Summarize
openclaw/openclaw
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Land a sprawling chat thread on an actual decision — the summarize-and-fork move (positions restated, the question isolated), the decider-and-deadline injection, and the recorded close that ends the…
MITAuto-check passed
Install Thread To Decision
$ npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills thread-to-decision --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/thread-to-decision .claude/skills/thread-to-decision && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "thread-to-decision" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/thread-to-decision into .claude/skills/thread-to-decision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thread-to-decision", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/thread-to-decisionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills thread-to-decision --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/thread-to-decision .agents/skills/thread-to-decision && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "thread-to-decision" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/thread-to-decision into .agents/skills/thread-to-decision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thread-to-decision", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills thread-to-decision --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/thread-to-decision .cursor/skills/thread-to-decision && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "thread-to-decision" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/thread-to-decision into .cursor/skills/thread-to-decision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thread-to-decision", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/thread-to-decision--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills thread-to-decision --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/thread-to-decision .gemini/skills/thread-to-decision && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "thread-to-decision" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/thread-to-decision into .gemini/skills/thread-to-decision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thread-to-decision", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mohitagw15856/pm-claude-skills thread-to-decisionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/thread-to-decision .github/skills/thread-to-decision && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "thread-to-decision" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/thread-to-decision into .github/skills/thread-to-decision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thread-to-decision", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills thread-to-decision --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/thread-to-decision .opencode/skills/thread-to-decision && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "thread-to-decision" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/thread-to-decision into .opencode/skills/thread-to-decision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thread-to-decision", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
thread-to-decision- GitHub stars
- 1.4k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 686 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Land a sprawling chat thread on an actual decision — the summarize-and-fork move (positions restated, the question isolated), the decider-and-deadline injection, and the recorded close that ends the…
- Works in 5 steps: Summarize before structuring: the… → Isolate the question, park the quests:… → Inject the missing trio: decider,… → …
- Asked this thread is going in circles
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Landing Rules and Output Format, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Thread To Decision is an agent skill from mohitagw15856/pm-claude-skills. Land a sprawling chat thread on an actual decision — the summarize-and-fork move (positions restated, the question isolated), the decider-and-deadline injection, and the recorded close that ends the forty-message orbit. Use when asked this thread is going in circles, get a decision out of this discussion, summarize where we landed, or why do our threads never conclude. Produces the thread summary with positions attributed, the isolated decision question, the closure message, and the decision record.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked this thread is going in circles
- Get a decision out of this discussion
- Summarize where we landed
- Why do our threads never conclude
Example prompts
- “/thread-to-decision”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Summarize before structuring: the landing message opens by compressing fairly — "Where we are: the question is X. [A] and [B] favor option…
- Isolate the question, park the quests: threads orbit partly because three questions share one thread — the landing names the question and…
- Inject the missing trio: decider, deadline, silence-meaning — "Proposal: [name] decides by Thu EOD; comments until then; silence =…
- Close with the why and the dissent: the decision message states the call, two sentences of why, and names the road not taken ("going with…
- Record or relitigate: the decision goes to the durable home (the decision log, the project doc) with a link back — and the thread gets the…
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Thread To Decision loads about 1.3k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 686 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 686 words, ~1,333 tokens.
Download SKILL.mdSave it as
.claude/skills/thread-to-decision/SKILL.md (or your agent's skills folder).- name
- thread-to-decision
- description
- Land a sprawling chat thread on an actual decision — the summarize-and-fork move (positions restated, the question isolated), the decider-and-deadline injection, and the recorded close that ends the forty-message orbit. Use when asked this thread is going in circles, get a decision out of this discussion, summarize where we landed, or why do our threads never conclude. Produces the thread summary with positions attributed, the isolated decision question, the closure message, and the decision record.
Thread To Decision Skill
Threads orbit because nobody performs the landing: forty messages in, three positions have emerged, two side-quests have spawned, and every participant believes a different thing was "basically agreed." The landing is a move, performable by anyone (not just the boss): summarize the positions fairly with names, isolate the actual question from the side-quests, inject the missing structure — a decider and a deadline (async-instead closure rules) — and when the call lands, record it where decisions live, because a decision that exists only at message 47 doesn't exist.
What This Skill Produces
- The summary message — the thread compressed: the question, the positions with names, the side-quests parked
- The structure injection — decider named (or proposed), deadline set, silence-meaning declared
- The closure message — the decision, its why, dissent acknowledged
- The record — the decision logged durably, linked back to the thread
Required Inputs
Ask for these if not provided:
- The thread — the actual messages; summarizing positions requires reading them, and attribution requires care ("A argued X" must be fair enough that A nods)
- The user's standing — thread owner, participant, or the person with authority to name a decider? The moves flex — a participant proposes the structure ("suggest [name] calls this by Friday?"); an owner installs it
- The real question — threads braid several; the user's read on which one matters (the summary tests it against the thread)
- Where decisions live — the log, the doc, the channel pin; the record needs a durable home
Framework: The Landing Rules
- Summarize before structuring: the landing message opens by compressing fairly — "Where we are: the question is X. [A] and [B] favor option 1 (reasons); [C] raises the cost concern; the tangent about Y is real but separate." A summary that participants recognize buys the standing to impose structure; a partisan summary restarts the war with citations.
- Isolate the question, park the quests: threads orbit partly because three questions share one thread — the landing names the question and explicitly parks the others ("Y deserves its own thread — starting it separately"). One thread, one decision.
- Inject the missing trio: decider, deadline, silence-meaning — "Proposal: [name] decides by Thu EOD; comments until then; silence = can-live-with-it." When the user lacks authority to appoint, the proposal of structure almost always gets adopted, because everyone is tired of orbiting — the mover's advantage.
- Close with the why and the dissent: the decision message states the call, two sentences of why, and names the road not taken ("going with 1; C's cost concern is real — we'll cap the spend at X to address it"). Acknowledged dissent ends threads; ignored dissent schedules the sequel.
- Record or relitigate: the decision goes to the durable home (the decision log, the project doc) with a link back — and the thread gets the final message pointing there. Six weeks later, "wait, did we decide this?" gets a link instead of a rematch. This is the decision-meeting-format record discipline, applied to the async venue where it's skipped most.
Show full SKILL.md (193 more words)Show less
Output Format
Thread Landing: [topic] — [N] messages in
The Summary Message (post this)
[The question · positions with names, fairly · parked side-quests · the structure proposal: decider, deadline, silence-meaning]
The Closure Message (when decided)
[The call · the two-sentence why · dissent acknowledged with its accommodation if any]
The Record
[The durable entry: decision, why, date, thread link · posted at (home) · the thread's final pointer message]
Quality Checks
- The summary would be endorsed by each summarized participant
- Exactly one question survived; side-quests got explicit parking
- Decider, deadline, and silence-meaning were all injected
- The closure acknowledges dissent by name and content
- The record lives outside the thread with links both ways
Anti-Patterns
- Do not structure before summarizing — unearned structure reads as a power move and gets litigated
- Do not summarize partisanly — one slanted attribution costs the whole landing
- Do not let three questions share the landing — braided threads orbit forever
- Do not close without the dissent line — smooth closes breed rough reopenings
- Do not leave the decision at message 47 — un-recorded decisions have a half-life of six weeks
Example Trigger Phrases
- "Get a decision out of this discussion."
- "Summarize where we landed."
- "Why do our threads never conclude?"
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/thread-to-decision of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Thread To Decision next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Thread To Decision this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Summarizeopenclaw/openclaw | 392k | 1 repos | ~531 | Automated safety check: Pass | MIT | |
| Landingalirezarezvani/claude-skills | 28k | — | ~3.8k | Automated safety check: Pass | MIT | |
| Research Summarizeralirezarezvani/claude-skills | 28k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Hacker News Summarizerykdojo/claude-code-tips | 10k | — | ~942 | Automated safety check: Pass | Custom licence | |
| Landing Page Conversion Auditgithub/awesome-copilot | 40k | 1 repos | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Landing
alirezarezvani/claude-skills
Generates a premium single-page HTML landing page with 3D CSS animations, GSAP scroll effects, and mouse-parallax depth.
Research Summarizer
alirezarezvani/claude-skills
Structured research summarization agent skill for non-dev users.
Hacker News Summarizer
ykdojo/claude-code-tips
Fetches Hacker News top stories, a chosen story with its comment thread and the linked article through the official APIs, then summarizes them.
- Official
Landing Page Conversion Audit
github/awesome-copilot
Audit a landing page, sales page or checkout page for conversion leaks and return a fix list ordered by expected revenue impact.
SEO Aeo Landing Page Writer
sickn33/agentic-awesome-skills
Writes or improves conversion-focused landing pages for products, services, and offers with practical SEO and AEO structure.
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Questions about Thread To Decision
What does Thread To Decision do?
Land a sprawling chat thread on an actual decision — the summarize-and-fork move (positions restated, the question isolated), the decider-and-deadline injection, and the recorded close that ends the…. Thread To Decision is an agent skill from mohitagw15856/pm-claude-skills. Land a sprawling chat thread on an actual decision — the summarize-and-fork move (positions restated, the question isolated), the decider-and-deadline injection, and the recorded close that ends the forty-message orbit.
When should I use Thread To Decision?
Thread To Decision fits situations like: asked this thread is going in circles; get a decision out of this discussion; summarize where we landed; why do our threads never conclude.
How do I install Thread To Decision in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a claude-code`. Or copy the skill folder (skills/thread-to-decision in mohitagw15856/pm-claude-skills) into .claude/skills/thread-to-decision in your project. Claude Code loads it when a task matches its description.
How do I install Thread To Decision in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a codex`. Or copy the skill folder (skills/thread-to-decision in mohitagw15856/pm-claude-skills) into .agents/skills/thread-to-decision in your project. Codex loads it when a task matches its description.
Can I use Thread To Decision in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill thread-to-decision -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/thread-to-decision, .gemini/skills/thread-to-decision, .github/skills/thread-to-decision and .opencode/skills/thread-to-decision in your project.
What does Thread To Decision need to run?
SKILL.md names no scripts, command-line tools or credentials: Thread To Decision is instructions for the agent only.
Does Thread To Decision access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Thread To Decision safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Thread To Decision use?
Thread To Decision is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Thread To Decision use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Thread To Decision?
Skills that share tags, products or a category with Thread To Decision: Summarize (openclaw/openclaw, 392k stars), Landing (alirezarezvani/claude-skills, 28k stars), Research Summarizer (alirezarezvani/claude-skills, 28k stars) and Hacker News Summarizer (ykdojo/claude-code-tips, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Thread To Decision?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.