New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Multi Deliverable Tracking

by HKUDS in HKUDS/OpenSpace

Track and complete all required deliverables before finishing a task

MITAuto-check passed

Install Multi Deliverable Tracking

skills CLI
$ npx skills add HKUDS/OpenSpace --skill multi-deliverable-tracking -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace multi-deliverable-tracking --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/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/multi-deliverable-tracking .claude/skills/multi-deliverable-tracking && 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
multi-deliverable-tracking
GitHub stars
7.8k
Token cost
~1.4k tokens
SKILL.md length
480 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Track and complete all required deliverables before finishing a task

  • Works in 6 steps: Identify All Deliverables Upfront → Create a Completion Tracker → 5: Filesystem Verification [MANDATORY… → …
  • SKILL.md covers Purpose, Core Workflow, Common Pitfalls to Avoid and Code Example: Tracker Template, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Multi Deliverable Tracking is an agent skill from HKUDS/OpenSpace. Track and complete all required deliverables before finishing a task

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

Example prompts

  • “/multi-deliverable-tracking”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Identify All Deliverables Upfront
  2. Create a Completion Tracker
  3. 5: Filesystem Verification [MANDATORY BEFORE COMPLETION]
  4. Work Through Deliverables Systematically
  5. Final Verification Before Stopping
  6. Self-Check Questions

What it can do on your machine

Read from SKILL.md and the folder at commit 3827781. 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 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

Multi Deliverable Tracking loads about 1.4k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 480 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 480 words, ~1,420 tokens.

Download SKILL.mdSave it as .claude/skills/multi-deliverable-tracking/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
multi-deliverable-tracking
description
Track and complete all required deliverables before finishing a task

Multi-Deliverable Task Completion

Purpose

Ensure ALL required outputs are completed before concluding a task, preventing premature task termination when multiple deliverables are required. This skill includes mandatory enforcement steps that MUST be followed.

Core Workflow

Step 1: Identify All Deliverables Upfront

CRITICAL: You MUST complete this step before producing ANY deliverable or taking any other action.

At task start, explicitly enumerate EVERY required output:

  • Parse task requirements carefully for action verbs: "create", "generate", "produce", "deliver", "write", "send"
  • Count distinct deliverables (files, reports, emails, code modules, analyses, etc.)
  • Document this list visibly in working notes
  • Note any dependencies between deliverables

MANDATORY OUTPUT FORMAT: Before any other work, output this exact format:

DELIVERABLES_IDENTIFIED:
1. [filename/description] - [brief description]
2. [filename/description] - [brief description]
...
TOTAL_DELIVERABLES: N

Example identification:

Required Deliverables:
1. [ ] Email to Juvoxa CEO
2. [ ] Follow-up analysis report
Total: 2 deliverables
Step 2: Create a Completion Tracker

CRITICAL: This tracker MUST be created and visible throughout task execution.

Maintain a visible checklist throughout task execution:

DELIVERABLE TRACKER
===================
[ ] Deliverable 1: [brief description]
[ ] Deliverable 2: [brief description]
[ ] Deliverable 3: [brief description]

Completed: 0/3

Update this tracker AFTER each deliverable is fully completed (not just started).

Step 2.5: Filesystem Verification [MANDATORY BEFORE COMPLETION]

Before considering any deliverable complete, verify it exists:

  • For file deliverables: Use list_dir or run_shell (ls/cat) to confirm the file exists
  • For output deliverables: Verify the output was actually produced in the response stream
  • Document verification with: [✓] filename verified in filesystem
Step 3: Work Through Deliverables Systematically
  • Complete each deliverable fully before marking it done
  • Update the tracker immediately after completion
  • If a deliverable fails, note the failure but continue to others if possible
  • Return to failed items after completing others
Step 4: Final Verification Before Stopping

Before concluding the task, run this mandatory checklist: CRITICAL ENFORCEMENT: You are BLOCKED from outputting <COMPLETE> until this verification passes.

FINAL VERIFICATION (REQUIRED BEFORE <COMPLETE>)
==================
1. Review original task requirements
2. Count total deliverables identified: ___
3. Count deliverables marked complete: ___
4. Do counts match? YES/NO
5. If NO: Identify missing deliverables and complete them
6. If YES: Verify each deliverable exists and meets quality standards
7. Filesystem verification (REQUIRED):
   - [ ] file1.ext: VERIFIED (list_dir/run_shell confirmed)
   - [ ] file2.ext: VERIFIED (list_dir/run_shell confirmed)

**BLOCKING RULE:** If counts do not match OR any file cannot be verified in the filesystem, you MUST:
1. NOT output <COMPLETE>
2. Identify the missing/unverified deliverables
3. Complete and verify them
4. Re-run this verification checklist

**Only output <COMPLETE> when all deliverables are verified present in the filesystem or output stream.**

Only stop when all deliverables are verified complete.

Show full SKILL.md (210 more words)Show less
Step 5: Self-Check Questions

Before marking task complete, ask:

  • "Did I create EVERY output the task requested?"
  • "Are there any deliverables I started but didn't finish?"
  • "Would someone reviewing my work see all required outputs?"
  • "Have I verified EACH deliverable exists in the filesystem using list_dir or run_shell?"
  • "Is my DELIVERABLES_IDENTIFIED output present and accurate?"

Common Pitfalls to Avoid

❌ Stopping after first deliverable - Just because one output is done doesn't mean the task is complete ❌ Stopping after first deliverable - Just because one output is done doesn't mean the task is complete

❌ Outputting <COMPLETE> without filesystem verification - You must verify files exist before completion

❌ Skipping DELIVERABLES_IDENTIFIED output - This mandatory output must appear before any work begins

❌ Assuming implicit completion - Don't assume related outputs are "part of" a main deliverable unless explicitly stated

❌ Losing track mid-task - The tracker must stay visible and updated throughout

❌ Counting drafts as complete - Only mark done when the deliverable meets quality standards

Code Example: Tracker Template

python
# Deliverable tracking template
deliverables = {
    "email_to_ceo": {"status": "pending", "file": "ceo_email.txt"},
    "analysis_report": {"status": "pending", "file": "analysis.pdf"},
    "summary_doc": {"status": "pending", "file": "summary.docx"},
}

def mark_complete(name):
    deliverables[name]["status"] = "complete"
    print(f"✓ {name} completed")
    print(f"Progress: {sum(1 for d in deliverables.values() if d['status'] == 'complete')}/{len(deliverables)}")

def all_complete():
    return all(d["status"] == "complete" for d in deliverables.values())

When to Apply This Skill

Use this pattern whenever a task involves:

  • Multiple files to create
  • Several analyses or reports
  • Multiple communications (emails, messages)
  • Code with multiple modules/components
  • Any task with enumerated requirements (1), 2), 3)...)

Remember

The task is NOT complete until ALL deliverables are complete. One done ≠ all done.

© HKUDS, 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 benchmarks/gdpval/skills/multi-deliverable-tracking of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Multi Deliverable Tracking 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.

Multi Deliverable Tracking compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Multi Deliverable Tracking this skillHKUDS/OpenSpace7.8k—~1.4kAutomated safety check: PassMIT
Cost Trackingaffaan-m/ECC276k1 repos~1.3kAutomated safety check: PassMIT
Requirementsrizsotto/Bear6.5k—~2kAutomated safety check: PassGPL-3.0
TrackingBuilderIO/agent-native7.1k—~8kAutomated safety check: PassNone
Time Trackingsickn33/agentic-awesome-skills47k1 repos~3.8kAutomated safety check: PassMIT
Horizon Trackruvnet/ruflo74k—~744Automated safety check: NotesMIT

Similar skills

  • Cost Tracking

    affaan-m/ECC

    Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.

    276k GitHub starsUsed in 1 repo~1.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Requirements

    rizsotto/Bear

    Write, modify, or review a requirement file under docs/requirements -- pick the single owning file, keep the text contract-only, name IDs so they need no explanation, and verify cross-references and…

    6.5k GitHub stars~2k tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Tracking

    BuilderIO/agent-native

    Server-side analytics tracking with pluggable providers. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~8k tokensUpdated today
    Backend & APIsAuto-check passed

  • Time Tracking

    sickn33/agentic-awesome-skills

    Time entry register: employee, project, client, task, hours, billable flag, rate and amount, invoice and approver.

    47k GitHub starsUsed in 1 repo~3.8k tokens
    Productivity & AutomationAuto-check passed

  • Horizon Track

    ruvnet/ruflo

    Track long-horizon objectives across multiple sessions with milestone checkpoints, progress persistence, and drift detection

    74k GitHub stars~744 tokensUpdated today
    Product & Project ManagementAuto-check: notes

  • Cost Track

    ruvnet/ruflo

    Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace

    74k GitHub stars~773 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

More from HKUDS/OpenSpace

All 199 skills in this repo

  • Audio Track Production Workflow

    HKUDS/OpenSpace

    Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.

    7.8k GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed

  • Cascade Failure Recovery

    HKUDS/OpenSpace

    Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

    7.8k GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed

  • Sandbox Code Execution Fallback

    HKUDS/OpenSpace

    Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.

    7.8k GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed

  • Code Execution Fallback

    HKUDS/OpenSpace

    A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.

    7.8k GitHub stars~652 tokensUpdated 1 mo ago
    Auto-check passed

  • Code Execution Fallback and Path Anchoring

    HKUDS/OpenSpace

    Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Code Execution Fallback E81068

    HKUDS/OpenSpace

    Fallback workflow for executing Python code when executecodesandbox fails repeatedly

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Multi Deliverable Tracking

What does Multi Deliverable Tracking do?

Track and complete all required deliverables before finishing a task. Multi Deliverable Tracking is an agent skill from HKUDS/OpenSpace.

How do I install Multi Deliverable Tracking in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill multi-deliverable-tracking -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/multi-deliverable-tracking in HKUDS/OpenSpace) into .claude/skills/multi-deliverable-tracking in your project. Claude Code loads it when a task matches its description.

How do I install Multi Deliverable Tracking in Codex?

Run `npx skills add HKUDS/OpenSpace --skill multi-deliverable-tracking -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/multi-deliverable-tracking in HKUDS/OpenSpace) into .agents/skills/multi-deliverable-tracking in your project. Codex loads it when a task matches its description.

Can I use Multi Deliverable Tracking 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 HKUDS/OpenSpace --skill multi-deliverable-tracking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/multi-deliverable-tracking, .gemini/skills/multi-deliverable-tracking, .github/skills/multi-deliverable-tracking and .opencode/skills/multi-deliverable-tracking in your project.

What does Multi Deliverable Tracking need to run?

SKILL.md names no scripts, command-line tools or credentials: Multi Deliverable Tracking is instructions for the agent only. Our summary lists: Python 3.

Does Multi Deliverable Tracking 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 Multi Deliverable Tracking 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 Multi Deliverable Tracking use?

Multi Deliverable Tracking 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 Multi Deliverable Tracking use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Multi Deliverable Tracking?

Skills that share tags, products or a category with Multi Deliverable Tracking: Cost Tracking (affaan-m/ECC, 276k stars), Requirements (rizsotto/Bear, 6.5k stars), Tracking (BuilderIO/agent-native, 7.1k stars) and Time Tracking (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Multi Deliverable Tracking?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,750 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.

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