ai-visual-recap
Skill65 starsChanged 2 months agoApache-2.0View on GitHub
Build an optional self-contained HTML recap when the user manually invokes this skill. The output is a local file on the feature branch.
In this repository41 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-auditSkill
- ai-adversarial-loopSkill
- ai-agents-mdSkill
- ai-architectSkill
- ai-audit-codeSkill
- ai-audit-designSkill
- ai-audit-docsSkill
- ai-brainstormSkill
- ai-codegraphSkill
- ai-config-to-projectSkill
- ai-debugSkill
- ai-design-md-plannerSkill
- ai-exploreSkill
- ai-git-cleanupSkill
- ai-issue-reportSkill
- ai-noteSkill
- ai-orchestratorSkill
- ai-prototypeSkill
- ai-prSkill
- ai-read-docsSkill
- ai-researchSkill
- ai-review-uiSkill
- ai-securitySkill
- ai-stress-testSkill
- ai-test-plannerSkill
- ai-triageSkill
- ai-verifySkill
- ai-writeSkill
- ai-writing-behaviorSkill
- build-checkSkill
- code-auditSkill
- design-checkSkill
- feature-verifySkill
- full-reviewSkill
- perf-auditSkill
- review-routerSkill
- second-opinionSkill
- security-auditSkill
- spec-extractSkill
- verify-featureSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 3 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
When manually invoked by the user, create the optional recap as .ai-engineering/recap.html from the changes on the current feature branch.
- Distinctive: line 19
Scope the change: Read git diff --stat main...HEAD and git diff --name-status main...HEAD, then inspect the relevant changed files and test …
- Very specific: line 23
Read the local format: Start with templates/recap.html.tpl, follow the artifact design, and use the wireframe guidance only when the change …
- Distinctive: line 31
Use the template's existing cards, notes, tables, and code panels.
- Distinctive: line 33
Protect the contents: Use repository evidence only.
- Very specific: line 49
Read by: the human, during app review Dies: when the feature branch is merged Next: none Stop: close Stop words: close, cierra, done, listo …
- Very specific: line 53
Stop words: close, cierra, done, listo Stop confirms: the local HTML recap is written and verified Stop runs: git status --short
- Very specific: line 54
Stop confirms: the local HTML recap is written and verified Stop runs: git status --short
- Very specific: line 55
Stop runs: git status --short
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ai-visual-recap
When manually invoked by the user, create the optional recap as
.ai-engineering/recap.html from the changes on the current feature branch. Use
the repository's template and keep the output self-contained. The orchestrator
never invokes this skill automatically, and a missing recap never blocks review
or merge.
Procedure
- Scope the change. Read
git diff --stat main...HEADandgit diff --name-status main...HEAD, then inspect the relevant changed files and test results. Include this feature's follow-up fixes. Exclude unrelated baseline changes. - Read the local format. Start with
templates/recap.html.tpl, follow the artifact design, and use the wireframe guidance only when the change alters a visible interface. - Write the recap. Replace each template placeholder with accurate, HTML-escaped text. Add matching navigation links and sections inside the template's main container. Summarize the outcome, meaningful decisions, changed files, verification evidence, and any real compatibility risks. Use the template's existing cards, notes, tables, and code panels. Include before/after visuals only when they explain a user-visible change.
- Protect the contents. Use repository evidence only. Never include credentials, private service output, raw work items, machine-specific paths, or unrelated changes. Keep code excerpts short and accurate.
- Verify the page. Confirm no
{{...}}placeholders remain, every navigation target names an existing section, and the existing scroll-spy script is unchanged. Runbun test tests/artifact-layout.spec.tsandbun test tests/artifact-scroll-spy.spec.ts. - Write the artifact. Save the complete page to
.ai-engineering/recap.htmlon the feature branch. The orchestrator includes it in the close commit only if the user requested this skill and the file exists; this skill does not commit or merge.
Lifecycle
Lane: standard, full
Writes: .ai-engineering/recap.html
Read by: the human, during app review
Dies: when the feature branch is merged
Next: none
Stop: close
Stop words: close, cierra, done, listo
Stop confirms: the local HTML recap is written and verified
Stop runs: git status --short
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.