walkthrough
Skill452 starsChanged 23 days agoApache-2.0View on GitHub
Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts. Use when a user asks for demo screenshots or a caller requires visual evidence after UI or rendered-output changes.
We split this skill into the rules it gives an agent
20 rules. 0 are common, 19 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 23 edited versions we read keep these.
19
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
When the caller requires a walkthrough and it cannot be produced, block closeout with the exact missing tool, access, or artifact.
- Distinctive: line 24
When the caller requires a diff check and no relevant UI or rendered-output change exists, record:
- Very specific: line 49
Use producedFileDiff for the file-diff gate.
- Distinctive: line 54
Keep receipts local. Do not publish file hashes.
- Distinctive: line 63
Read only what explains the completed result:
- Distinctive: line 75
Use one to four frames. Each frame should explain one point:
- Distinctive: line 82
Prefer the shortest sequence a non-developer can understand in under one minute.
- Distinctive: line 91
use the repo-required browser or capture tool.
- Distinctive: line 98
Prefer light mode when both themes are equally truthful.
- Distinctive: line 126
Keep labels to one sentence.
- Distinctive: line 128
Never add, remove, rewrite, beautify, or simulate product content.
- Distinctive: line 135
Do not send credentials, tokens, private URLs, customer data, personal data, health data, or other repo-restricted content to an image tool.
- Distinctive: line 137
Use deterministic sanitized fixtures or crop and redact before annotation.
- Distinctive: line 138
Do not present a mockup, recreated HTML, or synthetic screen as completed product work.
- Distinctive: line 140
Do not claim the annotation itself proves runtime behavior.
- Distinctive: line 147
Prefer common words and one project term per concept.
- Distinctive: line 148
Use active voice and short, single-topic paragraphs.
- Distinctive: line 151
Never make the reader inspect the diff to understand why the result is correct and safe.
- Distinctive: line 160
When a PR or tracker needs images, follow the owning repo's upload policy and replace local paths with hosted URLs there.
- Distinctive: line 169
every annotation matches its original.
“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Walkthrough
Explain a completed change with a few annotated visuals. Run this after final verification. A walkthrough explains proof; it does not replace proof.
Honor The Caller Contract
The caller decides whether the walkthrough is required. Follow the stricter repo rule when one exists.
For UI-gated workflows, treat app pages, websites, components, styles, visual content, and generated or rendered output as UI changes. If the packet changed one of those surfaces, run the walkthrough in the final handoff.
When the caller requires a walkthrough and it cannot be produced, block closeout with the exact missing tool, access, or artifact. Do not waive it silently.
When the caller requires a diff check and no relevant UI or rendered-output change exists, record:
Walkthrough: N/A — no UI or rendered-output change in this packet.Record A Diff Baseline
For a diff-gated workflow, capture the baseline before the first file mutation, including plan creation:
node .agents/skills/walkthrough/scripts/diff-baseline.mjs capture \
--output tmp/walkthrough/<slug>/baseline.jsonAt closeout, compare the final checkout with that baseline:
node .agents/skills/walkthrough/scripts/diff-baseline.mjs compare \
--baseline tmp/walkthrough/<slug>/baseline.json \
--output tmp/walkthrough/<slug>/diff-receipt.jsonUse producedFileDiff for the file-diff gate. Use changedPaths and the final
diff to decide whether UI or rendered output changed. The receipt detects
committed clean-tree changes, tracked working changes, executable-bit changes,
symlink changes, and untracked files without git status.
Keep receipts local. Do not publish file hashes. If an older packet has no baseline, reconstruct it from the recorded starting commit or base ref and the packet's changed-file ledger. Mark the receipt as reconstructed. New packets must capture the baseline before mutation. The helper excludes its own baseline and receipt paths from the comparison, but the output directory should still be ignored by the repo.
Read The Minimum Evidence
Read only what explains the completed result:
- the latest request and acceptance criteria;
- the baseline, diff receipt, and final diff;
- final screenshots or rendered proof already captured;
- the final route, role, data fixture, viewport, theme, or source artifact.
Reuse valid final-state screenshots. Do not rerun an expensive flow only to capture the same state.
Pick The Shortest Story
Use one to four frames. Each frame should explain one point:
- where the user acts;
- what changed or became possible;
- what consequence appears;
- what proves the result.
Prefer the shortest sequence a non-developer can understand in under one minute. Do not turn every field or test into a callout.
Capture The Real Artifact
For UI or rendered-output changes:
- capture the real final affected surface in its verified state;
- preserve the correct role, data, viewport, theme, and open or selected state;
- use the repo-required browser or capture tool;
- reuse existing final proof when it shows the required state.
For an explicit walkthrough of non-UI work, render the real final source, diff, report, document, CLI result, or provider read-back. Never invent a product screen to make backend or workflow work look visual.
Prefer light mode when both themes are equally truthful. Keep the verified theme when the change concerns dark mode or switching would misrepresent the result.
Save originals and annotated copies under a repo-approved ignored directory. Default to:
tmp/walkthrough/<slug>/Use paired names:
01-<step>-original.png
01-<step>-annotated.pngAnnotate Without Rewriting
Inspect each source image first. Use imagegen, or the repo-approved image
editor, to add only:
- numbered callouts in free margins or calm empty areas;
- short plain-English labels;
- thin arrows that land on the exact control, value, or consequence;
- a compact title when the frame needs context.
Keep labels to one sentence. Use product language, not implementation terms.
Never add, remove, rewrite, beautify, or simulate product content. Compare the annotated result with the original. If product text, values, layout, or state changed, discard it and regenerate. The original is proof. The annotation is explanation.
Protect Sensitive Data
- Do not send credentials, tokens, private URLs, customer data, personal data, health data, or other repo-restricted content to an image tool.
- Use deterministic sanitized fixtures or crop and redact before annotation.
- Do not present a mockup, recreated HTML, or synthetic screen as completed product work.
- Do not claim the annotation itself proves runtime behavior.
Write Plain Technical Prose
Apply these rules to annotation labels, captions, and the final handoff:
- Lead with the outcome. Give the reason before implementation details.
- Prefer common words and one project term per concept.
- Use active voice and short, single-topic paragraphs.
- Cover objective, owner, chosen fix, invariant, alternatives, blast radius, verification, and remaining risk when they apply.
- Never make the reader inspect the diff to understand why the result is correct and safe.
Final Handoff
Show every annotated image inline with an absolute local path. Give each image one short caption stating what to notice. Name the related test, browser, external, or source proof.
When a PR or tracker needs images, follow the owning repo's upload policy and replace local paths with hosted URLs there.
Close only when:
- the caller's applicability rule was classified correctly;
- the baseline and receipt exist when the caller uses a diff gate;
- the frames cover the user action and consequence;
- originals and annotated copies are saved;
- every annotation matches its original;
- annotated images appear inline in the final response;
- the owning proof is named.
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- udecode/plate★ 17k56% same
- udecode/dotai★ 1.2k56% same
Wrote their own version · 21
- Mathews-Tom/armory★ 340same name
- smallnest/goal-workflow★ 283same name
- andrew-yangy/gru-ai★ 153same name
- oborchers/proqi★ 45same name
- huytd/skills★ 19same name
- wycats/ai-plugin★ 19same name
- wycats/vscode-ai-plugin★ 19same name
- pche-broken-artist/forge-of-thought★ 11same name
- adamos486/skills★ 10same name
- aadishv/skills★ 1same name
11 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use to-issues.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillto-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
Also in 3 projects that use this
In this repository54 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- .agents/skills/autoreview/AGENTS.mdAGENTS.md
- .agents/skills/autoreview/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- 4-ultraciteSkill
- agent-browser-issueSkill
- agent-native-reviewerSkill
- architecture-cleanupSkill
- autoclosureSkill
- autogoalSkill
- autoreviewSkill
- autoSkill
- avoid-feature-creepSkill
- better-auth-best-practicesSkill
- changeset-doc-syncSkill
- changeset-resolveSkill
- changesetSkill
- component-colocationSkill
- concave-paritySkill
- concaveSkill
- convex-release-auditSkill
- designSkill
- deslopSkill
- diagnosing-bugsSkill
- find-skillsSkill
- grill-with-visionSkill
- hard-cutSkill
- jotai-xSkill
- kitcnSkill
- linear-backlogSkill
- major-taskSkill
- next-dev-loopSkill
- nextjsSkill
- orchestratorSkill
- package-release-auditSkill
- prototypeSkill
- react-querySkill
- research-wikiSkill
- resolve-pr-feedbackSkill
- resolving-merge-conflictsSkill
- scenariosSkill
- shadcn-paritySkill
- sync-convex-authSkill
- sync-visionSkill
- taskSkill
- tddSkill
- testingSkill
- toastSkill
- to-milestoneSkill
- to-prdSkill
- turborepoSkill
- video-transcriptsSkill
- visionSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

