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

Approve Verification

by xinzhuwang-wxz in xinzhuwang-wxz/OpenPE

Human gate for reviewing and approving full verification after Phase 5

GPL-3.0Auto-check passed

Install Approve Verification

skills CLI
$ npx skills add xinzhuwang-wxz/OpenPE --skill approve-verification -a claude-code

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

GitHub CLI
$ gh skill install xinzhuwang-wxz/OpenPE approve-verification --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/xinzhuwang-wxz/OpenPE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/approve-verification .claude/skills/approve-verification && 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
approve-verification
GitHub stars
101
Token cost
~1.5k tokens
SKILL.md length
507 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
GPL-3.0

At a glance

Human gate for reviewing and approving full verification after Phase 5

  • Works in 4 steps: Verify State → Gather Review Materials → Present to User → …
  • SKILL.md covers Step 1: Verify State, Step 2: Gather Review Materials, Step 3: Present to User and Step 4: Wait for User Response
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Approve Verification is an agent skill from xinzhuwang-wxz/OpenPE. Human gate for reviewing and approving full verification after Phase 5

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is GPL-3.0.

Example prompts

  • “/approve-verification”

Workflow steps

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

  1. Verify State
  2. Gather Review Materials
  3. Present to User
  4. Wait for User Response

What it can do on your machine

Read from SKILL.md and the folder at commit f29b438. 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

Approve Verification loads about 1.5k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 507 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 xinzhuwang-wxz/OpenPE at commit f29b438, republished under its GPL-3.0 licence (© xinzhuwang-wxz). 507 words, ~1,505 tokens.

Download SKILL.mdSave it as .claude/skills/approve-verification/SKILL.md (or your agent's skills folder).
name
approve-verification
description
Human gate for reviewing and approving full verification after Phase 5
user-invocable
true

/approve-verification -- Human Gate for Full Verification

This command implements the human gate between Phase 5 (partial verification) and Phase 6 (full verification). The analysis pauses here until a human explicitly approves.

Arguments: $ARGUMENTS (ignored)

Step 1: Verify State

  1. Read STATE.md. Confirm the current status is human_gate and the current phase is 5.

    • If the status is NOT human_gate, report: "The analysis is not at the human gate. Current status: {status}, phase: {phase}. This command can only be run after Phase 4b review passes." Stop.
    • If Phase 4b has not passed review, report: "Phase 5 review has not yet passed. Run the Phase 5 review first." Stop.

  2. Read analysis_config.yaml. Confirm verification.approved_for_verification is false.

    • If already true, report: "Verification has already been approved. Phase 6 can proceed." Stop.

Step 2: Gather Review Materials

Read the following files and present a summary to the user:

Draft Analysis Note
  • Read the latest ANALYSIS_NOTE_DRAFT*.md from phase5_inference/5b_partial/exec/
  • Summarize: title, analysis question, key methodology choices, 10% observed results, main conclusions
Verification Checklist
  • Read the latest VERIFICATION_CHECKLIST*.md from phase5_inference/5b_partial/exec/
  • Present each checklist item with its status (passed/failed/not evaluated)

The checklist should cover:

  1. Background model validated (closure tests pass in all validation regions)
  2. Systematic uncertainties evaluated and fit model stable
  3. Expected results physically sensible
  4. Signal injection tests confirm fit recovers injected signals
  5. 10% partial verification shows no unexpected pathologies
  6. All agent review cycles resolved (arbiter PASS)
  7. Draft analysis note reviewed and considered publication-ready modulo full observed results
4-bot Review Result
  • Read the latest arbiter file from phase5_inference/5b_partial/review/arbiter/
  • Summarize the arbiter's decision and any residual Category B/C items
Key Results Summary
  • Read the latest INFERENCE_PARTIAL*.md from phase5_inference/5b_partial/exec/
  • Report: expected vs 10% observed results, goodness-of-fit, any notable nuisance parameter pulls

Step 3: Present to User

Format the summary clearly:

================================================================
         VERIFICATION APPROVAL REQUEST -- {analysis_name}
================================================================

DRAFT ANALYSIS NOTE SUMMARY
----------------------------
{summary of the draft note -- 5-10 lines covering the analysis,
methodology, and 10% results}

VERIFICATION CHECKLIST
--------------------
[x] 1. Background model validated -- closure tests pass in all validation regions
[x] 2. Systematic uncertainties evaluated -- fit model stable
[x] 3. Expected results physically sensible
[x] 4. Signal injection tests pass
[x] 5. 10% partial verification -- no unexpected pathologies
[x] 6. Agent review cycles resolved -- arbiter PASS
[x] 7. Draft analysis note reviewed -- publication-ready

4-BOT REVIEW RESULT
--------------------
Decision: PASS
Iterations: {N}
Residual items: {list any B/C items}

KEY RESULTS (10% data)
-----------------------
Expected: {expected result}
Observed (10%): {observed result}
Goodness-of-fit: {GoF metric}
Notable NP pulls: {any pulls > 1 sigma}

================================================================
ARTIFACTS FOR DETAILED REVIEW:
  - Draft note: phase5_inference/5b_partial/exec/ANALYSIS_NOTE_DRAFT*.md
  - Partial results: phase5_inference/5b_partial/exec/INFERENCE_PARTIAL*.md
  - Expected results: phase5_inference/5a_expected/exec/INFERENCE_EXPECTED*.md
  - Checklist: phase5_inference/5b_partial/exec/VERIFICATION_CHECKLIST*.md
  - Arbiter review: phase5_inference/5b_partial/review/arbiter/
================================================================

Please review the above and respond with one of:
  APPROVE          -- Proceed to full verification (Phase 6)
  REQUEST_CHANGES  -- Send Phase 4b back for revisions (describe what to change)
  HALT             -- Stop the analysis (provide reason)
Show full SKILL.md (210 more words)Show less

Step 4: Wait for User Response

The user will respond with one of three decisions. Handle each:

APPROVE
  1. Update analysis_config.yaml: set verification.approved_for_verification: true
  2. Update STATE.md:
    • Phase 5 status: passed (with note: "human approved")
    • Current phase: 6
    • Status: executing
    • Timestamp
  3. Report: "Full verification approved. Proceeding to Phase 6."
  4. Begin Phase 4c execution:
    • Spawn systematics-fitter to run the full fit on complete dataset
    • Spawn cross-checker to validate consistency
    • Then run 1-bot review (with plot-validator)
    • Continue the pipeline through Phase 5
REQUEST_CHANGES
  1. Update STATE.md:
    • Status: executing (Phase 5 re-execution)
    • Add note: "Human requested changes: {description}"
    • Timestamp
  2. Re-spawn the Phase 4b executor via SendMessage with:
    • All original inputs
    • The human's change request as additional input
    • The previous draft note and partial results
    • Instruction: "The human reviewer has requested changes before approving verification. Address the following: {user's description}. Produce updated artifacts."
  3. After executor completes, re-run 4-bot review (with plot-validator) for Phase 4b
  4. On PASS, return to the human gate (present the updated summary)
HALT
  1. Update STATE.md:
    • Status: halted
    • Add to Blockers: "Human halted analysis at verification gate. Reason: {user's reason}"
    • Timestamp
  2. Update analysis_config.yaml: verification.approved_for_verification: false
  3. Report: "Analysis halted at human request. Reason: {reason}. To resume, the user must address the concerns and re-run /approve-verification."

© xinzhuwang-wxz, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/approve-verification of xinzhuwang-wxz/OpenPE.

Open the folder on GitHubat commit f29b438

Compare with similar skills

Approve Verification 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.

Approve Verification compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Approve Verification this skillxinzhuwang-wxz/OpenPE101—~1.5kAutomated safety check: PassGPL-3.0
Phase Gated Debuggingsickn33/agentic-awesome-skills47k2 repos~790Automated safety check: PassMIT
Phase Gate CheckDonchitos/Claude-Code-Game-Studios26k—~2.2kAutomated safety check: NotesMIT
Operator Approval Loopaffaan-m/ECC277k—~3.3kAutomated safety check: PassMIT
Gate Testsvercel/next.js143k—~2.8kAutomated safety check: PassMIT
Gateplugin87/ux-ui-agent-skills1.6k—~532Automated safety check: PassMIT

Similar skills

  • Phase Gated Debugging

    sickn33/agentic-awesome-skills

    A skill your agent uses when debugging any bug. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~790 tokens
    DevelopmentAuto-check passed

  • Phase Gate Check

    Donchitos/Claude-Code-Game-Studios

    Checks whether a game project is ready to move to its next production stage and returns a PASS, CONCERNS, NOT ASSESSED or FAIL verdict with blockers.

    26k GitHub stars~2.2k tokensUpdated 3 days ago
    Game DevelopmentAuto-check: notes

  • Operator Approval Loop

    affaan-m/ECC

    Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.

    277k GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Gate Tests

    vercel/next.js

    Official

    How to use the @gate / @force-gate test directives instead of it.skip or fake-green skip patterns.

    143k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Gate

    plugin87/ux-ui-agent-skills

    Run the one-command quality gate and report the real N/N result.

    1.6k GitHub stars~532 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed

  • Brain Ingest Gate

    garrytan/gbrain

    Pre-write quality gate for content entering the brain. An agent skill from garrytan/gbrain.

    31k GitHub stars~3.9k tokensUpdated today
    Testing & QAAuto-check passed

More from xinzhuwang-wxz/OpenPE

  • Review Phase

    xinzhuwang-wxz/OpenPE

    Run the review cycle for a completed phase artifact with plot validation

    101 GitHub stars~3.2k tokensUpdated 6 mo ago
    Auto-check passed

  • Run Analysis

    xinzhuwang-wxz/OpenPE

    Initialize and run the full automated analysis pipeline from analysis question to final documentation

    101 GitHub stars~2.7k tokensUpdated 6 mo ago
    Auto-check passed

  • Check Status

    xinzhuwang-wxz/OpenPE

    Display current analysis pipeline status. An agent skill from xinzhuwang-wxz/OpenPE.

    101 GitHub stars~617 tokensUpdated 6 mo ago
    Auto-check passed

  • Run Phase

    xinzhuwang-wxz/OpenPE

    Execute a single phase of the analysis pipeline by phase identifier

    101 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Approve Verification

What does Approve Verification do?

Human gate for reviewing and approving full verification after Phase 5. Approve Verification is an agent skill from xinzhuwang-wxz/OpenPE.

How do I install Approve Verification in Claude Code?

Run `npx skills add xinzhuwang-wxz/OpenPE --skill approve-verification -a claude-code`. Or copy the skill folder (.claude/skills/approve-verification in xinzhuwang-wxz/OpenPE) into .claude/skills/approve-verification in your project. Claude Code loads it when a task matches its description.

How do I install Approve Verification in Codex?

Run `npx skills add xinzhuwang-wxz/OpenPE --skill approve-verification -a codex`. Or copy the skill folder (.claude/skills/approve-verification in xinzhuwang-wxz/OpenPE) into .agents/skills/approve-verification in your project. Codex loads it when a task matches its description.

Can I use Approve Verification 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 xinzhuwang-wxz/OpenPE --skill approve-verification -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/approve-verification, .gemini/skills/approve-verification, .github/skills/approve-verification and .opencode/skills/approve-verification in your project.

What does Approve Verification need to run?

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

Does Approve Verification 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 Approve Verification 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 Approve Verification use?

Approve Verification is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Approve Verification use?

About 1.5k tokens (SKILL.md is roughly 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 Approve Verification?

Skills that share tags, products or a category with Approve Verification: Phase Gated Debugging (sickn33/agentic-awesome-skills, 47k stars), Phase Gate Check (Donchitos/Claude-Code-Game-Studios, 26k stars), Operator Approval Loop (affaan-m/ECC, 277k stars) and Gate Tests (vercel/next.js, 143k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Approve Verification?

xinzhuwang-wxz (a GitHub user) maintains it in xinzhuwang-wxz/OpenPE, which has 101 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on April 2, 2026.

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