Skip to content
cccskills
FreePublished on GitHubEnglish overview

verify-change

Track substantial SDK or CLI work across sessions, preserve goals and blockers, choose repository verification checks, and inspect revision-specific evidence. It helps agents resume work or hand it off with a clear record of what was checked.

OriginalShow the original description

Maintain resumable task records, select repository verification profiles, inspect revision-bound receipts, and carry work between coding agents. Use for substantial SDK or CLI work spanning sessions, evidence review, or carrying work between coding agents; use package-specific skills for implementation and ordinary small edits.

ComposioHQ/composio30,811 stars(GitHub 30,811 + cccskills 0)

Run score Not tested

See how to install

Good for

  • Resuming a substantial coding task after a break
  • Handing work and blockers to another agent
  • Reviewing which checks passed for a revision

Overview

What it does

For substantial SDK or CLI work, this skill records the goal, scope, next steps, and unresolved blockers so work can resume across sessions. It selects and runs checks from the repository’s verification profiles after implementation. It also reads verification receipts to confirm which revision was checked and what the checks covered. When an issue recurs, it considers whether an existing test, type check, or lint check can catch it.

When it helps

Use it for development that spans multiple days or needs to pass between agents. When resuming, it refreshes external issue, pull request, and CI status instead of relying only on earlier notes. Small edits do not need task records; package-specific implementation work belongs with the corresponding skill.

Example requests

  • “Create a task record for this CLI feature and choose a verification profile.”
  • “Check the previous task state and CI, then update the next steps.”
  • “Read the verification receipt and summarize what was checked for this change.”

Notes

Private task records and command output stay in the ignored .artifacts/ directory and should not be attached wholesale to a pull request. This skill records work context and verification evidence; it does not grant authority to commit, push, merge, or release.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Document check

AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).

SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt limits private data storage and PR attachments, and states that no commit or release authority is granted.
Easy setupDoes it need few tools or API keys, and are they documented?
AGoodNo API keys or external setup steps are specified.

Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 30, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (2)

  • SKILL.md1.7 KB
  • references/verification-map.md5.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Verify Change

Write agent-tooling scripts and tests in TypeScript and execute them with Bun; do not add .mjs or Node entrypoints. Existing SDK languages and package-management commands keep their repository ownership.

Use the verification map to select the existing checks and preserve a task's goal, authority, next step and blockers across sessions.

  1. For substantial work, initialize one task with the requested outcome and a matching profile. Keep the actual user request authoritative.
  2. Inspect status when resuming, update nextStep and blocker in its local task.json, and refresh external issue, PR and CI state before acting.
  3. Run the profile after implementation. Read the receipt and its boundary before reporting what passed. A passing profile establishes only its named checks.
  4. Treat a recurring intervention as a candidate for an existing behavioral test, type or lint check. Prove the check rejects the original mistake. Preserve one-off judgment locally instead of expanding global instructions.

Do not create task records for trivial edits. Private task data and command output stay under ignored .artifacts/; never attach them wholesale to a PR. This tool records context and evidence, and does not grant commit, push, merge or release authority.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

bug-fixing

FreeSummary

Fix defects in Composio SDK through focused reproduction, root-cause analysis, regression tests that check for recurrence, and targeted verification. Use it for reported bugs, failing tests, CI regressions, runtime errors, or incorrect SDK behavior.

  • Reproducing and fixing reported SDK bugs
  • Investigating failing tests
  • Fixing regressions in automated CI checks
ComposioHQ/composio30.8KUpdated Oct 29, 2026

cli-command

FreeSummary

Design, implement, and review Composio CLI commands, including user interactions, output, errors, and configuration. It guides command wiring and service changes using Effect and effect/cli, with references for implementation patterns.

  • Designing CLI command behavior and output
  • Implementing command wiring with Effect
  • Reviewing configuration and error handling
ComposioHQ/composio30.8KUpdated Oct 29, 2026

cli-e2e

FreeSummary

Create, update, and debug Docker-based end-to-end tests for the Composio CLI. Covers running the executable, keeping test data separate, checking command output, and maintaining package manifests within the CLI test suite.

  • Add end-to-end tests for CLI commands
  • Debug unexpected CLI test output
  • Keep test data isolated between tests
ComposioHQ/composio30.8KUpdated Oct 29, 2026

cli-release

FreeSummary

Build beta versions of the Composio CLI, promote a tested beta to a stable release, and investigate failed releases. Guides verification of published binaries and installation tests through the Build CLI Binaries workflow.

  • Build a CLI beta release
  • Promote a tested beta to stable
  • Verify release assets and installation
ComposioHQ/composio30.8KUpdated Oct 29, 2026

composio

FreeSummary

Set up and use Composio to connect AI agents with apps such as Gmail, Slack, and Notion. Selects guidance for personal accounts or product integrations, covering setup, app operations, troubleshooting, and migration.

  • Connect a personal AI agent to apps
  • Integrate account connections into a product
  • Diagnose failed connections or tool calls
ComposioHQ/composio30.8KUpdated Oct 29, 2026

cross-sdk-parity

FreeSummary

Keep TypeScript and Python SDKs consistent when shared behavior or backend APIs change. Aligns public API names, use of generated clients, and documentation examples, including updates to the fixed versions of generated clients.

  • Align a change across both SDKs
  • Compare TypeScript and Python behavior
  • Update fixed versions of generated clients
ComposioHQ/composio30.8KUpdated Oct 29, 2026

See all skills by ComposioHQ

Report a problem with this skill