Agent skill

Deliverable Step Report

by CurryTang in CurryTang/Amadeus

Generate a deliverable report for each research step using template.md and reference/xguideline.md, then persist it to .researchops/deliverables and upload to SSH target when the project location is…

No licenceAuto-check passed

Install Deliverable Step Report

skills CLI
$ npx skills add CurryTang/Amadeus --skill deliverable-step-report -a claude-code

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

GitHub CLI
$ gh skill install CurryTang/Amadeus deliverable-step-report --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/CurryTang/Amadeus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deliverable-step-report .claude/skills/deliverable-step-report && 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
deliverable-step-report
GitHub stars
176
Token cost
~299 tokens
SKILL.md length
99 words
Files
2
Skills in repo
13
Repo updated
First seen
Licence
None found

At a glance

Generate a deliverable report for each research step using template.md and reference/xguideline.md, then persist it to .researchops/deliverables and upload to SSH target when the project location is…

  • Works in 5 steps: Render report content from template.md. → Follow quality gates in… → Persist report path:… → …
  • SKILL.md covers Required Structure, Behavior, Runtime Inputs and Output Contract
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deliverable Step Report is an agent skill from CurryTang/Amadeus. Generate a deliverable report for each research step using template.md and reference/xguideline.md, then persist it to .researchops/deliverables and upload to SSH target when the project location is remote.

Its SKILL.md is about 300 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `template.md`).

The repository describes itself as: Your personal AI research assistant that automatically reads, summarizes, organizes, and acts on academic papers.

Example prompts

  • “/deliverable-step-report”

Workflow steps

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

  1. Render report content from template.md.
  2. Follow quality gates in reference/x_guideline.md.
  3. Persist report path: .researchops/deliverables//.md.
  4. If project location is SSH, upload report to remote project path automatically.
  5. Attach report as a run artifact (kind=deliverable_report).

What it can do on your machine

Read from SKILL.md and the folder at commit 72f0e2f. 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

Deliverable Step Report loads about 299 tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 99 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~299

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 99 words (~299 tokens).

“This skill defines a deterministic report format for each step/node run.”

— opening of SKILL.md by CurryTang
name
deliverable-step-report

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/deliverable-step-report of CurryTang/Amadeus.

  • SKILL.md
  • template.md

Open the folder on GitHubat commit 72f0e2f

Compare with similar skills

Deliverable Step Report 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.

Deliverable Step Report compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deliverable Step Report this skillCurryTang/Amadeus176—~299Automated safety check: PassNone
Deliverable CompletionHKUDS/OpenSpace7.8k—~731Automated safety check: PassMIT
Review Team Deliverablesruvnet/ruflo74k—~207Automated safety check: PassMIT
Multi Deliverable TrackingHKUDS/OpenSpace7.8k—~1.4kAutomated safety check: PassMIT
Finalize Zip DeliverableHKUDS/OpenSpace7.8k—~1.5kAutomated safety check: NotesMIT
Zip Deliverable FinalizationHKUDS/OpenSpace7.8k—~787Automated safety check: PassMIT

Similar skills

  • Deliverable Completion

    HKUDS/OpenSpace

    Clarifies that file creation tasks are complete when the deliverable is successfully written—no submission step required

    7.8k GitHub stars~731 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Checks an AI team run against its acceptance criteria using the evidence bundle.

    74k GitHub stars~207 tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Track and complete all required deliverables before finishing a task

    7.8k GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Ensures codebase deliverables are properly archived into a ZIP file before marking task complete

    7.8k GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check: notes
  • Ensure codebase deliverables are properly packaged as ZIP exports in a dedicated final step

    7.8k GitHub stars~787 tokensUpdated 1 mo ago
    Auto-check passed
  • Zip Export Deliverable

    HKUDS/OpenSpace

    Ensures codebase deliverables are properly exported as ZIP archives through a dedicated finalization step

    7.8k GitHub stars~768 tokensUpdated 1 mo ago
    Auto-check passed

More from CurryTang/Amadeus

All 13 skills in this repo
  • Research Lit

    CurryTang/Amadeus

    Search and analyze research papers, find related work, summarize key ideas.

    176 GitHub starsUsed in 5 repos~963 tokens
    Auto-check: notes
  • Repo Sync Updater

    CurryTang/Amadeus

    Synchronize a local or WSL clone with its upstream branch and verify backend runtime prerequisites for this project.

    176 GitHub stars~564 tokensUpdated 6 mo ago
    Auto-check passed
  • Auto Review Loop

    CurryTang/Amadeus

    Autonomous multi-round research review loop. An agent skill from CurryTang/Amadeus.

    176 GitHub stars~4.3k tokensUpdated 6 mo ago
    Auto-check: notes
  • Sync Workspace

    CurryTang/Amadeus

    Sync local and remote project files bidirectionally. An agent skill from CurryTang/Amadeus.

    176 GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check: notes
  • Todo To Node

    CurryTang/Amadeus

    Convert a project TODO item into a ResearchOps tree node via LLM.

    176 GitHub stars~691 tokensUpdated 6 mo ago
    Auto-check passed
  • GPU Status

    CurryTang/Amadeus

    Show GPU availability across all SSH servers listed in this project's CLAUDE.md.

    176 GitHub stars~862 tokensUpdated 6 mo ago
    Auto-check: warnings

Questions about Deliverable Step Report

What does Deliverable Step Report do?

Generate a deliverable report for each research step using template.md and reference/xguideline.md, then persist it to .researchops/deliverables and upload to SSH target when the project location is…. Deliverable Step Report is an agent skill from CurryTang/Amadeus.researchops/deliverables and upload to SSH target when the project location is remote.

How do I install Deliverable Step Report in Claude Code?

Run `npx skills add CurryTang/Amadeus --skill deliverable-step-report -a claude-code`. Or copy the skill folder (skills/deliverable-step-report in CurryTang/Amadeus) into .claude/skills/deliverable-step-report in your project. Claude Code loads it when a task matches its description.

How do I install Deliverable Step Report in Codex?

Run `npx skills add CurryTang/Amadeus --skill deliverable-step-report -a codex`. Or copy the skill folder (skills/deliverable-step-report in CurryTang/Amadeus) into .agents/skills/deliverable-step-report in your project. Codex loads it when a task matches its description.

Can I use Deliverable Step Report 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 CurryTang/Amadeus --skill deliverable-step-report -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deliverable-step-report, .gemini/skills/deliverable-step-report, .github/skills/deliverable-step-report and .opencode/skills/deliverable-step-report in your project.

What does Deliverable Step Report need to run?

SKILL.md names no scripts, command-line tools or credentials: Deliverable Step Report is instructions for the agent only.

Does Deliverable Step Report 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 Deliverable Step Report 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 Deliverable Step Report use?

No licence was found for Deliverable Step Report or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Deliverable Step Report use?

About 299 tokens (SKILL.md is roughly 1.2k 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 Deliverable Step Report?

Skills that share tags, products or a category with Deliverable Step Report: Deliverable Completion (HKUDS/OpenSpace, 7.8k stars), Review Team Deliverables (ruvnet/ruflo, 74k stars), Multi Deliverable Tracking (HKUDS/OpenSpace, 7.8k stars) and Finalize Zip Deliverable (HKUDS/OpenSpace, 7.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deliverable Step Report?

CurryTang (a GitHub user) maintains it in CurryTang/Amadeus, which has 176 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on March 25, 2026.

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