Agent skill

Easyslides Clarify

by Rimagination in Rimagination/easyslides

Resolve only result-affecting ambiguities in an EasySlides request through explicit user choices before route selection or generation.

MITAuto-check passedDocuments & Office

Install Easyslides Clarify

skills CLI
$ npx skills add Rimagination/easyslides --skill easyslides-clarify -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Rimagination/easyslides easyslides-clarify --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Rimagination/easyslides.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/easyslides-clarify .claude/skills/easyslides-clarify && rm -rf skills-src

Use ~/.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/

Facts

Skill name
easyslides-clarify
GitHub stars
138
Token cost
~1.9k tokens
SKILL.md length
935 words
Files
2
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Resolve only result-affecting ambiguities in an EasySlides request through explicit user choices before route selection or generation.

  • Works in 6 steps: Inspect the conversation and available… → Ask ONE highest-impact question with the… → Give concise context-specific options… → …
  • More reasonable interpretations would materially change the story
  • SKILL.md covers Mandatory production-scheme…, Mandatory reconstruction-mode…, Blocking rule and Conversation protocol, plus 1 more section
  • Calls python

What it does

Easyslides Clarify is an agent skill from Rimagination/easyslides. Resolve only result-affecting ambiguities in an EasySlides request through explicit user choices before route selection or generation. Use when two or more reasonable interpretations would materially change the story, page count, template, visible wording, or fidelity target; do not trigger for harmless implementation details or already explicit requests.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Documents & Office. The licence is MIT.

When your agent uses it

  • More reasonable interpretations would materially change the story
  • Visible wording
  • Fidelity target
  • Do not trigger for harmless implementation details

Example prompts

  • “/easyslides-clarify”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Inspect the conversation and available source metadata first. Maintain
  2. Ask ONE highest-impact question with the host's native question tool
  3. Give concise context-specific options and a justified recommendation; allow
  4. Use each answer to choose the next question. Narrow broad goals, identify
  5. Persist explicit answers and skip resolved items. Handle free-text answers
  6. Stop when the task can be executed without a material guess. Briefly restate

What it can do on your machine

Read from SKILL.md and the folder at commit fe4882b. 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

    Shell commands in SKILL.md call:

    • python

    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

Easyslides Clarify loads about 1.9k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 935 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 Rimagination/easyslides at commit fe4882b, republished under its MIT licence (© Rimagination). 935 words, ~1,896 tokens.

Download SKILL.mdSave it as .claude/skills/easyslides-clarify/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
easyslides-clarify
description
Resolve only result-affecting ambiguities in an EasySlides request through explicit user choices before route selection or generation. Use when two or more reasonable interpretations would materially change the story, page count, template, visible wording, or fidelity target; do not trigger for harmless implementation details or already explicit requests.

EasySlides Clarification Gate

Use this skill when a new/regenerated PPT lacks an explicit production scheme, or another result-affecting ambiguity remains. Notes-only, narration-only and preview-only tasks do not require a production scheme; ask only about unresolved details within the requested editing scope.

Mandatory production-scheme choice

An unspecified scheme is always blocking for a new or regenerated PPT. MUST ask the user to choose directly generated editable PPT, full-image reconstruction, or partial-image reconstruction, using the exact user-facing labels in workflows/clarification-gate.md. No automatic default; wait for the user's answer before slide planning, image generation, SVG reconstruction or PPTX production. An explicit choice already made for the same task must not be asked again.

Mandatory reconstruction-mode choice

In both choice rounds, MUST show Token 消耗 and 耗时 levels for every option before the user chooses. Explain that levels are relative estimates adjusted for scope and complexity, not exact usage or promised time; disclose image generation separately. Follow the cost and time disclosure in the clarification workflow.

For image reconstruction, confirm 全图矢量重建 (full_vector) or 保留复杂配图 (preserve_complex_images) through workflows/clarification-gate.md before execution. No automatic default, even for “快点做”; reuse only an explicit choice in the same task. Both modes require native PPT text boxes. Preserve one source line in one text box, merging OCR fragments and using text runs for mixed styling; keep independent labels and table cells separate. Full-vector mode needs approval before any raster exception. Partial rebuilds apply this within selected regions.

Blocking rule

Do not infer a value when two or more reasonable interpretations would change the route, story, page count, template, visible wording, or visual fidelity. Ask the user to choose. A recommendation is allowed, but it only becomes a decision when the user explicitly chooses it or says to use the recommendation.

Do not write deck_plan.json, design_spec.md, spec_lock.md, SVG pages, or an exported PPTX while a blocking clarification remains unanswered.

Conversation protocol

For academic tasks, read references/academic-orchestration.md before asking. Use its evidence-aware intake and internal handoffs across all templates and production schemes. Catalog completion alone does not establish readiness: resolve the academic brief's material gaps and conflicts before planning.

Default to an adaptive interview in the conversation, using native popup questions. Never open an in-app browser, HTML guide, questionnaire, or require copy/paste to discover requirements unless the user explicitly requests that UI.

  1. Inspect the conversation and available source metadata first. Maintain confirmed facts, unresolved decisions and contradictions internally. Do not ask for information already visible in the user's files or messages.
  2. Ask ONE highest-impact question with the host's native question tool (request_user_input_async in Codex Default mode; use a synchronous question tool only where available). Wait for the answer before dependent work. Group up to three questions only when their answers are genuinely independent.
  3. Give concise context-specific options and a justified recommendation; allow free text. Ask for a missing fact directly when choices would distort it. Explain route/mode tradeoffs without internal IDs; retain token/time disclosure.
  4. Use each answer to choose the next question. Narrow broad goals, identify what the audience should understand or decide, and surface contradictions such as exhaustive evidence versus a five-minute talk. Offer concrete tradeoffs. Do not mechanically exhaust a catalog or ask for detail that would not change the result.
  5. Persist explicit answers and skip resolved items. Handle free-text answers faithfully; never coerce them into an inaccurate canned option. Check source access, research scope, length, route, applicable editability/template choices and any preserve/rewrite boundary before execution.
  6. Stop when the task can be executed without a material guess. Briefly restate the agreed outcome and proceed. No confirmation of the confirmation. Resolve conflicts first. Missing files call for the specific file, not more options.

Do not ask open-ended “请再描述一下” questions when a choice set can expose the ambiguity. Do not ask again for a value the user already made explicit.

Show full SKILL.md (301 more words)Show less

State contract

Use the repository question catalog and state machine:

For new academic content tasks, add --academic to clarify init. This extends the same blocking state machine with academic goals, evidence policy, audience, timing, style and content boundaries. It conditionally requires research scope and/or a material inventory. Keep this off for notes-only edits and faithful reconstruction of an already approved deck with no new content planning. Older saved requests remain compatible; do not restart an approved task.

Free-text questions have no option_ids: save the actual response with clarify answer ... --answer "field=actual response". Populate explicit facts via --known-json first. Record inspected file content with --by "inspection:file:page"; record user answers with --by "user:message". needs_material_inspection has an empty popup payload: inspect the files, resolve essential missing sources, then record the source-located inventory. Never mark a missing/unreadable required file as an inspected usable source. Copy the confirmed decisions into deck_plan.json as academic_brief and retain the sibling clarification_request.json for the existing plan gate.

powershell
python scripts/easyslides.py clarify init --route new_deck --out <project>/clarification_request.json
python scripts/easyslides.py clarify answer <project>/clarification_request.json --answer purpose=defense
python scripts/easyslides.py clarify next <project>/clarification_request.json
python scripts/easyslides.py clarify require <project>/clarification_request.json

The request is confirmed only when every blocking question has an answer. The machine-readable state is the source of truth for the later deck plan and execution lock.

next is a read-only catalog adapter. Its questions array matches Codex's request_user_input_async payload; map the actual answer using option_ids. For a different host or a synchronous tool, convert to that tool's declared schema (including required question IDs, headers and structured options); never call an unavailable tool. If no popup tool is available, ask one concise question with options directly in chat and wait. A browser is not the fallback. The adapter does not display a popup itself. ready_for_summary means catalog choices and enabled academic requirements are recorded; still check their substance, contradictions, source rights and partial regions. The program checks completeness, not the truth of an inspection or scientific claim. Follow interview examples in workflows/clarification-gate.md.

© Rimagination, 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 skills/easyslides-clarify of Rimagination/easyslides.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit fe4882b

Compare with similar skills

Easyslides Clarify 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.

Easyslides Clarify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Easyslides Clarify this skillRimagination/easyslides138—~1.9kAutomated safety check: PassMIT
Markdown Article FormatterJimLiu/baoyu-skills27k6 repos~3.5kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Obsidian MarkdownAtmosphere/atmosphere3.8k20 repos~1.3kAutomated safety check: PassApache-2.0
DOCXrvdbreemen/OTGW-firmware20733 repos~4.3kAutomated safety check: PassProprietary
Word Document Reader and WriterHKUDS/DeepTutor41k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Markdown Article Formatter

    JimLiu/baoyu-skills

    Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.

    27k GitHub starsUsed in 6 repos~3.5k tokens
    Documents & OfficeAuto-check passed
  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Obsidian Markdown

    Atmosphere/atmosphere

    Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.

    3.8k GitHub starsUsed in 20 repos~1.3k tokens
    Documents & OfficeAuto-check passed
  • DOCX

    rvdbreemen/OTGW-firmware

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).

    207 GitHub starsUsed in 33 repos~4.3k tokens
    Documents & OfficeAuto-check passed
  • Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.

    41k GitHub stars~2.5k tokensUpdated 3 days ago
    Documents & OfficeAuto-check passed
  • Crossposting

    wasp-lang/wasp

    Crosspost Wasp blog articles (MDX) to DEV.to and Medium. An agent skill from wasp-lang/wasp.

    19k GitHub stars~1.1k tokensUpdated today
    Documents & OfficeAuto-check passed

More from Rimagination/easyslides

  • Easyslides

    Rimagination/easyslides

    Use EasySlides to create, distill, edit, review, and export editable academic PPTX presentations, including 蒸馏PPT、提取模板、复用模板和答辩PPT。

    138 GitHub stars~12k tokensUpdated 28 days ago
    Auto-check passed
  • Easyslides

    Rimagination/easyslides

    Canonical EasySlides entry point for creating, distilling, editing, reviewing, and exporting editable academic PPTX presentations.

    138 GitHub stars~1.7k tokensUpdated 28 days ago
    Auto-check passed
  • Easyslides Distill

    Rimagination/easyslides

    Distill a source PPTX with EasySlides into factual source evidence, a content-free semantic layout family, and real reusable component and symbol assets.

    138 GitHub stars~4.7k tokensUpdated 28 days ago
    Auto-check passed

Questions about Easyslides Clarify

What does Easyslides Clarify do?

Resolve only result-affecting ambiguities in an EasySlides request through explicit user choices before route selection or generation. Easyslides Clarify is an agent skill from Rimagination/easyslides. Resolve only result-affecting ambiguities in an EasySlides request through explicit user choices before route selection or generation.

When should I use Easyslides Clarify?

Easyslides Clarify fits situations like: more reasonable interpretations would materially change the story; visible wording; fidelity target; do not trigger for harmless implementation details.

How do I install Easyslides Clarify in Claude Code?

Run `npx skills add Rimagination/easyslides --skill easyslides-clarify -a claude-code`. Or copy the skill folder (skills/easyslides-clarify in Rimagination/easyslides) into .claude/skills/easyslides-clarify in your project. Claude Code loads it when a task matches its description.

How do I install Easyslides Clarify in Codex?

Run `npx skills add Rimagination/easyslides --skill easyslides-clarify -a codex`. Or copy the skill folder (skills/easyslides-clarify in Rimagination/easyslides) into .agents/skills/easyslides-clarify in your project. Codex loads it when a task matches its description.

Can I use Easyslides Clarify 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 Rimagination/easyslides --skill easyslides-clarify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/easyslides-clarify, .gemini/skills/easyslides-clarify, .github/skills/easyslides-clarify and .opencode/skills/easyslides-clarify in your project.

What does Easyslides Clarify need to run?

Going by SKILL.md and its folder, Easyslides Clarify needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Easyslides Clarify 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 Easyslides Clarify 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 Easyslides Clarify use?

Easyslides Clarify 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 Easyslides Clarify use?

About 1.9k tokens (SKILL.md is roughly 7.6k 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 Easyslides Clarify?

Skills that share tags, products or a category with Easyslides Clarify: Markdown Article Formatter (JimLiu/baoyu-skills, 27k stars), Markitdown (ImCa0/just-laws, 781 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and DOCX (rvdbreemen/OTGW-firmware, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Easyslides Clarify?

Rimagination (a GitHub user) maintains it in Rimagination/easyslides, which has 138 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 13, 2026.

Source: Rimagination/easyslides on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.