Feature Spec
PackmindHub/packmind
Generate a Packmind feature specification from a GitHub issue, file, URL, or direct description.
Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.
Install Clarification Analyst
$ npx skills add GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install GulajavaMinistudio/Mayukai-Theme clarification-analyst --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/GulajavaMinistudio/Mayukai-Theme.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/clarification-analyst .claude/skills/clarification-analyst && 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 "clarification-analyst" agent skill from https://github.com/GulajavaMinistudio/Mayukai-Theme/tree/master/.agents/skills/clarification-analyst into .claude/skills/clarification-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-analyst", 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/GulajavaMinistudio/Mayukai-Theme/tree/master/.agents/skills/clarification-analystType 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 GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install GulajavaMinistudio/Mayukai-Theme clarification-analyst --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GulajavaMinistudio/Mayukai-Theme.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/clarification-analyst .agents/skills/clarification-analyst && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "clarification-analyst" agent skill from https://github.com/GulajavaMinistudio/Mayukai-Theme/tree/master/.agents/skills/clarification-analyst into .agents/skills/clarification-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-analyst", 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 GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install GulajavaMinistudio/Mayukai-Theme clarification-analyst --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GulajavaMinistudio/Mayukai-Theme.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/clarification-analyst .cursor/skills/clarification-analyst && 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 "clarification-analyst" agent skill from https://github.com/GulajavaMinistudio/Mayukai-Theme/tree/master/.agents/skills/clarification-analyst into .cursor/skills/clarification-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-analyst", 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/GulajavaMinistudio/Mayukai-Theme.git --path .agents/skills/clarification-analyst--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 GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install GulajavaMinistudio/Mayukai-Theme clarification-analyst --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GulajavaMinistudio/Mayukai-Theme.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/clarification-analyst .gemini/skills/clarification-analyst && 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 "clarification-analyst" agent skill from https://github.com/GulajavaMinistudio/Mayukai-Theme/tree/master/.agents/skills/clarification-analyst into .gemini/skills/clarification-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-analyst", 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 GulajavaMinistudio/Mayukai-Theme clarification-analystInstalls 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 GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/GulajavaMinistudio/Mayukai-Theme.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/clarification-analyst .github/skills/clarification-analyst && 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 "clarification-analyst" agent skill from https://github.com/GulajavaMinistudio/Mayukai-Theme/tree/master/.agents/skills/clarification-analyst into .github/skills/clarification-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-analyst", 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 GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install GulajavaMinistudio/Mayukai-Theme clarification-analyst --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GulajavaMinistudio/Mayukai-Theme.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/clarification-analyst .opencode/skills/clarification-analyst && 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 "clarification-analyst" agent skill from https://github.com/GulajavaMinistudio/Mayukai-Theme/tree/master/.agents/skills/clarification-analyst into .opencode/skills/clarification-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clarification-analyst", 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
clarification-analyst- GitHub stars
- 139
- Token cost
- ~1.1k tokens
- SKILL.md length
- 470 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.
- Works in 3 steps: Document Interrogation → Formulating Sharp Questions (The "Grill… → Iterative Interrogation & Reporting
- Tasks that involve PRD writing
- SKILL.md covers Overview, When to Use, Operational Workflow and Clarification Quality Standards, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Clarification Analyst is an agent skill from GulajavaMinistudio/Mayukai-Theme. Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Product & Project Management, covering PRD writing and Planning. It works with Visual Studio Code. The repository describes itself as: Combination theme for VS Code and VSCodium that inspired from Ayu Theme, Monokai , Andromeda, Material Color, and Gruvbox Darktooth Color. The licence is MIT.
When your agent uses it
- Tasks that involve PRD writing
- Tasks that involve Planning
Example prompts
- “Use the clarification-analyst skill to help interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find…”
- “/clarification-analyst”
Workflow steps
3 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 c8c9159. 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 (its code samples are diff).
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
Clarification Analyst loads about 1.1k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 470 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 GulajavaMinistudio/Mayukai-Theme at commit c8c9159, republished under its MIT licence (© GulajavaMinistudio). 470 words, ~1,123 tokens.
Download SKILL.mdSave it as
.claude/skills/clarification-analyst/SKILL.md (or your agent's skills folder).- name
- clarification-analyst
- description
- Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.
- license
- MIT
<!-- markdownlint-disable -->Clarification Analyst Skill
Overview
This skill focuses on executing a systematic clarification phase against requirement documents (PRD), Technical Specifications, or Implementation Plans. It ensures that no hidden assumptions slip through before entering the next SDLC phase. This skill accompanies the @ClarificationAnalyst agent.
When to Use
Use this skill when:
- Transitioning from the Requirements phase (PRD) to Technical Specification.
- Transitioning from Technical Specification to Implementation Planning.
- The provided requirement documents feel vague, have contradictions, or omit edge cases.
- The user specifically requests to "interrogate", "clarify", or "perform an ambiguity analysis" on their plans.
Operational Workflow
Phase 1: Document Interrogation
Thoroughly analyze the target document (PRD, Technical Specification, or Implementation Plan) with a focus on:
- Ambiguous Terminology: Search for unmeasurable words like "fast", "easy", "sufficient", "automatically".
- Negative Conditions & Edge Cases: What happens if the database goes down? What happens if the user uploads an empty file?
- Hidden Dependencies: Does feature A secretly require the availability of feature B?
Phase 2: Formulating Sharp Questions (The "Grill Me" Approach)
Turn findings into pointed questions that cannot be answered with a simple "Yes/No", and always do the heavy lifting by providing concrete options.
- Bad (Lazy): "How should we handle the error if the connection drops?"
- Good (Heavy Lifting): "If the connection is lost during compression, should we (A) Implement an automatic retry 3 times before failing, or (B) Fail immediately and show a manual 'Try Again' button to the user?"
Phase 3: Iterative Interrogation & Reporting
- Halt and Iterate: Ask only ONE question at a time. Wait for the user to respond before moving to the next ambiguity.
- Reporting: Once all issues are resolved interactively, use the Clarification Report template to summarize all agreements. Refuse requests to design architecture or write code until the source documents (PRD/Spec/Plan) have been updated with these findings.
Show full SKILL.md (173 more words)Show less
Clarification Quality Standards
Detecting Ambiguity
Use measurable criteria to challenge requirements.
# Example Ambiguous PRD Statement (BAD)
- The application must process PDFs quickly and not consume a lot of memory.
# Challenge/Clarification (GOOD)
+ What does "quickly" mean in seconds/milliseconds? Is there a target SLA (e.g., < 5 seconds per 10MB)?
+ What is the maximum limit for "a lot of memory" in Megabytes?
+ What happens if the PDF file size is over 100MB, does the memory limit remain the same?Finding Edge Cases
Every feature has a "Happy Path". Your primary job is to find the "Sad Paths".
# Example Happy Path in PRD (BAD)
- The user uploads a PDF, the system compresses it, and provides a download link.
# Challenge/Clarification (GOOD)
+ What happens if the PDF is password-protected (encrypted)?
+ What happens if the uploaded file is corrupt or not actually a PDF (e.g., an .exe renamed to .pdf)?
+ How long does the download link last before it expires or is deleted from the system?Implementation Guidelines
DO (Always)
- Challenge Assumptions: If a requirement seems reasonable but its boundaries are not explicitly written down, question it.
- Block (Halt): Politely but firmly refuse if asked to proceed to the Planning phase without definitive answers from the user.
DON'T (Avoid)
- Fabricating Solutions: Do not assume solutions. If there is a problem (e.g., a PDF over the memory limit), do not immediately propose algorithm X; instead, ask the user how they want to handle it.
- Closed Questions: Avoid Yes/No questions. Force the user to think by using questions like "What if", "What is the maximum size", or "When exactly".
- Machine Gun Questioning: Never output a bulleted list of 5 or 10 questions at once. Ask sequentially, one per interaction.
- Fabricating Solutions Silently: Do not assume solutions without asking. You must propose them as options, but the user must make the final call.
© GulajavaMinistudio, 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 .agents/skills/clarification-analyst of GulajavaMinistudio/Mayukai-Theme.
Open the folder on GitHubat commit c8c9159
Compare with similar skills
Clarification Analyst 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 |
|---|---|---|---|---|---|---|
| Clarification Analyst this skillGulajavaMinistudio/Mayukai-Theme | 139 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Feature SpecPackmindHub/packmind | 318 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Mcaf Feature Specmanagedcode/Storage | 138 | — | ~959 | Automated safety check: Pass | MIT | |
| Run Judgesclosedloop-ai/claude-plugins | 122 | — | ~15k | Automated safety check: Notes | Apache-2.0 | |
| Dex Improvedavekilleen/Dex | 494 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Prd To PlanDwlad90/stylex-swc-plugin | 112 | — | ~767 | Automated safety check: Pass | MIT |
Similar skills
Mcaf Feature Spec
managedcode/Storage
Create or update a feature spec under docs/Features/ with business rules, user flows, system behaviour, verification, and Definition of Done.
Run Judges
closedloop-ai/claude-plugins
Orchestrate parallel judge agent execution, aggregate CaseScore results, write plan-judges.json, code-judges.json, prd-judges.json, or feature-judges.json, and validate output.
Dex Improve
davekilleen/Dex
Workshop one improvement idea into an implementation plan. An agent skill from davekilleen/Dex.
Prd To Plan
Dwlad90/stylex-swc-plugin
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/.
Alignment
Ovid/paad
A skill your agent uses when verifying that requirements/specs/PRDs and their implementation plans match — before starting work, after a spec or plan update, or when suspecting coverage gaps, scope…
More from GulajavaMinistudio/Mayukai-Theme
All 11 skills in this repoOmni Dev
GulajavaMinistudio/Mayukai-Theme
Omni-expert principal software architect. An agent skill from GulajavaMinistudio/Mayukai-Theme.
Artifact Consistency Checker
GulajavaMinistudio/Mayukai-Theme
Performs consistency and traceability audits across documents (PRD vs Spec vs Plan) to detect missing coverage and scope creep.
Brainstorming Explorer
GulajavaMinistudio/Mayukai-Theme
Systematic codebase exploration, architectural critique, and generation of Project Discovery Drafts for SDLC Phase 0.
Bug Remediation Architect
GulajavaMinistudio/Mayukai-Theme
Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.
Expert Code Reviewer
GulajavaMinistudio/Mayukai-Theme
Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans.
Memory Manager
GulajavaMinistudio/Mayukai-Theme
Standardized workflow for discovering, reading, and writing the project's memory file (memory.instructions.md) to persist context across chat sessions.
Related
Works with
Questions about Clarification Analyst
What does Clarification Analyst do?
Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions. Clarification Analyst is an agent skill from GulajavaMinistudio/Mayukai-Theme. Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.
When should I use Clarification Analyst?
Clarification Analyst fits situations like: tasks that involve PRD writing; tasks that involve Planning.
How do I install Clarification Analyst in Claude Code?
Run `npx skills add GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a claude-code`. Or copy the skill folder (.agents/skills/clarification-analyst in GulajavaMinistudio/Mayukai-Theme) into .claude/skills/clarification-analyst in your project. Claude Code loads it when a task matches its description.
How do I install Clarification Analyst in Codex?
Run `npx skills add GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a codex`. Or copy the skill folder (.agents/skills/clarification-analyst in GulajavaMinistudio/Mayukai-Theme) into .agents/skills/clarification-analyst in your project. Codex loads it when a task matches its description.
Can I use Clarification Analyst 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 GulajavaMinistudio/Mayukai-Theme --skill clarification-analyst -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clarification-analyst, .gemini/skills/clarification-analyst, .github/skills/clarification-analyst and .opencode/skills/clarification-analyst in your project.
What does Clarification Analyst need to run?
SKILL.md names no scripts, command-line tools or credentials: Clarification Analyst is instructions for the agent only.
Does Clarification Analyst 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 Clarification Analyst 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 Clarification Analyst use?
Clarification Analyst is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Clarification Analyst use?
About 1.1k tokens (SKILL.md is roughly 4.5k 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 Clarification Analyst?
Skills that share tags, products or a category with Clarification Analyst: Feature Spec (PackmindHub/packmind, 318 stars), Mcaf Feature Spec (managedcode/Storage, 138 stars), Run Judges (closedloop-ai/claude-plugins, 122 stars) and Dex Improve (davekilleen/Dex, 494 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Clarification Analyst?
GulajavaMinistudio (a GitHub user) maintains it in GulajavaMinistudio/Mayukai-Theme, which has 139 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 1, 2026.
Source: GulajavaMinistudio/Mayukai-Theme on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.