cf-help
starsforks
How to install cf-help?
indranilbanerjee/contentforge/cf-help
$npx -y skills add indranilbanerjee/contentforge --skill cf-helpShow the ContentForge user guide, available skills, pipeline overview, examples, and troubleshooting
SKILL.md
| 1 | # /contentforge:cf-help |
| 2 | |
| 3 | Show the ContentForge user guide with live plugin state (version, asset counts, connector counts, runtime environment) pulled from disk — not hardcoded — plus pipeline overview, available skills, usage examples, and troubleshooting. |
| 4 | |
| 5 | ## CRITICAL: never hardcode version, asset counts, or connector counts |
| 6 | |
| 7 | Versions and counts in this plugin used to be baked into this skill body as |
| 8 | literal version strings and count strings ("Agents: 13 · Skills: 19 · |
| 9 | Connectors: 9 HTTP + 19 npx"). Those drifted out of sync with the actual |
| 10 | install every release (reported by users in v3.12.7 testing: "I'm on 3.12.7, |
| 11 | but the help output shows an old version"). |
| 12 | |
| 13 | **Always read live values from `scripts/plugin-metadata.py`. Never quote a |
| 14 | version number, skill count, agent count, or connector count from memory or |
| 15 | from this skill body.** |
| 16 | |
| 17 | ## Behavior |
| 18 | |
| 19 | ### Step 1 — Fetch live plugin metadata |
| 20 | |
| 21 | Run **first**, every time this skill is invoked (any argument or none): |
| 22 | |
| 23 | ```bash |
| 24 | python scripts/plugin-metadata.py --section all-with-environment |
| 25 | ``` |
| 26 | |
| 27 | This returns JSON with `version`, `assets` (agent/skill/command/script counts), |
| 28 | `connectors` (HTTP + npx counts), `skills` list, `commands` list, |
| 29 | `pipeline_phases` list (read from agent file names), and `environment` |
| 30 | (detects Cowork sandbox vs local Claude Code, with a warning if filesystem |
| 31 | writes won't reach the user's host). |
| 32 | |
| 33 | Substitute the values from this JSON into every place the help output |
| 34 | references a count, a version, or a slash-command list. Do **not** invent |
| 35 | or quote numbers from elsewhere. |
| 36 | |
| 37 | ### Step 2 — Default rendering (no args) |
| 38 | |
| 39 | Render a clean help overview using the live data. Suggested format: |
| 40 | |
| 41 | ``` |
| 42 | === CONTENTFORGE === |
| 43 | Version: <version from JSON> |
| 44 | Agents: <agents> | Skills: <skills_total> | Commands: <commands> | Scripts: <scripts> |
| 45 | Connectors: <available_http> HTTP + <available_npx> npx available |
| 46 | (<active_count> currently active in your .mcp.json) |
| 47 | Cowork-compatible: <cowork_compatible_count> (HTTP only — npx connectors don't run in Cowork) |
| 48 | Environment: <environment from JSON> |
| 49 | <if environment.cowork_warning is non-null, show it as a WARNING block> |
| 50 | |
| 51 | Getting Started: |
| 52 | 1. /contentforge:brand-setup -- Configure brand voice, terminology, guardrails |
| 53 | 2. /contentforge:cf-integrations -- See which connectors are active |
| 54 | 3. /contentforge:create-content -- Run the full content pipeline |
| 55 | 4. /contentforge:cf-help --examples -- Worked example workflows |
| 56 | ``` |
| 57 | |
| 58 | ### Step 3 — Cowork warning (when applicable) |
| 59 | |
| 60 | If `environment.cowork_warning` is non-null, surface it prominently after |
| 61 | the orientation block: |
| 62 | |
| 63 | ``` |
| 64 | ⚠ COWORK SANDBOX DETECTED |
| 65 | <cowork_warning text from JSON> |
| 66 | |
| 67 | What this means in practice: |
| 68 | - File writes to ~/Documents/ContentForge/ and ~/.claude-marketing/ |
| 69 | land inside the sandbox, NOT on your Windows / macOS host |
| 70 | - Files persist only for this Cowork session |
| 71 | - The full /contentforge:create-content pipeline can run, but the |
| 72 | dual-copy save and per-phase checkpointing target the sandbox FS |
| 73 | - For full host-filesystem behavior, run ContentForge in local |
| 74 | Claude Code (CLI or VS Code / JetBrains IDE extension) instead |
| 75 | ``` |
| 76 | |
| 77 | ### Step 4 — Argument routing |
| 78 | |
| 79 | | Argument | What to render | |
| 80 | |----------|---------------| |
| 81 | | (none) | Steps 2 + 3 + Quick command list | |
| 82 | | `--pipeline` | Steps 2 + 3 + full phase-by-phase overview (use `pipeline_phases` from JSON) | |
| 83 | | `--skills` | Steps 2 + 3 + list every skill from JSON `skills` array with slash command + description | |
| 84 | | `--commands` | Steps 2 + 3 + list every command from JSON `commands` array with slash command + description | |
| 85 | | `--connectors` | Steps 2 + 3 + redirect: "For active/available connector status, run /contentforge:cf-integrations" | |
| 86 | | `--examples` | Steps 2 + 3 + the worked-example workflows (see below) | |
| 87 | | `--troubleshoot` | Steps 2 + 3 + troubleshooting matrix (see below) | |
| 88 | | `--brand` | Steps 2 + 3 + brand setup methods (see below) | |
| 89 | |
| 90 | When rendering the skills/commands list, **iterate over the JSON arrays** — |
| 91 | do not paste a hand-maintained list. Each row should show the |
| 92 | `slash_command` field as the user-facing label and the `description` field |
| 93 | as the explanation. |
| 94 | |
| 95 | ### Pipeline phase rendering (--pipeline) |
| 96 | |
| 97 | The pipeline phases come from agent file names (`01-researcher.md` → |
| 98 | "Phase 01: Researcher"). Iterate `pipeline_phases` from the JSON and render |
| 99 | phase + role + description. Add this preamble: |
| 100 | |
| 101 | ``` |
| 102 | === CONTENTFORGE PIPELINE (10 phases) === |
| 103 | Step 0.5: Title Curation runs BEFORE Phase 1 (SERP recon + 4-5 SEO title options; |
| 104 | user selects before draft starts). |
| 105 | |
| 106 | Quality gates: composite score >=7.0 to pass | max 2 loops per phase | |
| 107 | 3-layer verification (Fact Checker -> Scientific Validator -> Reviewer). |
| 108 | ``` |
| 109 | |
| 110 | Then lis |
People who liked this also viewed
6 picksType
- seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026
- copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026
- marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026
- content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026
- programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026
- marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026
