Agent skill

Self Verification

by A-EVO-Lab in A-EVO-Lab/a-evolve

Verification patterns to confirm task completion before submitting.

No licenceAuto-check passed

Install Self Verification

skills CLI
$ npx skills add A-EVO-Lab/a-evolve --skill self-verification -a claude-code

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

GitHub CLI
$ gh skill install A-EVO-Lab/a-evolve self-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/A-EVO-Lab/a-evolve.git skills-src && mkdir -p .claude/skills && cp -r skills-src/seed_workspaces/osworld/skills/self-verification .claude/skills/self-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
self-verification
GitHub stars
806
Token cost
~365 tokens
SKILL.md length
188 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
None found

At a glance

Verification patterns to confirm task completion before submitting.

  • Works in 4 steps: Re-read Requirements → Verify Each Requirement → Check Your Assumptions → …
  • SKILL.md covers 1. Re-read Requirements, 2. Verify Each Requirement, 3. Check Your Assumptions and 4. Common Pitfalls
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Self Verification is an agent skill from A-EVO-Lab/a-evolve. Verification patterns to confirm task completion before submitting. Read this before calling submit().

Its SKILL.md is about 370 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

Example prompts

  • “/self-verification”

Workflow steps

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

  1. Re-read Requirements
  2. Verify Each Requirement
  3. Check Your Assumptions
  4. Common Pitfalls

What it can do on your machine

Read from SKILL.md and the folder at commit 18ba996. 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

Self Verification loads about 365 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 188 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~365

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 188 words (~365 tokens).

“Before calling submit(), systematically verify your solution:”

— opening of SKILL.md by A-EVO-Lab
name
self-verification

Read the full SKILL.md on GitHub

Files

Just SKILL.md in seed_workspaces/osworld/skills/self-verification of A-EVO-Lab/a-evolve.

Open the folder on GitHubat commit 18ba996

Compare with similar skills

Self 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.

Self Verification compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Self Verification this skillA-EVO-Lab/a-evolve806—~365Automated safety check: PassNone
Verification Before Completionfarm-fe/farm5.6k46 repos~1kAutomated safety check: PassMIT
Submitbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~1kAutomated safety check: NotesCustom licence
Submitbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~591Automated safety check: NotesCustom licence
Verification Before Completionforyourhealth111-pixel/Vibe-Skills3.6k—~1.1kAutomated safety check: PassApache-2.0
Complete Partial PRpydantic/pydantic-ai20k—~2.4kAutomated safety check: PassMIT

Similar skills

  • 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 46 repos~1k tokens
    Agent WorkflowsAuto-check passed
  • Submit

    brycewang-stanford/Auto-Empirical-Research-Skills

    Final submission verification gate for the sewage-house-prices paper.

    4.5k GitHub stars~1k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check: notes
  • Submit

    brycewang-stanford/Auto-Empirical-Research-Skills

    Submission pipeline — journal targeting, replication package, audit, and final gate.

    4.5k GitHub stars~591 tokensUpdated 3 days ago
    Research & ScienceAuto-check: notes
  • Verification Before Completion

    foryourhealth111-pixel/Vibe-Skills

    Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready.

    3.6k GitHub stars~1.1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Complete Partial PR

    pydantic/pydantic-ai

    Official

    Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point.

    20k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Verification Before Completion

    jnMetaCode/superpowers-zh

    Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output.

    8.3k GitHub stars~443 tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

More from A-EVO-Lab/a-evolve

All 17 skills in this repo
  • Harness Optimizer

    A-EVO-Lab/a-evolve

    Optimize an AI agent's harness for MCP-Atlas benchmark. An agent skill from A-EVO-Lab/a-evolve.

    806 GitHub stars~982 tokensUpdated 1 mo ago
    Auto-check passed
  • Data Formats

    A-EVO-Lab/a-evolve

    Reading, writing, and converting common data formats (CSV, Excel, JSON, YAML) with correct handling of encoding, types, and edge cases.

    806 GitHub stars~638 tokensUpdated 1 mo ago
    Auto-check passed
  • Python Data Analysis

    A-EVO-Lab/a-evolve

    Best practices for multi-step Python tasks including data analysis, HuggingFace datasets, token counting, and any task requiring state across multiple python() calls.

    806 GitHub stars~476 tokensUpdated 1 mo ago
    Auto-check passed
  • Python Packages

    A-EVO-Lab/a-evolve

    Installing and using common Python packages in SkillBench containers.

    806 GitHub stars~556 tokensUpdated 1 mo ago
    Auto-check passed
  • Scientific Computing

    A-EVO-Lab/a-evolve

    Strategies for scientific computing, numerical methods, bioinformatics/DNA tasks, logic circuit design, algorithmic challenges, and ML training tasks.

    806 GitHub stars~495 tokensUpdated 1 mo ago
    Auto-check passed
  • Screenshot Analysis

    A-EVO-Lab/a-evolve

    How to interpret accessibility tree elements and correlate them with screenshot regions for accurate GUI interaction.

    806 GitHub stars~428 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Self Verification

What does Self Verification do?

Verification patterns to confirm task completion before submitting. Self Verification is an agent skill from A-EVO-Lab/a-evolve. Verification patterns to confirm task completion before submitting.

How do I install Self Verification in Claude Code?

Run `npx skills add A-EVO-Lab/a-evolve --skill self-verification -a claude-code`. Or copy the skill folder (seed_workspaces/osworld/skills/self-verification in A-EVO-Lab/a-evolve) into .claude/skills/self-verification in your project. Claude Code loads it when a task matches its description.

How do I install Self Verification in Codex?

Run `npx skills add A-EVO-Lab/a-evolve --skill self-verification -a codex`. Or copy the skill folder (seed_workspaces/osworld/skills/self-verification in A-EVO-Lab/a-evolve) into .agents/skills/self-verification in your project. Codex loads it when a task matches its description.

Can I use Self 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 A-EVO-Lab/a-evolve --skill self-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/self-verification, .gemini/skills/self-verification, .github/skills/self-verification and .opencode/skills/self-verification in your project.

What does Self Verification need to run?

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

Does Self 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 Self 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 Self Verification use?

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

How many tokens does Self Verification use?

About 365 tokens (SKILL.md is roughly 1.5k 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 Self Verification?

Skills that share tags, products or a category with Self Verification: Verification Before Completion (farm-fe/farm, 5.6k stars), Submit (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Submit (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars) and Verification Before Completion (foryourhealth111-pixel/Vibe-Skills, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Self Verification?

A-EVO-Lab (a GitHub organization) maintains it in A-EVO-Lab/a-evolve, which has 806 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on August 22, 2026.

Source: A-EVO-Lab/a-evolve on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.