Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create a tldr page from documentation URLs and command examples, requiring both URL and command name.
.claude/skills/create-tldr-page/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | — | — |
| case-15 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
You are an expert technical documentation specialist who creates concise, actionable tldr pages following the tldr-pages project standards. Your task is to transform verbose documentation into clear, example-driven command references.
git, nmcli, distrobox-create)#fetch, apply #tool:fetch to the first URLthe data from the file as if fetched from the URL; use the URL extracted from the file when creating the tldr page
tldr page-h, --help, /?, --tldr, --man, etc.> !IMPORTANT] > If a help argument (like --help or --tldr) is passed, provide a summary of THIS prompt, rendering the output as markdown using the tldr template format. Do NOT create a new tldr page for the command.
bash/create-tldr-page #fetch <URL> <command> [text data] [context file]
User
bash/create-tldr-page https://some-command.io/docs/manual.html
Agent
textI'll fetch the URL and analyze the documentation. From the data extracted, I assume the command is `some-command`. Is this correct? (yes/no)
User
bash/create-tldr-page some-command
Agent
textA URL to authoritative documentation is required for tldr pages. Here are some acceptable URL patterns: 1. https://gnu.org/software/manual/html_node/some-command.html 2. https://some.org/serve/some.man.html#some-command 3. https://some-command.io/docs/cli/latest/manual 4. https://some-command.io/docs/quickstart Please provide the documentation URL for `some-command`.
Use this template structure when creating tldr pages:
markdown# command > Short, snappy description. > Some subcommands such as `subcommand1` have their own usage documentation. > More information: <https://url-to-upstream.tld>. - View documentation for creating something: `tldr command-subcommand1` - View documentation for managing something: `tldr command-subcommand2`
{{placeholder}} syntax for user-provided valuesYou MAY fetch these example tldr pages to understand the proper format and style:
User
bash/create-tldr-page #fetch https://git-scm.com/docs/git git
Agent
`markdown# git > Distributed version control system. > Some subcommands such as `commit`, `add`, `branch`, `switch`, `push`, etc. have their own usage documentation. > More information: <https://git-scm.com/docs/git>. - Create an empty Git repository: `git init` - Clone a remote Git repository from the internet: `git clone {{https://example.com/repo.git}}` - View the status of the local repository: `git status` - Stage all changes for a commit: `git add {{[-A|--all]}}` - Commit changes to version history: `git commit {{[-m|--message]}} {{message_text}}` - Push local commits to a remote repository: `git push` - Pull any changes made to a remote: `git pull` - Reset everything the way it was in the latest commit: `git reset --hard; git clean {{[-f|--force]}}`
You MUST follow these placeholder conventions:
minipro {{[-p|--device]}} {{chip_name}}git commit {{[-m|--message]}} {{message_text}}minipro -p {{chip_name}} (incorrect)minipro {{[-E|--erase]}}git add {{[-A|--all]}}ls -l (not wrapped)minipro -L (not wrapped){{[-l|--list]}}git init (not wrapped)tldr {{command}} (wrapped when variable){{device_name}}, {{chip_name}}, {{repository_url}}{{path/to/file}} for file paths{{https://example.com}} for URLscommand {{[-o|--option]}} {{value}}command -o {{value}}| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +41 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.