site-visit-report
Skill390 starsChanged 55 days agoMITView on GitHub
Prepare a sourced site-visit record separating direct observations, participant reports, interpretations, limitations and proposed follow-ups.
In this repository63 other files it gives its agents.
- docs/agents.mdAGENTS.md
- skills/project/templates/AGENTS.mdAGENTS.md
- skills/project/templates/CLAUDE.mdCLAUDE.md
- agreementSkill
- architecture-knowledgeSkill
- color-palette-generatorSkill
- csv-to-sifSkill
- demographics-analysisSkill
- drawing-quantity-extractSkill
- environmental-analysisSkill
- epd-compareSkill
- epd-parserSkill
- epd-researchSkill
- epd-to-specSkill
- ffe-spec-bookSkill
- invoiceSkill
- learnSkill
- lighting-report-extractSkill
- master-scheduleSkill
- meeting-minutesSkill
- mobility-analysisSkill
- normaSkill
- norma-supportSkill
- nyc-acrisSkill
- nyc-bsaSkill
- nyc-dob-permitsSkill
- nyc-dob-violationsSkill
- nyc-hpdSkill
- nyc-landmarksSkill
- nyc-property-reportSkill
- occupancy-calculatorSkill
- product-auditSkill
- product-cut-sheetSkill
- product-data-cleanupSkill
- product-data-importSkill
- product-enrichSkill
- product-image-processorSkill
- product-librarySkill
- product-matchSkill
- product-pairSkill
- product-researchSkill
- product-spec-bulk-fetchSkill
- product-spec-pdf-parserSkill
- product-url-clipSkill
- projectSkill
- proposalSkill
- receiveSkill
- resize-imagesSkill
- schedule-quantity-reconcileSkill
- sif-to-csvSkill
- site-historySkill
- skill-makerSkill
- slide-deck-generatorSkill
- spec-writerSkill
- studio-feedbackSkill
- studioSkill
- tasklistSkill
- timetrackerSkill
- tool-catalogSkill
- workplace-programmerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 16
Before acting, read the host contract, this component's declaration (skill:site-visit-report), and applicable workspace semantics.
≈ “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
/as:site-visit-report
Before acting, read the host contract, this component's declaration (skill:site-visit-report), and applicable workspace semantics. Load only the required modes from the shared catalog.
<!-- architecture-studio:harness-compatibility -->Use the host adapter and available native tools or ordinary task-specific code. Apply the receive-owned semantic document rules directly; no installed library, nested skill invocation, runner or executable reconstruction is required. Resolve context before durable work. Existing exact authorization persists; ask only for material missing information or missing permission.
Own authored event documents of kind site-visit. Use the site template. Keep direct observations, participant-reported information, interpretations, issues and proposed actions separate; give stable item labels. Record participants, date, visit scope and access/visibility/weather/testing/equipment/document limits. Inaccessible or concealed work is Not observed, never no issue observed. Do not fabricate photo identity, location, dates or certainty about concealed conditions.
Resolve the project and authorized notes/photos. Distinguish visit, source and created dates. Inspect available photos before describing their content; a filename or caption alone is not visual evidence. Link registered attachments by ID and actual resolved path. This record does not certify code, life-safety, structural, MEP, accessibility, environmental or contractual compliance; route substantive conclusions to the relevant specialist/professional workflow.
Before changing records
Before persistent changes, follow the native mutation sequence: Inspect → Prepare → Verify preparation → Apply → Verify result → Complete. Inspect pending work first. Finish and verify preparation before the first canonical write: separately reread every saved original and prepared file, check its complete actual bytes, establish durable saving, and inspect actual permissions, ownership and ACLs. Merely writing recovery files does not finish verification. Apply only that verified set. Mark complete only after fresh readback validates the entire affected result and its relationships. Read-only requests and inline drafts need no publication sequence.
Saving a report affects the complete site-visit document plus DOCUMENTS.csv and any explicitly authorized attachment registrations. Prepare and verify that full set before writing the first member. Notes/photos remain source read guards; no project-fact, task or decision promotion belongs to this publication set.
Prepare the report, then resolve confirmed coordinates and register through documents.register, kind site-visit. An explicit revision is a new document with supersedes; preserve old bytes. For client/authority-facing or regulated-conclusion reports, apply the existing disclaimer procedure when applicable, including the required terminal <!-- architecture-studio:requires-disclaimer --> marker; do not invent a universal disclaimer for an internal administrative draft.
Reopen the actual report and inspect requested presentation. Only after saving, offer selected project-fact/decision/task promotions with exact item IDs. Report approval alone is not promotion approval. Keep observations, reports and interpretations in their original epistemic category. No silent mutation of PROJECT.md, TASKS.csv or decision records.
site_visit.prepare means the authored preparation procedure above; it may produce an inline draft without a workspace write. Persistence uses the shared native document contract, restricted here to kind site-visit and authorized attachments. A saved record does not authorize its proposed actions or promote facts/decisions automatically.
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.

