Verify Success After Unknown Error
HKUDS/OpenSpace
Verify task completion by checking filesystem state when executecodesandbox or runshell return misleading unknown errors
This skill should be used when the user provides a strategy, plan, or decision document and wants to surface hidden assumptions and blind spots using the Known/Unknown 4-quadrant framework.
MITAuto-check passed
Install Unknown
$ npx skills add team-attention/plugins-for-claude-natives --skill unknown -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install team-attention/plugins-for-claude-natives unknown --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/team-attention/plugins-for-claude-natives.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/clarify/skills/unknown .claude/skills/unknown && 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 "unknown" agent skill from https://github.com/team-attention/plugins-for-claude-natives/tree/main/plugins/clarify/skills/unknown into .claude/skills/unknown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unknown", 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/team-attention/plugins-for-claude-natives/tree/main/plugins/clarify/skills/unknownType 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 team-attention/plugins-for-claude-natives --skill unknown -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install team-attention/plugins-for-claude-natives unknown --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/team-attention/plugins-for-claude-natives.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/clarify/skills/unknown .agents/skills/unknown && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "unknown" agent skill from https://github.com/team-attention/plugins-for-claude-natives/tree/main/plugins/clarify/skills/unknown into .agents/skills/unknown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unknown", 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 team-attention/plugins-for-claude-natives --skill unknown -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install team-attention/plugins-for-claude-natives unknown --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/team-attention/plugins-for-claude-natives.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/clarify/skills/unknown .cursor/skills/unknown && 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 "unknown" agent skill from https://github.com/team-attention/plugins-for-claude-natives/tree/main/plugins/clarify/skills/unknown into .cursor/skills/unknown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unknown", 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/team-attention/plugins-for-claude-natives.git --path plugins/clarify/skills/unknown--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 team-attention/plugins-for-claude-natives --skill unknown -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install team-attention/plugins-for-claude-natives unknown --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/team-attention/plugins-for-claude-natives.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/clarify/skills/unknown .gemini/skills/unknown && 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 "unknown" agent skill from https://github.com/team-attention/plugins-for-claude-natives/tree/main/plugins/clarify/skills/unknown into .gemini/skills/unknown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unknown", 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 team-attention/plugins-for-claude-natives unknownInstalls 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 team-attention/plugins-for-claude-natives --skill unknown -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/team-attention/plugins-for-claude-natives.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/clarify/skills/unknown .github/skills/unknown && 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 "unknown" agent skill from https://github.com/team-attention/plugins-for-claude-natives/tree/main/plugins/clarify/skills/unknown into .github/skills/unknown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unknown", 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 team-attention/plugins-for-claude-natives --skill unknown -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install team-attention/plugins-for-claude-natives unknown --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/team-attention/plugins-for-claude-natives.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/clarify/skills/unknown .opencode/skills/unknown && 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 "unknown" agent skill from https://github.com/team-attention/plugins-for-claude-natives/tree/main/plugins/clarify/skills/unknown into .opencode/skills/unknown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unknown", 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
unknown- GitHub stars
- 827
- Token cost
- ~1.7k tokens
- SKILL.md length
- 752 words
- Files
- 3 (incl. references)
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- MIT
At a glance
This skill should be used when the user provides a strategy, plan, or decision document and wants to surface hidden assumptions and blind spots using the Known/Unknown 4-quadrant framework.
- Works in 6 steps: Intake → Context → Draft + R1 Questions → …
- Provides a strategy
- SKILL.md covers When to Use, Core Principle:…, 3-Round Depth Pattern and Protocol, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Unknown is an agent skill from team-attention/plugins-for-claude-natives. This skill should be used when the user provides a strategy, plan, or decision document and wants to surface hidden assumptions and blind spots using the Known/Unknown 4-quadrant framework. Trigger on "known unknown", "4분면 분석", "blind spots", "뭘 놓치고 있지", "뭘 모르는지 모르겠어", "전략 점검", "전략 분석", "assumption check", "가정 점검", "quadrant analysis", "what am I missing". Strategy-level blind spot analysis with hypothesis-driven questioning. For requirement clarification use vague; for content-vs-form reframing use metamedium.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/playbook-template.md` and `references/question-design.md`).
The repository describes itself as: Claude Code plugins for power users. The licence is MIT.
When your agent uses it
- Provides a strategy
- Decision document and wants to surface hidden assumptions and blind spots using the Known/Unknown 4-quadrant framework
- Assumption check
- Quadrant analysis
Example prompts
- “known unknown”
- “blind spots”
- “assumption check”
- “/unknown”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit fd9c207. 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
Unknown loads about 1.7k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 131 tokens; SKILL.md has 752 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 team-attention/plugins-for-claude-natives at commit fd9c207, republished under its MIT licence (© team-attention). 752 words, ~1,720 tokens.
Download SKILL.mdSave it as
.claude/skills/unknown/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- unknown
- description
- This skill should be used when the user provides a strategy, plan, or decision document and wants to surface hidden assumptions and blind spots using the Known/Unknown 4-quadrant framework. Trigger on "known unknown", "4분면 분석", "blind spots", "뭘 놓치고 있지", "뭘 모르는지 모르겠어", "전략 점검", "전략 분석", "assumption check", "가정 점검", "quadrant analysis", "what am I missing". Strategy-level blind spot analysis with hypothesis-driven questioning. For requirement clarification use vague; for content-vs-form reframing use metamedium.
Unknown: Surface Blind Spots with Known/Unknown Quadrants
Surface hidden assumptions and blind spots in any strategy, plan, or decision using the Known/Unknown quadrant framework and hypothesis-driven questioning.
When to Use
- Strategy or planning documents that need scrutiny
- Decisions with unclear direction or hidden assumptions
- Any situation where "what we don't know" matters more than "what we do know"
For specific requirement clarification (feature requests, bug reports), use the vague skill. For content-vs-form reframing (optimizing within a form vs inventing a new form), use the metamedium skill.
Core Principle: Hypothesis-as-Options
ALWAYS use the AskUserQuestion tool for every question in R1/R2/R3 — never ask questions in plain text. The structured format enforces hypothesis-as-options and limits choice fatigue.
Present hypotheses as options instead of open questions. The hypotheses ARE the analysis — by designing good options, 80% of the analytical work is done before the user even answers. The user's job is to confirm, correct, or surprise.
BAD: "Why can't you do video content?" ← open question, high load
GOOD: "Time / Skill gap / No guests / High bar" ← pick one or more- Each option IS a testable hypothesis about the user's situation
- Use multiSelect: true to catch compound causes
- "Other" is always available for out-of-frame answers
3-Round Depth Pattern
| Round | Purpose | Questions | Key trait |
|---|---|---|---|
| R1 | Validate draft quadrant | 3-4 | Broad, covers all quadrants |
| R2 | Drill into weak spots | 2-3 | Targeted, follows R1 answers |
| R3 | Nail execution details | 2-3 | Specific, optional |
Critical: Generate Round N questions from Round N-1 answers. Never use pre-prepared questions across rounds. Cap total at 7-10 questions.
Protocol
Phase 1: Intake
File provided: Read and extract goals, components, implicit assumptions, missing elements.
Topic keyword only: Start directly with R1 questions to establish scope. The draft in Phase 3 will be rougher but R1 corrects it.
Phase 2: Context
Gather related context to find Unknown Knowns — assets the user may not realize they have:
- Glob for related files: CLAUDE.md, README, decision records, past analyses in the project
- Read project context: recent goals, team structure, active initiatives
- Identify underutilized assets: existing tools/skills not in use, past projects with reusable patterns, team expertise not leveraged
Items discovered here become UK candidates and options in R1 questions.
Phase 3: Draft + R1 Questions
Generate an initial 4-quadrant classification. The draft is intentionally rough — R1 exists to correct it, not confirm it. Err on the side of classifying uncertain items as KU rather than KK.
Design R1 questions to test quadrant boundaries. Batch all R1 questions into a single AskUserQuestion call (max 4 questions):
| Target | Pattern | Example |
|---|---|---|
| KK | "Is this really certain?" | "Primary revenue source?" (options) |
| KU | "Where's the weakest link?" | "Which flywheel connection is weakest?" |
| UK | "What exists but isn't used?" | Based on context findings |
| UU | "What's the biggest fear?" | Risk scenarios as options |
Phase 4: Deepen + R2 Questions
Analyze R1 answers. Find the most uncertain area and drill in.
R2 triggers: compound answers (messy area), unexpected answers (draft wrong), "Other" selected (outside frame).
For detailed R2 question types, see references/question-design.md.
Show full SKILL.md (283 more words)Show less
Phase 5: Execute + R3 Questions (Optional)
After priorities are set, nail down execution details for top items. Skip if R2 already provides enough detail.
Phase 6: Playbook Output
Generate a structured 4-quadrant playbook file. For the complete output template, see references/playbook-template.md.
Output structure:
# {Topic}: Known/Unknown Quadrant Analysis
## Current State Diagnosis
## Quadrant Matrix (ASCII with resource %)
## 1. Known Knowns: Systematize (60%)
## 2. Known Unknowns: Design Experiments (25%)
- Each KU: Diagnosis → Experiment → Success Criteria → Deadline → Promotion Condition
## 3. Unknown Knowns: Leverage (10%)
## 4. Unknown Unknowns: Set Up Antennas (5%)
## Strategic Decision: What to Stop
## Execution Roadmap (week-by-week)
## Core Principles (3-5 decision criteria)Resource percentages (60/25/10/5) are defaults. Adjust based on context — e.g., a startup exploring product-market fit may allocate 40% KU and 30% KK.
Anti-Patterns
- Open questions ("What would you like to do?") — use hypothesis options
- 5+ options per question — causes choice fatigue
- Ignoring R1 answers when designing R2 — performative questioning
- Equal depth on all quadrants — wastes time, loses focus
- No "stop doing" section — adding without subtracting
Example
Input: Growth strategy document
R1: Revenue source? → Workshops. Weakest link? → Biz→Knowledge. Blocker? → Skill gap + high bar (multiSelect). Biggest fear? → Execution scattered.
R2 (driven by "execution scattered"): What to drop? → Product dev. Why no knowledge→content? → No process + no time + hard to abstract. Role clarity? → Unclear.
R3: Video format? → Screen recording. Retro blocker? → Don't know what to capture. What content resonated? → Raw discoveries.
Key discovery: Abstraction isn't needed — raw insights work better. Collapsed triple bottleneck into 15-minute pipeline.
Rules
- Hypotheses, not questions: Every option is a testable hypothesis
- Answers drive depth: R2 from R1, R3 from R2
- 7-10 questions max: Beyond this is fatigue
- Stop > Start: Always include "what to stop doing"
- Promote or kill: Every KU gets a promotion condition and a kill condition
- Raw > Perfect: Encourage minimum viable experiments, not perfect plans
- Draft is disposable: The initial quadrant is meant to be corrected
Additional Resources
Reference Files
references/question-design.md— Detailed question types for each round, trigger conditions, and AskUserQuestion formatting guidereferences/playbook-template.md— Complete output template with section-by-section guide
© team-attention, 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 2 other files (references) in plugins/clarify/skills/unknown of team-attention/plugins-for-claude-natives.
- SKILL.md
- references/playbook-template.md
- references/question-design.md
Open the folder on GitHubat commit fd9c207
Compare with similar skills
Unknown 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 |
|---|---|---|---|---|---|---|
| Unknown this skillteam-attention/plugins-for-claude-natives | 827 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Verify Success After Unknown ErrorHKUDS/OpenSpace | 7.7k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Grill For UnknownsAsymmetric-al/core | 381 | — | ~4.6k | Automated safety check: Pass | MIT | |
| Unknowns Discoverysecondsky/claude-skills | 227 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Grill For Unknownsnicobailon/grill-for-unknowns | 219 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Unknown Coverage Reviewhashgraph-online/awesome-codex-plugins | 1.2k | — | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Grill For Unknowns
Asymmetric-al/core
Use only when the user explicitly invokes grill-for-unknowns or asks for a map-vs-territory unknowns pass, blindspot discovery, unknown-known prototypes, or a subagent launch packet before…
Unknowns Discovery
secondsky/claude-skills
Discover and reduce task unknowns — blindspots, missing context, and unknown unknowns — before committing to a plan, implementation, review, or merge.
Grill For Unknowns
nicobailon/grill-for-unknowns
A skill your agent uses when starting or reviewing a complex implementation where the user wants an agent to interrogate the plan against docs/source evidence, surface unknown unknowns, and avoid…
Unknown Coverage Review
hashgraph-online/awesome-codex-plugins
完成した差分・PR・検証証拠に残る Unknown（未確認の前提・調査されていない影響・ 不足している証拠）を横断合成する evidence-sufficiency のメタ観点。個別 defect の 検出は既存 skill へ委譲し、本 skill は「そのリスク種別を調査した証拠が残っているか」 の meta 評価のみを行う。通常は finding verification 後の…
Blindspot Pass
Neeeophytee/finding-unknowns-skills
Surface the user's unknown unknowns before work starts. An agent skill from Neeeophytee/finding-unknowns-skills.
More from team-attention/plugins-for-claude-natives
All 16 skills in this repoGmail
team-attention/plugins-for-claude-natives
This skill should be used when the user asks to "check email", "read emails", "send email", "reply to email", "search inbox", or manages Gmail.
History Insight
team-attention/plugins-for-claude-natives
This skill should be used when user wants to access, capture, or reference Claude Code session history.
Session Analyzer
team-attention/plugins-for-claude-natives
This skill should be used when the user asks to "analyze session", "세션 분석", "evaluate skill execution", "스킬 실행 검증", "check session logs", "로그 분석", provides a session ID with a skill path, or wants…
Tech Decision
team-attention/plugins-for-claude-natives
This skill should be used when the user asks to "기술 의사결정", "뭐 쓸지 고민", "A vs B", "비교 분석", "라이브러리 선택", "아키텍처 결정", "어떤 걸 써야 할지", "트레이드오프", "기술 선택", "구현 방식 고민", or needs deep analysis for technical…
Youtube Digest
team-attention/plugins-for-claude-natives
This skill should be used when the user asks to "유튜브 정리", "영상 요약", "transcript 번역", "YouTube digest", "영상 퀴즈", or provides a YouTube URL for analysis.
Fetch Tweet
team-attention/plugins-for-claude-natives
This skill should be used when the user asks to "트윗 가져와", "트윗 번역", "X 게시글 읽어줘", "tweet fetch", "트윗 내용", "트윗 원문", or provides an X/Twitter URL (x.com, twitter.com) and wants to read, translate, or…
Questions about Unknown
What does Unknown do?
This skill should be used when the user provides a strategy, plan, or decision document and wants to surface hidden assumptions and blind spots using the Known/Unknown 4-quadrant framework. Unknown is an agent skill from team-attention/plugins-for-claude-natives. This skill should be used when the user provides a strategy, plan, or decision document and wants to surface hidden assumptions and blind spots using the Known/Unknown 4-quadrant framework.
When should I use Unknown?
Unknown fits situations like: provides a strategy; decision document and wants to surface hidden assumptions and blind spots using the Known/Unknown 4-quadrant framework; assumption check; quadrant analysis.
How do I install Unknown in Claude Code?
Run `npx skills add team-attention/plugins-for-claude-natives --skill unknown -a claude-code`. Or copy the skill folder (plugins/clarify/skills/unknown in team-attention/plugins-for-claude-natives) into .claude/skills/unknown in your project. Claude Code loads it when a task matches its description.
How do I install Unknown in Codex?
Run `npx skills add team-attention/plugins-for-claude-natives --skill unknown -a codex`. Or copy the skill folder (plugins/clarify/skills/unknown in team-attention/plugins-for-claude-natives) into .agents/skills/unknown in your project. Codex loads it when a task matches its description.
Can I use Unknown 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 team-attention/plugins-for-claude-natives --skill unknown -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/unknown, .gemini/skills/unknown, .github/skills/unknown and .opencode/skills/unknown in your project.
What does Unknown need to run?
SKILL.md names no scripts, command-line tools or credentials: Unknown is instructions for the agent only.
Does Unknown 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 Unknown 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 Unknown use?
Unknown 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 Unknown use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.
What are the alternatives to Unknown?
Skills that share tags, products or a category with Unknown: Verify Success After Unknown Error (HKUDS/OpenSpace, 7.7k stars), Grill For Unknowns (Asymmetric-al/core, 381 stars), Unknowns Discovery (secondsky/claude-skills, 227 stars) and Grill For Unknowns (nicobailon/grill-for-unknowns, 219 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Unknown?
team-attention (a GitHub organization) maintains it in team-attention/plugins-for-claude-natives, which has 827 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on April 20, 2026.
Source: team-attention/plugins-for-claude-natives on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.