Agent skill

Task Verification Checkpoints

Verify output format, file coverage, and task alignment before completing

Install Task Verification Checkpoints

skills CLI

$ npx skills add HKUDS/OpenSpace --skill task-verification-checkpoints -a claude-code

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

GitHub CLI

$ gh skill install HKUDS/OpenSpace task-verification-checkpoints --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/task-verification-checkpoints .claude/skills/task-verification-checkpoints && 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/

Paste into Claude Code

Install the "task-verification-checkpoints" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/task-verification-checkpoints into .claude/skills/task-verification-checkpoints/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-verification-checkpoints", 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

$skill-installer install https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/task-verification-checkpoints

Type 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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill task-verification-checkpoints -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace task-verification-checkpoints --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmarks/gdpval/skills/task-verification-checkpoints .agents/skills/task-verification-checkpoints && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "task-verification-checkpoints" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/task-verification-checkpoints into .agents/skills/task-verification-checkpoints/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-verification-checkpoints", 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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill task-verification-checkpoints -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace task-verification-checkpoints --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmarks/gdpval/skills/task-verification-checkpoints .cursor/skills/task-verification-checkpoints && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "task-verification-checkpoints" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/task-verification-checkpoints into .cursor/skills/task-verification-checkpoints/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-verification-checkpoints", 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

$ gemini skills install https://github.com/HKUDS/OpenSpace.git --path benchmarks/gdpval/skills/task-verification-checkpoints

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill task-verification-checkpoints -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace task-verification-checkpoints --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmarks/gdpval/skills/task-verification-checkpoints .gemini/skills/task-verification-checkpoints && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "task-verification-checkpoints" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/task-verification-checkpoints into .gemini/skills/task-verification-checkpoints/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-verification-checkpoints", 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.

GitHub CLI

$ gh skill install HKUDS/OpenSpace task-verification-checkpoints

Installs 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).

skills CLI

$ npx skills add HKUDS/OpenSpace --skill task-verification-checkpoints -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmarks/gdpval/skills/task-verification-checkpoints .github/skills/task-verification-checkpoints && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "task-verification-checkpoints" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/task-verification-checkpoints into .github/skills/task-verification-checkpoints/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-verification-checkpoints", 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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill task-verification-checkpoints -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace task-verification-checkpoints --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmarks/gdpval/skills/task-verification-checkpoints .opencode/skills/task-verification-checkpoints && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "task-verification-checkpoints" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/task-verification-checkpoints into .opencode/skills/task-verification-checkpoints/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-verification-checkpoints", 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: task-verification-checkpoints
GitHub stars: 7.7k
Token cost: ~1.3k tokens
SKILL.md length: 297 words
Files: 2
Skills in repo: 199
Repo updated: Aug 12, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Verify output format, file coverage, and task alignment before completing

Works in 4 steps: Re-read the task prompt for explicit… → Check file extensions of all output files → Verify the actual file type matches the… → …
Tasks that involve Verification before completion
SKILL.md covers Overview, Three Critical Checkpoints, Pre-Completion Checklist and When to Apply, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Task Verification Checkpoints is an agent skill from HKUDS/OpenSpace. Verify output format, file coverage, and task alignment before completing

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Agent Workflows, covering Verification before completion. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

When your agent uses it

Tasks that involve Verification before completion

Example prompts

“/task-verification-checkpoints”

Requirements

Python 3

Workflow steps

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

Re-read the task prompt for explicit format requirements
Check file extensions of all output files
Verify the actual file type matches the extension
Confirm against any format specifications (e.g., "revised PDF report")

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

Task Verification Checkpoints loads about 1.3k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 297 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~26
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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). 297 words, ~1,256 tokens.

Download SKILL.mdSave it as .claude/skills/task-verification-checkpoints/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: task-verification-checkpoints
description: Verify output format, file coverage, and task alignment before completing

Task Verification Checkpoints

Before declaring a task as <COMPLETE>, perform these verification checks to ensure the deliverable matches requirements and prevents wrong-task completion.

Overview

This skill prevents common failures where agents:

Create outputs in wrong formats (PDF vs PPTX vs DOCX)
Skip processing some reference files
Drift from the actual task requirements

Three Critical Checkpoints

Checkpoint 1: Output Format Verification

Question: Does the output file format match task requirements?

Actions:

Re-read the task prompt for explicit format requirements
Check file extensions of all output files
Verify the actual file type matches the extension
Confirm against any format specifications (e.g., "revised PDF report")

Example validation:

python

def verify_output_format(task_prompt, output_files):
    """Check if output format matches task requirements."""
    required_format = extract_format_requirement(task_prompt)  # e.g., 'pdf', 'pptx'
    
    for f in output_files:
        actual_ext = f.split('.')[-1].lower()
        if actual_ext != required_format:
            return False, f"Expected .{required_format}, got .{actual_ext}"
    
    return True, "Format verified"

Checkpoint 2: Reference File Coverage

Question: Were ALL reference/input files processed?

Actions:

List all files mentioned in the task as inputs
Confirm each was read/analyzed/used (check file access logs)
Document which content from each file contributed to output
Flag any unprocessed reference files

Example validation:

python

def verify_reference_coverage(task_files, accessed_files):
    """Ensure all reference files were actually processed."""
    missing = set(task_files) - set(accessed_files)
    if missing:
        return False, f"Unprocessed files: {missing}"
    return True, "All references processed"

Checkpoint 3: Task Alignment Verification

Question: Does the deliverable address the ACTUAL task prompt?

Actions:

Re-read the original task description verbatim
Compare output purpose against stated task goal
Check for scope creep or task drift
Verify the output solves the stated problem (not a different one)

Example validation:

python

def verify_task_alignment(task_prompt, output_description):
    """Confirm output addresses the actual task."""
    task_verbs = extract_action_verbs(task_prompt)  # e.g., 'review', 'revise', 'create'
    output_verbs = extract_action_verbs(output_description)
    
    if not set(task_verbs).issubset(set(output_verbs)):
        return False, "Output actions don't match task requirements"
    
    return True, "Task alignment verified"

Pre-Completion Checklist

Execute this checklist before marking ANY task complete:

python

def pre_completion_verification(task_prompt, output_files, reference_files):
    """
    Complete verification before declaring task done.
    Returns (success, message) tuple.
    """
    checks = []
    
    # Check 1: Format
    format_ok, format_msg = verify_output_format(task_prompt, output_files)
    checks.append(('Format', format_ok, format_msg))
    
    # Check 2: Coverage
    coverage_ok, coverage_msg = verify_reference_coverage(reference_files, get_accessed_files())
    checks.append(('Coverage', coverage_ok, coverage_msg))
    
    # Check 3: Alignment
    alignment_ok, alignment_msg = verify_task_alignment(task_prompt, get_output_summary())
    checks.append(('Alignment', alignment_ok, alignment_msg))
    
    # Report results
    all_passed = all(ok for _, ok, _ in checks)
    
    if not all_passed:
        print("❌ VERIFICATION FAILED - Do not mark complete")
        for name, ok, msg in checks:
            status = "✓" if ok else "✗"
            print(f"  {status} {name}: {msg}")
        return False, "Verification failed"
    
    print("✓ All verification checkpoints passed")
    return True, "Ready for completion"

When to Apply

Use this skill whenever:

Creating deliverables from input/reference files
Task specifies output format requirements
Multiple files must be processed/analyzed
Task involves transformation, revision, or synthesis
Always before any <COMPLETE> declaration

Common Failure Modes to Catch

Failure Type	Example	Prevention
Format mismatch	Created PPTX when PDF requested	Checkpoint 1
Incomplete coverage	Skipped Photographs.zip	Checkpoint 2
Task drift	Created new report instead of revising existing	Checkpoint 3
Assumption errors	Assumed format without verification	All checkpoints

Quick Reference

Before <COMPLETE>:
  □ Output format matches requirements?
  □ All reference files processed?
  □ Deliverable addresses actual task?
  
If ANY box unchecked → Do NOT complete, fix first.

Files

SKILL.md and 1 other file in benchmarks/gdpval/skills/task-verification-checkpoints of HKUDS/OpenSpace.

SKILL.md
.skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Task Verification Checkpoints 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.

Task Verification Checkpoints compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Task Verification Checkpoints this skillHKUDS/OpenSpace	7.7k	—	~1.3k	Automated safety check: Pass	MIT	1 mo ago
Show Me Your Work Decision Logcursor/plugins	10k	9 repos	~1.6k	Automated safety check: Pass	None	today
Verification Before Completionfarm-fe/farm	5.6k	45 repos	~1k	Automated safety check: Pass	MIT	15 days ago
Scope Creep Guardlennney/stop-that-shit	2.5k	1 repos	~2k	Automated safety check: Pass	MIT	2 days ago
PUA High-Agency Governancetanweai/pua	20k	—	~502	Automated safety check: Pass	MIT	28 days ago
Incremental Implementationaddyosmani/agent-skills	102k	1 repos	~2.3k	Automated safety check: Pass	MIT	3 days ago

Similar skills

Show Me Your Work Decision Log
cursor/plugins
Official
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
10k GitHub starsUsed in 9 repos~1.6k tokens
Agent WorkflowsAuto-check passed
Verification Before Completion
farm-fe/farm
A skill your agent uses when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any…
5.6k GitHub starsUsed in 45 repos~1k tokens
Agent WorkflowsAuto-check passed
Scope Creep Guard
lennney/stop-that-shit
Keeps an agent focused on the requested work by applying a five-step ladder that checks for direct solutions, real gaps and speculative defenses before adding anything.
2.5k GitHub starsUsed in 1 repo~2k tokens
Agent WorkflowsAuto-check passed
PUA High-Agency Governance
tanweai/pua
Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.
20k GitHub stars~502 tokensUpdated 28 days ago
Agent WorkflowsAuto-check passed
Incremental Implementation
addyosmani/agent-skills
Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.
102k GitHub starsUsed in 1 repo~2.3k tokens
Agent WorkflowsAuto-check passed
PUA Loop
tanweai/pua
Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.
20k GitHub stars~1.1k tokensUpdated 28 days ago
Agent WorkflowsAuto-check passed

Questions about Task Verification Checkpoints

What does Task Verification Checkpoints do?

Verify output format, file coverage, and task alignment before completing. Task Verification Checkpoints is an agent skill from HKUDS/OpenSpace.

When should I use Task Verification Checkpoints?

Task Verification Checkpoints fits situations like: tasks that involve Verification before completion.

How do I install Task Verification Checkpoints in Claude Code?

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

How do I install Task Verification Checkpoints in Codex?

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

Can I use Task Verification Checkpoints 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 task-verification-checkpoints -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-verification-checkpoints, .gemini/skills/task-verification-checkpoints, .github/skills/task-verification-checkpoints and .opencode/skills/task-verification-checkpoints in your project.

What does Task Verification Checkpoints need to run?

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

Does Task Verification Checkpoints 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 Task Verification Checkpoints 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 Task Verification Checkpoints use?

Task Verification Checkpoints 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 Task Verification Checkpoints use?

About 1.3k tokens (SKILL.md is roughly 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 Task Verification Checkpoints?

Skills that share tags, products or a category with Task Verification Checkpoints: Show Me Your Work Decision Log (cursor/plugins, 10k stars), Verification Before Completion (farm-fe/farm, 5.6k stars), Scope Creep Guard (lennney/stop-that-shit, 2.5k stars) and PUA High-Agency Governance (tanweai/pua, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Verification Checkpoints?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,743 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.

Install Task Verification Checkpoints

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Task Verification Checkpoints

Overview

Three Critical Checkpoints

Checkpoint 1: Output Format Verification

Checkpoint 2: Reference File Coverage

Checkpoint 3: Task Alignment Verification

Pre-Completion Checklist

When to Apply

Common Failure Modes to Catch

Quick Reference

Files

Compare with similar skills

Similar skills

More from HKUDS/OpenSpace

Related

Questions about Task Verification Checkpoints