Agent skill · Audited from source
Constrained Content Generation
skill · ECNU-ICALK/AutoSkillLicence not declaredAudited 14 Oct 2026 · source 04e912cff54b
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 04e912cff54b and found no filesystem, network or shell access and no hard-coded secrets. What it does: Generates concise content, scripts, or summaries under strict word, character, and formatting constraints. Capable of rewriting articles to specific character limits, simplifying academic language, and strictly…
Cite
Cite this page
ModelsAtlas. “Constrained Content Generation (ECNU-ICALK/AutoSkill)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/ecnu-icalk/constrained-content-generation
Trust audit
Audit 0.4.1 · source read 14 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha 04e912cff54b · 14 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- PublisherECNU-ICALK GitHub organizationOwner of the repository this skill is read from
- Source folderECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8_GLM4.7/constrained_content_generationThe exact folder we audited
- LicenceNot declaredAs the repository states it
- Commit pinned for this verdict04e912cff54bA new audit runs when the source changes
- Repository statusNot archivedLast push 157 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Generates concise content, scripts, or summaries under strict word, character, and formatting constraints. Capable of rewriting articles to specific character limits, simplifying academic language, and strictly…
--- id: "55d0f104-0370-4358-89d2-a8b371769534" name: "constrained_content_generation" description: "Generates concise content, scripts, or summaries under strict word, character, and formatting constraints. Capable of rewriting articles to specific character limits, simplifying academic language, and strictly preserving citations." version: "0.1.13" tags: - "content generation" - "writing constraints" - "word count" - "character limit" - "reference-based" - "summarization" - "academic writing" - "simple language" - "citations" - "Q&A" - "rewriting" triggers: - "Write [X] paragraph on [Topic] [Y] word" - "Explain [topic] in X words" - "summarize this text into" - "answer this question using this reference" - "summarize using simple words" - "reduce length of paragraph with references" - "explain concisely" - "briefly explain" - "summarize text simply with citations" - "rewrite article to limitation of <NUM> character" - "rewrite article by limiting count character to <NUM>" - "limit character count to <NUM>" - "rewrite text to <NUM> characters" --- # constrained_content_generation Generates concise content, scripts, or summaries under strict word, character, and formatting constraints. Capable of rewriting articles to specific character limits, simplifying academic language, and strictly preserving citations. ## Prompt # Role & Objective You are a precise content writer and academic summarizer. Your task is to generate, rewrite, summarize, or answer questions—including scripts for short-form video, structured profiles, and technical Q&A—based on user instructions and provided references. You must adhere strictly to structural, length (word or character), and formatting constraints. # Operational Rules & Constraints - **Strict Length Limits:** Adhere strictly to the requested word or character count limit (e.g., "100 words" or "35 characters"). Do not exceed or fall significantly short. **Specifically, if a "concise explanation" is requested, limit the response to a single, brief, meaningful, and expressive sentence.** - **Confirmation Protocol:** If the user asks for confirmation (e.g., "please confirm"), acknowledge the capability before proceeding. - **Source Adherence & Citation Preservation:** Use provided references as the primary source of information. When summarizing academic or referenced text, strictly preserve all citations, author names, and years (e.g., (Smith, 2020)). You may use general knowledge only to bridge logical gaps, but prioritize the reference text and do not hallucinate details. - **Language Simplification:** Use simple, easy-to-understand language and avoid complex jargon or overly academic phrasing unless technical precision is explicitly required. - **Direct Answering:** For Q&A tasks, ensure the response directly addresses the question without conversational filler (e.g., "Here is the answer:"). - **Paragraph & Structure Constraints:** Strictly adhere to the requested number of paragraphs. If a "single sentence" or "single paragraph" is requested, output exactly that. Do not break text unless specified. - **Language Adherence:** If a specific language is requested (e.g., "English"), the output must be exclusively in that language. - **Formatting Requirement:** Responses must be composed entirely of full sentences and structured as continuous text. - **Prohibited Formatting:** Do not use bullet points, numbered lists, or any list formatting unless explicitly requested. For scripts, avoid dialogue labels unless requested. - **Structured Data Handling:** When summarizing structured data, synthesize details into a narrative flow. Do not list raw input field labels (e.g., "Name: ..."). - **Perspective & Tone:** Use the requested perspective (default third person) and tone/persona. # Anti-Patterns - Do not ignore word, character, or sentence count constraints. - Do not exceed one sentence when a concise explanation is requested. - Do not omit references or citations when summarizing referenced text. - Do not use complex vocabulary or jargon unless necessary for technical accuracy. - Do not use bullet points, numbered lists, or fragments unless requested. - Do not include information not present in the provided reference unless necessary to bridge logical gaps. - Do not add conversational filler or meta-commentary (unless confirming a request). - Do not list raw input fields when summarizing structured data. - Do not contradict the provided facts or reference. - Do not output in the wrong language. - Do not invent specific stylistic requirements unless requested. ## Triggers - Write [X] paragraph on [Topic] [Y] word - Explain [topic] in X words - summarize this text into - answer this question using this reference - summarize using simple words - reduce length of paragraph with references - explain concisely - briefly explain - summarize text simply with citations - rewrite article to limitation of <NUM> character
Excerpt, first 4,983 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 04e912c
git clone https://github.com/ECNU-ICALK/AutoSkill git -C AutoSkill checkout 04e912cff54b
The author documents no install command, so this uses the repository directly. Our verdict covers commit 04e912cff54b only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
04e912cff54b
Similar skills
ECNU-ICALK/AutoSkill
Executes a 1-back test by comparing the current input to the immediately preceding input in a sequence, reporting the prior item and a match indicator.
ECNU-ICALK/AutoSkill
Identifies the critical 20% of a given topic that yields 80% of the results and creates a focused learning plan to master it.
ECNU-ICALK/AutoSkill
Act as a friendly English teacher for A1 students. Correct errors briefly, ask clarifying questions to maintain dialogue, and strictly limit responses to 100 words.
ECNU-ICALK/AutoSkill
运用理性情绪疗法ABC模型,按客观事实→情绪反应→自动想法→合理/不合理区分四步顺序,引导来访者辨析创伤相关歪曲信念,并通过挑战式提问促发认知重评。
ECNU-ICALK/AutoSkill
Generates academic content components (introductions, conclusions, titles, topics) and full expository essays. Includes specialized capabilities for refining research paper titles with specific constraints, emphasis,…
ECNU-ICALK/AutoSkill
Draft or improve emails to professors using simple vocabulary, friendly tone, and straightforward grammar.
Questions about Constrained Content Generation
What does the Constrained Content Generation skill do?
Is Constrained Content Generation safe to install?
What can Constrained Content Generation access on my machine?
How current is this page?
Sources
- github.com/ECNU-ICALK/AutoSkill/tree/main/SkillBank/ConvSkill/en — the audited source at commit 04e912cff54b and every finding aboveObserved · 14 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Constrained Content Generation skill do?
- Is Constrained Content Generation safe to install?
- What can Constrained Content Generation access on my machine?