Ambiguity Resolver
mohitagw15856/pm-claude-skills
Structure vague opportunities and unclear briefs into actionable one-page problem statements.
Elicit user preferences and resolve material ambiguity before a long autonomous run.
MITAuto-check passed
Install Align Me
$ npx skills add swyxio/skills --skill align-me -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install swyxio/skills align-me --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/swyxio/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/align-me .claude/skills/align-me && 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 "align-me" agent skill from https://github.com/swyxio/skills/tree/main/align-me into .claude/skills/align-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "align-me", 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/swyxio/skills/tree/main/align-meType 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 swyxio/skills --skill align-me -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install swyxio/skills align-me --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/align-me .agents/skills/align-me && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "align-me" agent skill from https://github.com/swyxio/skills/tree/main/align-me into .agents/skills/align-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "align-me", 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 swyxio/skills --skill align-me -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install swyxio/skills align-me --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/align-me .cursor/skills/align-me && 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 "align-me" agent skill from https://github.com/swyxio/skills/tree/main/align-me into .cursor/skills/align-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "align-me", 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/swyxio/skills.git --path align-me--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 swyxio/skills --skill align-me -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install swyxio/skills align-me --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/align-me .gemini/skills/align-me && 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 "align-me" agent skill from https://github.com/swyxio/skills/tree/main/align-me into .gemini/skills/align-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "align-me", 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 swyxio/skills align-meInstalls 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 swyxio/skills --skill align-me -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/align-me .github/skills/align-me && 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 "align-me" agent skill from https://github.com/swyxio/skills/tree/main/align-me into .github/skills/align-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "align-me", 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 swyxio/skills --skill align-me -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install swyxio/skills align-me --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/align-me .opencode/skills/align-me && 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 "align-me" agent skill from https://github.com/swyxio/skills/tree/main/align-me into .opencode/skills/align-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "align-me", 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
align-me- GitHub stars
- 175
- Token cost
- ~1.3k tokens
- SKILL.md length
- 700 words
- Files
- 2
- Skills in repo
- 89
- Repo updated
- First seen
- Licence
- MIT
At a glance
Elicit user preferences and resolve material ambiguity before a long autonomous run.
- Works in 3 steps: Inspect available context and perform… → Do not ask for facts that can be… → Identify ambiguities involving scope,…
- The user invokes $align-me
- SKILL.md covers Prepare, Ask the batch, Apply the answers and Voice
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Align Me is an agent skill from swyxio/skills. Elicit user preferences and resolve material ambiguity before a long autonomous run. Use when the user invokes $align-me or /align-me, or asks to be interviewed, grilled, aligned, or given a batch of decisions before implementation, migration, deployment, design, or other consequential work.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
The repository describes itself as: Agent skills for Claude Code and other AI agents. The licence is MIT.
When your agent uses it
- The user invokes $align-me
- Asks to be interviewed
- Given a batch of decisions before implementation
- Other consequential work
Example prompts
- “/align-me”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Inspect available context and perform lightweight, read-only discovery first.
- Do not ask for facts that can be discovered safely or decisions whose answer would not affect the work.
- Identify ambiguities involving scope, product behavior, destructive changes, architecture, migration, rollout, safety, cost, or…
What it can do on your machine
Read from SKILL.md and the folder at commit 038ef34. 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
Align Me loads about 1.3k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 700 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 swyxio/skills at commit 038ef34, republished under its MIT licence (© swyxio). 700 words, ~1,301 tokens.
Download SKILL.mdSave it as
.claude/skills/align-me/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- align-me
- description
- Elicit user preferences and resolve material ambiguity before a long autonomous run. Use when the user invokes $align-me or /align-me, or asks to be interviewed, grilled, aligned, or given a batch of decisions before implementation, migration, deployment, design, or other consequential work.
Align Me
Pause before the long autonomous run and surface the choices that could materially change the outcome.
Output contract: The deliverable is a self-contained questionnaire in the final answer: every numbered question, every lettered option with its consequence, and every recommendation. A tool call or a summary of decisions is not the deliverable.
Prepare
- Inspect available context and perform lightweight, read-only discovery first.
- Do not ask for facts that can be discovered safely or decisions whose answer would not affect the work.
- Identify ambiguities involving scope, product behavior, destructive changes, architecture, migration, rollout, safety, cost, or verification.
Ask the batch
Give one batch of 2–10 numbered questions. For every question:
- State the decision plainly.
- Provide a few mutually exclusive lettered options, normally 2–4.
- Explain the concrete tradeoff or consequence of each option.
- End with a reasonable recommendation and briefly explain why.
Keep the questions compact, specific to the task, and answerable without specialist knowledge. Do not manufacture filler questions. If fewer than two material ambiguities exist, ask only the meaningful question or state the assumptions and proceed.
Required final-answer output
Write the complete question batch directly in the final user-facing response as ordinary Markdown. Include every option, its tradeoff, and the recommendation. The user must be able to answer by reading that response alone, without expanding activity, opening a panel, inspecting tool arguments, or finding another message. Put the questionnaire before any extended explanation or implementation plan.
Default to text only for this skill. Do not call a native question tool or asynchronous picker merely because one is available. Some interfaces may show question titles while hiding the option payload; a tool response saying accepted: true confirms submission, not that the user can see or answer the options.
If a picker is explicitly requested or required by higher-priority instructions, use it only as permitted. Still reproduce the complete batch in the final answer whenever text options are permitted. If higher-priority instructions prohibit text options, respect that restriction: include the full alternatives and consequences in the tool's visible question text when permitted, and explain the output limitation plainly. Never ask the user to approve codes whose definitions are missing from the visible interface.
These are incomplete outputs and must be rewritten before sending:
- “I've sent six alignment choices” followed by a summary or default codes.
- Question titles with recommendations but no alternative options.
- “See the picker / activity above” in place of the questionnaire.
- An
approve allprompt whose referenced options appear only in tool arguments.
For example:
Show full SKILL.md (280 more words)Show less
1. How broad should the research be?
- A — Distribution first: improve packaging and promotion; keep editorial changes as optional bets. Recommended for near-term action.
- B — Challenge the format too: include episode length, cadence and guest selection; broader conclusions, more disruption.
- C — Promotion only: hold editorial and packaging fixed; narrower but immediately operational.
Before sending the final answer, check the answer text itself:
- Every numbered decision includes all of its lettered options, not just the recommended one.
- Every option states a concrete consequence or tradeoff.
- Every decision ends with a recommendation and its reason.
- Every code in the aggregate default maps to an option printed in this answer.
- The answer remains usable if all commentary, tools, and pickers are hidden.
If any check fails, repair the final answer before sending. Do not shorten the answer by removing the choices; shorten background explanation instead. If text options are prohibited by higher-priority instructions, explain that limitation rather than claiming these checks passed.
Finish with an aggregate default such as:
Reply approve all to accept
1A, 2C, 3B, or give changes such as2A, 3C.
Then stop and wait for the user's response. Do not begin consequential or mutating work while waiting.
Apply the answers
- Treat approve all as approval of every recommended option.
- Accept partial overrides, prose feedback, or follow-up questions without requiring the user to restate accepted choices.
- Restate the final choices briefly only when needed to prevent misunderstanding, then proceed.
- Ask a second batch only when the answers expose a genuinely new material ambiguity.
Voice
Be candid and useful, not bureaucratic. Make a real recommendation instead of hiding behind neutral option lists. Clearly flag irreversible, production, privacy, security, and data-loss consequences.
© swyxio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in align-me of swyxio/skills.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 038ef34
Compare with similar skills
Align Me 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 |
|---|---|---|---|---|---|---|
| Align Me this skillswyxio/skills | 175 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Ambiguity Resolvermohitagw15856/pm-claude-skills | 1.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Preference Optimizationwshobson/agents | 40k | — | ~2k | Automated safety check: Pass | MIT | |
| Ccs Alignthedotmack/claude-mem | 99k | — | ~6.1k | Automated safety check: Pass | Apache-2.0 | |
| Rich Elicitationsickn33/agentic-awesome-skills | 47k | 1 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Investor Materialsaffaan-m/ECC | 276k | 3 repos | ~268 | Automated safety check: Pass | MIT |
Similar skills
Preference Optimization
wshobson/agents
Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO.
Ccs Align
thedotmack/claude-mem
Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → getobservations, land them in a seat-owned middle…
Rich Elicitation
sickn33/agentic-awesome-skills
Asks clarifying questions in multiple rounds before starting ambiguous tasks.
Investor Materials
affaan-m/ECC
创建和更新宣传文稿、一页简介、投资者备忘录、加速器申请、财务模型和融资材料。当用户需要面向投资者的文件、预测、资金用途表、里程碑计划或必须在多个融资资产中保持内部一致性的材料时使用。
Material Design
sickn33/agentic-awesome-skills
Web and App implementation guide for Material Design. An agent skill from sickn33/agentic-awesome-skills.
More from swyxio/skills
All 89 skills in this repoProgrammatic Agents
swyxio/skills
Run a selected coding-agent CLI programmatically, with latency, error, usage, cost, and trace logging.
Reserved Handle Policy
swyxio/skills
Design, implement, audit, or refresh protected username and handle namespaces for public products.
New Mac Setup
swyxio/skills
Fully automated new Mac setup for fullstack web developers and AI engineers.
Youtube API
swyxio/skills
Manage YouTube videos programmatically via the YouTube Data API v3 — upload video files, upload custom thumbnails, update video metadata (titles, descriptions, tags), and query video/channel info…
Youtube Studio Batch Upload
swyxio/skills
Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files.
Deep Trajectory Analysis
swyxio/skills
Reconstruct and visually analyze paired agent, game, or policy trajectories to determine whether changed actions produced their intended effects.
Questions about Align Me
What does Align Me do?
Elicit user preferences and resolve material ambiguity before a long autonomous run. Align Me is an agent skill from swyxio/skills. Elicit user preferences and resolve material ambiguity before a long autonomous run.
When should I use Align Me?
Align Me fits situations like: the user invokes $align-me; asks to be interviewed; given a batch of decisions before implementation; other consequential work.
How do I install Align Me in Claude Code?
Run `npx skills add swyxio/skills --skill align-me -a claude-code`. Or copy the skill folder (align-me in swyxio/skills) into .claude/skills/align-me in your project. Claude Code loads it when a task matches its description.
How do I install Align Me in Codex?
Run `npx skills add swyxio/skills --skill align-me -a codex`. Or copy the skill folder (align-me in swyxio/skills) into .agents/skills/align-me in your project. Codex loads it when a task matches its description.
Can I use Align Me 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 swyxio/skills --skill align-me -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/align-me, .gemini/skills/align-me, .github/skills/align-me and .opencode/skills/align-me in your project.
What does Align Me need to run?
SKILL.md names no scripts, command-line tools or credentials: Align Me is instructions for the agent only.
Does Align Me 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 Align Me 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 Align Me use?
Align Me 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 Align Me use?
About 1.3k tokens (SKILL.md is roughly 5.2k 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 Align Me?
Skills that share tags, products or a category with Align Me: Ambiguity Resolver (mohitagw15856/pm-claude-skills, 1.4k stars), Preference Optimization (wshobson/agents, 40k stars), Ccs Align (thedotmack/claude-mem, 99k stars) and Rich Elicitation (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Align Me?
swyxio (a GitHub user) maintains it in swyxio/skills, which has 175 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 5, 2026.
Source: swyxio/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.