Automated summary
Reviews a release checklist against the supplied evidence and git status, then reports a pass/fail gate table with blockers and evidence gaps, without ever tagging or publishing.
Strengths
- Read-only by design: it stops before any tag, publish, or release action
- Clearly separates observed facts from assumptions and calls out missing evidence
- Structured output with a gate table, blockers, and evidence gaps that feeds directly into a go/no-go decision
- Narrow tool scope (readFile, git.status) keeps the risk surface small
Limitations
- Cannot run tests, builds, or query CI — it relies on command outputs the user provides
- Does not automatically verify pass criteria; it interprets the evidence it is given
- Does not cover the delivery steps themselves (tagging, publishing), which are deliberately out of scope
Use it right before a release when you want a factual, evidence-based review of the checklist with a pass/fail verdict per gate.
Avoid it when you need to actually run the build/test pipeline or perform the tag and publish step.
Security analysis
SafeThe skill is purely advisory: it reads a checklist and reports pass/fail evidence using read-only capabilities (file read, git status). It contains no shell commands, no network or credential access, no obfuscation, and explicitly requires stopping before any irreversible or account-changing action and deferring to a supervised/approval-gated step. The only issue is a documentation mismatch about which tools are allowed, which is not an execution risk.
- •Allowed-tools declaration is inconsistent: the header says '(none declared)' while the body lists filesystem.readFile and git.status. Both are read-only, so risk is low, but the capability declaration should be reconciled so an agent runtime enforces the intended scope.
- •No executable commands, network calls, or code blocks are present; the instruction is prose-only and explicitly prohibits tagging, publishing, or releasing artifacts.
Examples
Here is our release checklist for v2.4.0, plus the outputs of `git status`, `npm test`, and the changelog diff. Review each item and tell me which gates pass, which fail, and which have no supporting evidence.Check this release checklist against the current repo state and list the blockers that must be cleared before shipping 1.9.0. Flag anything you cannot verify with the files and git status available.Audit the attached release checklist for missing evidence — point out every item where no command output or file was provided, and suggest the safest manual verification for each.Release Checklist Runner
Purpose
Review a release checklist and report pass/fail evidence.
Allowed tools
- filesystem.readFile
- git.status
Instructions
Use this skill for: Review a release checklist and report pass/fail evidence. Expected inputs: Checklist, release target, and command outputs. Work only from user-provided context, visible evidence, or explicitly allowed project files. Separate observed facts from assumptions, and say when evidence is missing. If a required live capability is unavailable, explain the limitation and provide the safest manual verification path. For any state-changing, irreversible, account-changing, or destructive action, stop and propose a supervised Feather task or approval-gated next step. Never: Tag, publish, or release artifacts.
Output
Return Gate table, blockers, and evidence gaps. Use this structure:
- Summary
- Evidence used
- Findings
- Risks or uncertainty
- Recommended next supervised action
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/release-checklist-runner-ms2s7d1i/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/release-checklist-runner-ms2s7d1i' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/release-checklist-runner-ms2s7d1i/download' --output '.skill-downloads/release-checklist-runner-ms2s7d1i/SKILL.md.part' && mv '.skill-downloads/release-checklist-runner-ms2s7d1i/SKILL.md.part' '.skill-downloads/release-checklist-runner-ms2s7d1i/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/release-checklist-runner-ms2s7d1i/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Ansible PR Review
DevOps
Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.