o executor local inteligente (dots.llm1) para tarefas que exigem reasoning mais forte
SkillCFreshness: C★ 7Claude Code +9 - 0.523score
local-fast
carloshpdoc
Use o executor local rápido (Qwen3.5 35B A3B) para tarefas de baixo risco e baixo custo
SkillCFreshness: C★ 7Claude Code +9 - 0.286score
content
carloshpdoc
No description from the publisher yet.
SkillCFreshness: C★ 7Claude Code +9
Signals
- Stars
- 7
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jun 8, 2026 (4 months ago)
- Last release
- May 23, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from carloshpdoc
- 0.539score
xcode-build-benchmark
carloshpdoc
Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts.
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
xcode-compilation-analyzer
carloshpdoc
Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level…
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
spm-build-analysis
carloshpdoc
Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode builds.
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
xcode-project-analyzer
carloshpdoc
Audit Xcode project configuration, build settings, scheme behavior, and script phases to find build-time improvements with explicit approval gates.
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
xcode-build-fixer
carloshpdoc
Implement approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement.
SkillCFreshness: C★ 7Claude Code +9 - 0.539score
xcode-build-orchestrator
carloshpdoc
Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval…
SkillCFreshness: C★ 7Claude Code +9
Cite this page
knowledge skill. Agent Mart. https://agentmart.dev/skills/carloshpdoc-knowledge (last updated 2026-10-24)