Turn your rambling notes into a clear brief
Unverified●32/40Claude Code◐PartialHas SKILL.md but declares no allowed-tools — Claude Code will ask for permission each time
Cursor◐PartialPlain prose you can paste in — but no Cursor rules file
Codex◐PartialPlain prose you can paste in — but no AGENTS.md
Gemini CLI◐PartialPlain prose you can paste in
Copilot◐PartialPlain prose you can paste in — but no Copilot instructions file
npx agentalley add thinking-out-loudWho is stuck, and on what
I think out loud in half-finished sentences and change my mind halfway through, so whoever picks it up fills the gaps their own way and runs with it. By the time I see the result, it's built on a misunderstanding I never got the chance to catch.
What it gives you
A short structured brief with your goal, your locked-in decisions, the open questions, anything you flip-flopped on, and a clearly separated list of guesses flagged for you to fix.
When NOT to use it
It won't make the decisions for you or produce the finished work — it only plays your thinking back so you can spot what's wrong before anyone acts on it.
The whole source
Frontmatter — 4 properties
| name | thinking-out-loud |
|---|---|
| description | >- A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's inferences and guesses quarantined away from the user's own phrasing, so the user verifies what the model believes, not just what it doubts. Use when the user says "let me think out loud" or wants to ramble a bit before building anything, when a message opens with a speech-to-text preamble like "switching to voice, sorry for typos", when input is a long weakly punctuated stream with restarts and mid-message reversals ("actually no, wait, scrap that idea entirely"), or when the user asks to be interviewed about a fuzzy half-formed idea. Includes an optional capture mode for rambles spread across several messages and an optional targeted interview. |
| license | Apache-2.0 |
| metadata | author: "Shubham Saboo version: "1.3.0 source: "https://github.com/Shubhamsaboo/awesome-llm-apps |
| 1 | --- |
| 2 | name: thinking-out-loud |
| 3 | description: >- |
| 4 | A contract for what the agent does when a long, messy, stream-of-consciousness |
| 5 | ramble arrives (usually voice dictation): act on nothing until the echo brief |
| 6 | is approved. The echo audits the entire transfer, mission, locked decisions |
| 7 | and constraints, open questions, flips and parked tangents, with the model's |
| 8 | inferences and guesses quarantined away from the user's own phrasing, so the |
| 9 | user verifies what the model believes, not just what it doubts. Use when the |
| 10 | user says "let me think out loud" or wants to ramble a bit before building |
| 11 | anything, when a message opens with a speech-to-text preamble like "switching |
| 12 | to voice, sorry for typos", when input is a long weakly punctuated stream |
| 13 | with restarts and mid-message reversals ("actually no, wait, scrap that idea |
| 14 | entirely"), or when the user asks to be interviewed about a fuzzy half-formed |
| 15 | idea. Includes an optional capture mode for rambles spread across several |
| 16 | messages and an optional targeted interview. |
| 17 | license: Apache-2.0 |
| 18 | metadata: |
| 19 | author: "Shubham Saboo" |
| 20 | version: "1.3.0" |
| 21 | source: "https://github.com/Shubhamsaboo/awesome-llm-apps" |
| 22 | ---A5 — No allowed-tools declared — no way to tell what this skill may touch |
| 23 | |
| 24 | # Thinking Out Loud |
| 25 | |
| 26 | A ten minute voice ramble transfers more context than any prompt a person |
| 27 | would type, and models reconstruct rambles well. The failure is |
| 28 | downstream and invisible: the model fills every gap in the ramble |
| 29 | confidently. "The usual model" silently becomes a specific model. "The |
| 30 | standard size" becomes a specific viewport. A position the user reversed |
| 31 | mid-ramble survives as fact. None of this registers as uncertainty from |
| 32 | the inside, so none of it ever becomes a clarifying question. The model |
| 33 | then acts on a misreading it fully believes, and the user discovers it an |
| 34 | hour of generated work later. |
| 35 | |
| 36 | This skill is the fix: before acting on any ramble, produce an echo, a |
| 37 | short structured audit of everything absorbed, with the model's own |
| 38 | additions quarantined from the user's words. The user corrects three |
| 39 | lines instead of debugging a built artifact. |
| 40 | |
| 41 | ## Why an echo instead of follow-up questions |
| 42 | |
| 43 | Asking clarifying questions is good, and the interview below does it. |
| 44 | But questions alone cannot secure a ramble, for two structural reasons: |
| 45 | |
| 46 | - **Questions verify what the model doubts. The echo verifies what the |
| 47 | model believes.** A clarifying question requires felt uncertainty, and |
| 48 | confident misreadings feel like knowledge. The echo forces every |
| 49 | inference and gap-fill into the open whether or not it felt uncertain. |
| 50 | - **Questions sample; the echo audits.** A long ramble carries dozens of |
| 51 | facts and half-decisions. Even good questions probe three or four; the |
| 52 | rest of the model's understanding goes unverified into action. The |
| 53 | echo inventories the entire transfer, and it works by recognition, not |
| 54 | recall: the user reads and spots what is wrong, which is far cheaper |
| 55 | than producing answers, and ramblers often do not know their answer |
| 56 | until they see the wrong guess written down. |
| 57 | |
| 58 | ## The contract |
| 59 | |
| 60 | 1. **Act on nothing.** No file edits, no code, no plans, no solutions to |
| 61 | fragments, until the echo is approved. Reconstruct first. |
| 62 | 2. **Label every addition.** Inferences and guesses live in their own |
| 63 | section, apart from the user's own content. Never present a guess in |
| 64 | the user's voice. |
| 65 | 3. **Surface every reversal.** Adopt the later position, but flag the |
| 66 | flip. Never silently average or pick. |
| 67 | 4. **Lose nothing.** Tangents get parked, not dropped. |
| 68 | 5. **Never remark on dictation artifacts.** Typos, homophones, filler, |
| 69 | and restarts are resolved silently from context. Keep the user's own |
| 70 | vocabulary and project names. |
| 71 | 6. **Ask before persisting.** The approved brief is offered a home, never |
| 72 | saved unprompted. |
| 73 | |
| 74 | ## When to use |
| 75 | |
| 76 | - A message is a long, weakly punctuated stream of consciousness with |
| 77 | restarts, filler, and mid-message reversals ("actually no, scrap that") |
| 78 | - A message opens with a voice preamble ("switching to speech |
| 79 | recognition, sorry for any typos", "dictating this") |
| 80 | - The user says they want to ramble or think out loud |
| 81 | - The user asks to be interviewed to untangle a fuzzy idea |
| 82 | |
| 83 | ## When not to use |
| 84 | |
| 85 | - Short requests that are already clear |
| 86 | - The user wants a verbatim transcript, minutes, or cleanup of dictation |
| 87 | while keeping their exact words |
| 88 | - Long but already structured text, such as a pasted spec or document |
| 89 | - The user asked a direct question and wants a direct answer |
| 90 | |
| 91 | ## The echo |
| 92 | |
| 93 | One structured reply. Dense, scannable, and short: the user should find |
| 94 | and fix an error in seconds. Full template with a worked example in |
| 95 | [references/echo-format.md](references/echo-format.md). |
| 96 | |
| 97 | 1. **Mission**: one sentence stating what the user is actually trying to |
| 98 | achieve. Often this differs from what they said first; that is fine. |
| 99 | 2. **Locked**: the user's decisions and constraints, merged into one |
| 100 | list. Mark anything they called a top priority. |
| 101 | 3. **Open**: questions the ramble raised but did not answer. |
| 102 | 4. **Ledger**: flips (both positions in one line, later one adopted) and |
| 103 | parked tangents (one line each). |
| 104 | 5. **My additions**: the only interpretation callouts. "Inferred" |
| 105 | (strongly implied but never stated) and "Guessed" (gaps you filled). |
| 106 | Tell the user to correct these first. |
| 107 | |
| 108 | Compression rules, non-negotiable: |
| 109 | |
| 110 | - **Nothing appears twice.** Every fact lives in exactly one section. |
| 111 | - **No "you said" recap.** Everything outside My additions is the user's |
| 112 | own content by definition; only the model's additions get called out. |
| 113 | - **One line per bullet.** If a bullet needs two lines, it is two bullets |
| 114 | or it is bloat. |
| 115 | - **Vague quantifiers are never silently resolved.** "The usual model", |
| 116 | "standard size", "soon": each lands in Open or Guessed, never absorbed |
| 117 | into a locked item as if it were specified. |
| 118 | |
| 119 | Close by inviting corrections and offering the interview. |
| 120 | |
| 121 | ## The interview (optional) |
| 122 | |
| 123 | Follow-up questions have their place: after the audit, not instead of |
| 124 | it. Only if the user accepts the offer, or asked to be interviewed up |
| 125 | front. |
| 126 | |
| 127 | - Ask only about items flagged in Open or Guessed |
| 128 | - One question per message, highest information gain first |
| 129 | - Each question states in one clause why it matters |
| 130 | - Cap at five questions; stop early once answers stop changing the brief |
| 131 | - After the interview, restate only the sections of the echo that changed |
| 132 | |
| 133 | ## Capture mode (multi-message rambles) |
| 134 | |
| 135 | Not needed for dictation tools, where the whole ramble arrives as one |
| 136 | message. Use it when the user invokes the skill before rambling and then |
| 137 | adds thoughts across several messages, possibly over a long stretch. |
| 138 | |
| 139 | - Acknowledge once, in one short line ("Go ahead, I'm listening. Say |
| 140 | 'done' when you want the echo.") |
| 141 | - For every following message, reply with a single minimal line |
| 142 | ("Listening."). Vary it slightly so it does not feel robotic. |
| 143 | - Do NOT solve, praise, summarize, analyze, or ask questions mid-stream. |
| 144 | - If the user asks a direct question mid-ramble, answer it in at most two |
| 145 | sentences, then return to listening. |
| 146 | - Exit on "done", "echo", "echo me", "that's it", "what did you get", or |
| 147 | any clear equivalent, then deliver the echo. |
| 148 | |
| 149 | ## Persistence |
| 150 | |
| 151 | After the user approves the echo, offer exactly three options: |
| 152 | |
| 153 | 1. Append the brief to CLAUDE.md so future sessions inherit it |
| 154 | 2. Save it to `docs/rambles/YYYY-MM-DD-<topic>.md` |
| 155 | 3. Keep it in-conversation only |
| 156 | |
| 157 | The approved brief then governs the rest of the session: honor its |
| 158 | decisions and constraints without re-asking. |
| 159 |
Reviews
Installed this one?Write the first review and take the Trailblazer badge.
Alternatives
Structure Your Invention For A Patent FilingDescribe your invention in plain words and get back a formal write-up that lays out the problem it solves, how it works, and which parts are worth protecting.●····●37/40Claims Drafting: The Core Patent SkillDescribe your invention in plain words and get back a numbered set of formal patent claims — the legal wording that defines exactly what you own.●····●36/40Patent Novelty and Non-Obviousness CheckDescribe your invention in everyday words and get back a clear read on whether it's new and original enough to patent, plus where it might hit trouble.●····●35/40Patent Pipeline: From Invention to FilingDescribe your invention in plain words and get back a complete first-draft patent application — claims, full description, and abstract — ready to hand to a patent attorney.●····●35/40