Menu
Reduces a target to the tip of the inverted pyramid: its core conclusion in a short paragraph, dropping supporting detail and reasoning, then tightened to the fewest words.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Computes the optimal Claude usage-window ping schedule from work hours and creates or reconciles the scheduled cloud routines that pin the window boundaries.
Reviews changes to prose files (markdown, text, blog posts, docs). Focuses on voice, grammar, factual claims, dead links, and structure. Loads the project's voice or style guide when one exists. Skips linter and Actions hash verification.
Full code review for large or security-sensitive changes. Gathers requirements first, loads all relevant language references, runs the linter where applicable, applies the full review checklist with security as the top priority.
Reviews infrastructure changes: GitHub Actions workflows, Terraform, Dockerfiles, docker-compose, IaC. Focuses on supply-chain pinning, secret handling, least-privilege permissions, action versions, and CI failure modes. Always verifies action hash pins when present.
Abbreviated code review for small or low-stakes code changes. Skips requirements gathering. Skips the linter in PR mode (CI runs it). Focuses on correctness against obvious intent, readability, and pattern consistency. For large or security-sensitive diffs, use code-review-deep instead.
Orchestrator. Triages a PR, local diff, patch file, or staged/branch changes into one of four review types (content, code-lite, code-deep, infra) and dispatches to the matching child skill. Use this when you don't already know which depth or type of review you want. For a known type, invoke the child skill directly.
| name | tldr |
| description | Reduces a target to the tip of the inverted pyramid: its core conclusion in a short paragraph, dropping supporting detail and reasoning, then tightened to the fewest words. |
| when_to_use | Use when the user invokes /tldr, or asks for the tip, lede, or bottom line of something, or to compress, distil, or shorten a block of text or a prior reply to its core point (e.g. 'tldr it', 'tldr this', 'give me the gist', 'in short', 'just the conclusion', 'bottom line'). This is an on-demand pass on a specific target that drops elaboration by design. Do NOT use to set ongoing output style; that belongs in standing instructions (CLAUDE.md). Follow all steps in order; do not shortcut based on this description. |
| argument-hint | [optional: text or target to reduce; defaults to the preceding reply] |
The target is, in priority order: (a) text or a reference passed as an argument; (b) a specific block the user named ("tldr the second paragraph"); or (c) the immediately preceding reply if nothing is specified. If the target is ambiguous, ask which block. Do not guess.
Find the single core conclusion or answer, the one thing the reader needs. Drop everything below it in the pyramid: reasoning, justification, elaboration, examples, and background. Drop any caveat that does not change the conclusion; keep one only if its removal would mislead. The result is a short paragraph, the lede, not a recap of the whole.
On that paragraph, strip words to the minimum:
Full grammatical sentences. No telegraphic fragments, headline style, or clipped parallel clauses. Keep subjects, articles, and pronouns ("I worked on it," not "Worked on it"), and use full words, not slang or abbreviations. Density comes from dropping detail and redundant words, not from breaking syntax.
Emit the core point and nothing else: no reasoning, no "here's why," no supporting detail, no preamble or label, no closing offer. If the reader wants the rest, they will ask.
Example:
The tip keeps the conclusion and drops the comparison of options, while staying a full sentence.
