tin-computer/tin/planned-content

Claude Code and agent skill by tin-computer/tin

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Compare current coverage, then draft useful, fact-grounded planned content.

Install

npx vskill@latest install tin-computer/tin/planned-content

SKILL.md

  1. Read the exact brief, buyer intent, action, destination and verification requirements in

the run context. Separate observed product facts from keyword opportunity hypotheses. content_draft.kind names an answer page (use the answer-page skill too) or a page refresh (use the page-refresh skill too); without it the item is an article.

  1. Read the project writing guide when present. Use its rhythm, structure and editorial

preferences without treating style as factual evidence. Explicit direction can refine expression but cannot override output ownership or invent claims.

  1. Inspect relevant durable context and current authoritative public sources. For existing

pages, understand their purpose before proposing replacement copy. Preserve supported capabilities and useful information; do not turn a documentation update into a sales essay.

  1. Compare actual current coverage, not merely matching keywords, to find what this page adds

for its reader. The brief is always drafted: existing coverage shapes the angle and the links, it never cancels the page. Record the reader gain and bounded change. Preserve unrelated page content on updates; a small addition never licenses deleting the rest of the API reference. Never replace one planned item with another inside this run.

  1. Develop one clear contribution for the buyer. Prefer concrete mechanisms and examples to

promotional claims. Mark hypothetical examples as hypothetical. Avoid repetitive SEO introductions, keyword stuffing, invented experience and unsupported promises.

  1. Edit the draft for clarity, transitions, useful headings and a proportionate conclusion.

Cite factual claims near the supporting links. Sources that merely mention a topic do not establish product behavior, pricing or outcomes.

  1. Keep the article clean. Put source frontmatter, editorial judgment and requirement accounting in the separate

generation-notes file. Missing factual evidence means omitting or qualifying claims, not inventing them or starting an unbounded research loop. Live product testing is outside this writing workflow: no credentials, accounts, registration or real sends. Carry even explicit live-test requests in older briefs as optional follow-ups, not draft blockers. Distinguish documentation-grounded examples and local checks from examples actually executed live. Review concerns article copy only. The companion notes are available as internal context.

Before broad research, inspect the exact destination and nearest competing page, so the draft adds to them rather than repeating them. Save an argument outline in the declared generation-notes file before writing: buyer decision, direct answer, the project's positioning (from the files in content_draft.positioning, never the plan's), proof, objection, next step. Use that outline to remove tangents. Reuse verified project evidence and read focused excerpts before whole files. Record dated official competitor facts in the notes. Compare total costs on like-for-like usage and distinguish customer-owned from provider-operated hardware. Never infer missing capability from silence. Keep notes and process details outside customer-facing copy.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/tin-computer/tin/planned-content/badge)](https://verified-skill.com/skills/tin-computer/tin/planned-content)

Something wrong with this skill or its page? Tell us.