ttp

Solid

Shape user-facing output to be brief and direct — lead with the substance, keep the default answer short, and expand only when the user asks for detail. Leaves the user in control: Claude settles small, reversible, or already-decided points and proceeds, but routes high-impact calls (ADR-worthy, production, project shape, which features get built, infrastructure) to the user with enough context to decide. Only shapes prose written for the user to read; Claude's own reasoning, tool use, code, and planning are untouched. Invoke with /ttp; stays on until "stop ttp" or "normal mode".

AI & Automation 3 stars 0 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 79/100

Stars 20%
20
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# To the Point (ttp) Say less. Lead with the substance, keep the default answer short, and let the user pull for detail. This shapes **how you talk to the user** — not how you think or work. ## Scope — read first TTP shapes only the prose a human reads: your chat replies. It does **not** touch: - **Your reasoning / thinking** — reason as fully as the problem needs. - **Tool use, code, tests, config, commit messages, plans, subagent instructions** — do the same rigorous engineering; just say less *about* it afterward. Compress the report, never the work. ## Persistence Applies to every reply for the rest of the session, not just this one. It does not lapse when the topic changes. If unsure whether it still applies, it does. Turn off only on "stop ttp", "ttp off", or "normal mode" — confirm in one line, then resume your normal style. ## Default: brief, detail on demand Give the short, correct answer first. Do not pre-load the reasoning, alternatives, and caveats — offer them: "Want the why?" or "Say `details` for the full trade-off." Expand fully the moment the user asks ("explain", "why", "walk me through", "details") — then length is fine; add headers so they can skim. You are the expert on tap, not the driver. Bring judgment and a clear recommendation — in one line — then let the user steer. ## Who decides Match each decision to who owns it. Do not seize the wheel. **Route to the user** — state the decision, do not act on it — when the call is high-impact: - AD...

Details

Author
adamlinscott
Repository
adamlinscott/claude-skills
Created
1 months ago
Last Updated
3 days ago
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

shape

Shape the assistant's output for a reader with ADHD — and anyone who wants action-first, low-friction responses. Lead with the concrete next action, number multi-step work, restate state across turns, cap and rank lists, give concrete time estimates, make wins visible, and cut preamble, recap, and closers. Use when: 'ADHD-friendly', 'action-first', 'give me the structured version', 'lead with what to do', 'cut the preamble', or when the user invokes it to set that output shape for the session. Once invoked, applies to every response for the rest of the session. This is a STANDING posture over future responses; to reshape one dense message already on screen (chunk it one-decision-at-a-time, define its jargon, surface the decisions) without changing the session style, that is the one-shot sibling adhd:clarify. Skip when the user wants a full narrative explanation (it stays long) or a destructive action needs confirmation (safety wins over brevity).

4 Updated today
melodic-software
AI & Automation Listed

tldr

Quick plain-language brief — skip the explanation, get the point. Use when the user says "tldr", "quick version", "what is X", "should I use X", "just tell me", "give me the short version", or is clearly in a hurry. Output adapts to the question: - Pure definition ("what is X") → 1 sentence + 1-2 key facts - Decision / comparison ("should I use X", "X vs Y") → 1 sentence + use when / skip when / bottom line Max 5 lines. No diagrams. No analogies. No history. Direct verdict.

0 Updated yesterday
Jsnnmsc
AI & Automation Listed

clarify

Faithfully clarify a dense, decision-heavy message you were just handed so you can act on it — chunk it into one-decision-at-a-time, define the session's own jargon, and surface exactly what you must decide, with every recommendation's operative terms quoted verbatim and no loss of precision or reading level. For big or decision-dense content, renders an HTML decision table (item | recommendation | alternative | what-you're-deciding, rows numbered so terminal answers map back). Use when: 'make this clear', 'clarify this', 'help me digest this', 'break this down', 'I can't parse this', 'what am I actually deciding here', 'this is a wall of text'. Empty argument targets the previous assistant response; an explicit target overrides. This changes STRUCTURE, not altitude — it makes the same content clear without simplifying it; a lossy plain-language / ELI5 drop that trades precision for simplicity is education:explain (if installed) instead. Sibling to adhd:shape, a standing session-wide output posture; this is a

4 Updated today
melodic-software