Reading Measurements
Read a number without being fooled by it: an exit code, a passing result file, a test count, a list size, a control run, a red or a green. Use before reporting any figure, before turning a test run into a verdict, before acting on 'N items are broken', and whenever two outputs or two counts of the same thing disagree.
Install
/plugin marketplace add okgrit/done-is-a-claimThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add okgrit/done-is-a-claim --skill reading-measurementsgit clone --depth 1 https://github.com/okgrit/done-is-a-claim.git /tmp/done-is-a-claim
mkdir -p ~/.claude/skills
cp -r /tmp/done-is-a-claim/skills/reading-measurements ~/.claude/skills/reading-measurementsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Reading measurements Wrong reports rarely lack a measurement. They read a real number as answering a question it never asked. Before you report, decide or spend anything on a figure, ask: > What would this same number look like if my claim were false? If the answer is "exactly the same", the number alone does not distinguish the claim from its alternative. Seek a discriminating observation or control. ## Reading any figure Use the relevant checks below to decide what the figure supports. A limitation may invalidate an interpretation without invalidating the observation itself. 1. **An exit code is not a verdict.** pytest exit 4 indicates a usage error, such as a missing path; exit 5 indicates nothing was collected. Read the collection and result summaries. `no tests ran` does not establish a pass; investigate selection, setup and the change before assigning cause. 2. **Capture the command's own exit code.** In `cmd | tail; echo $?` the status is `tail`'s in ordinary shell pipeline behavior. Capture the tested command's status before reading a saved log, or use the shell's pipeline status facility. `set -o pipefail` detects a failing pipeline in shells that support it; its status is not necessarily the tested command's code. 3. **Read the relevant artefacts.** A result file, a CI summary, a log and a progress counter are separate claims about one run. When they disagree, the disagreement is the finding.
Details
- Skill name
reading-measurements- Repository
- okgrit/done-is-a-claim
- Path
skills/reading-measurements/SKILL.md- License
- Apache-2.0
- Repo updated
- 25 October 2026
- Listed in
- heilcheng/awesome-agent-skills
FAQ
What does the Reading Measurements skill do?
Read a number without being fooled by it: an exit code, a passing result file, a test count, a list size, a control run, a red or a green. Use before reporting any figure, before turning a test run into a verdict, before acting on 'N items are broken', and whenever two outputs or two counts of the same thing disagree.
How do I install the Reading Measurements skill?
Claude Code plugin: /plugin marketplace add okgrit/done-is-a-claim. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Reading Measurements popular?
It lives in okgrit/done-is-a-claim, which has 33 GitHub stars and 4 forks, and is included in 1 curated skill list.
Related skills
Acceptance Design
33okgrit/done-is-a-claim
Define executable acceptance for a bounded task before work or dispatch. Use when writing a worker brief, selecting success checks, or repairing an acceptance contract that cannot test the intended outcome.
Checking Delivery
33okgrit/done-is-a-claim
Verify an artifact at its actual delivery destination and distinguish send attempts, acknowledgements, publication and consumer checks. Use when reporting a file, message, export or deployment as delivered; creating a local draft alone does not imply delivery.
Collecting Worker Results
33okgrit/done-is-a-claim
Inspect a stopped worker's returned work and evidence before accepting it, retrying it or handing it to an integration owner. Use when a worker finishes, records disagree, or a green result has no visible change. Collection does not authorize merging.
Render QA and Surgical Changes
48saranambiar/hyperframes-video-agent-skills
Verify final video renders and make tiny safe edits without breaking approved sync, including proof frames, contact sheets, media probing, stale theme scans, exact timestamp checks, carryover-frame refreshes, and re-render-only-affected-scenes workflows. Use when a user asks for final QA, HD/render verification, a small text/audio/color change, or regression checks after approved timing.
Implementing with Tests
33okgrit/done-is-a-claim
Implement runtime behavior changes and bug fixes with meaningful before-and-after checks, preserved behavior and relevant regression evidence. Use while editing code; prose-only changes do not need a failing test.
Scene Continuity and Transitions
48saranambiar/hyperframes-video-agent-skills
Preserve visual continuity across video scenes with previous-final-frame starts, camera swipes, carryover frames, transition QA, and boundary proofing. Use when a scene must begin from the exact last frame of a previous scene, when adding camera-move transitions, when replacing scene endings, or when debugging stale starting frames.
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.