Skip to content
Skills Library
AI & agents · Testing

verification-loop

/verification-loop

Use when a task spans more than a few steps or files — establishes a checkable definition of done, a verification cadence, and fresh-context verifier subagents before claiming completion.

Licence
MIT
Last repository change
14.06.2026

Assessment and security

85/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content20 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 14.06.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when a task spans more than a few steps or files — establishes a checkable definition of done, a verification cadence, and fresh-context verifier subagents before claiming completion.

Original author description

Use when a task spans more than a few steps or files — establishes a checkable definition of done, a verification cadence, and fresh-context verifier subagents before claiming completion.

How it works

  1. 1. Define "done" before starting
  2. 2. Verify on a cadence, not at the end
  3. 3. Fresh-context verification before completion claims
  4. 4. Act on the verdict
Original SKILL.md headings · 29 lines, 222 words
SKILL.md preview
---
name: verification-loop
description: Use when a task spans more than a few steps or files — establishes a checkable definition of done, a verification cadence, and fresh-context verifier subagents before claiming completion.
---

# Verification Loop

Fable 5 builds its own checking harness on long tasks. Reproduce that explicitly.

## 1. Define "done" before starting
Write down (in your todo list or a scratch note) the binary checks that prove the task
is complete: which tests must pass, which command must produce which output, which
behavior must be observable. If the user's request doesn't define them, derive them
and state them in one sentence.

## 2. Verify on a cadence, not at the end
After each meaningful increment (a function implemented, a module refactored), run the
relevant real check immediately — the actual test command, the actual build. Never
batch all verification to the end of a long task; errors compound.

## 3. Fresh-context verification before completion claims
Before declaring a substantial task complete, dispatch a verifier subagent
(`modelharness:verifier` agent, or a general-purpose subagent given the
`agents/verifier.md` instructions). Give it: the original specification, the
definition-of-done checks, and the current diff (`git diff` output or changed file
list). A fresh context catches what you have rationalized away. Self-review is the
fallback only when subagents are unavailable.

## 4. Act on the verdict
If the verifier reports gaps: fix them, re-run the checks, re-verify. Only report
completion to the user when checks pass AND the verifier (or the checks themselves)
confirm it. Report any unverified remainder explicitly.

Versions

RepositoryScoreLicence
This page · vitaliikapliuk/modelharness85MIT
frankxai/claude-skills-library100MIT
smartworldarafath/REA_Skill100MIT
MJayConstantino/skills100MIT
affaan-m/ECC100MIT
affaan-m/ECC100MIT
SHRIJANAGAIN/Nemo-Cli100Apache-2.0
Galaxy-Dawn/claude-scholar100MIT
nguyentrunghieutcu/ctxora-engine100MIT

Database snapshot: 13.11.2026 · package version 3027fdf52d8b (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90clade-verification
    Verification, testing, review, screenshots, and evidence rules. Use when testing, reviewing, debugging, collecting evidence, or claiming completion.
  • 100goal-test
    Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a…
  • 90nerd-loop
    Use when the user explicitly asks for Nerd Loop or wants a cost-proportional, behavior-aware task-completion controller that selects the cheapest adequate loop profile and iterates toward an explicit Definition of Done through focused work, automatic verification, and bounded stopping rules.
  • 100mini-loop
    Autonomous build-verify-fix loop that runs until an explicit Definition of Done passes. Use when named (mini-loop) or when the user says exactly "run a loop".
  • 100loop-ledger
    Scaffold a J-Space-style 5-state task ledger (Goal/Core/Verified/Open/Next) for long multi-step tasks and goal runs. Use when starting loop-tier work that spans multiple tools, files, sessions, or subagents, or when resuming such work after a pause or handoff. Pairs with the…
  • 100setup-project
    Analyze the current repository and propose a lean Claude Code setup (CLAUDE.md, verification commands, optional hooks, skills, subagents). Asks for approval before changing anything.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.