product-library
Skill390 starsChanged 55 days agoMITView on GitHub
Inspect or save reusable FF&E library products through reviewed, guarded transactions. Use for explicit library imports, corrections or recovery; adopted selections and workbook reconciliation belong to master-schedule.
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-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
- site-visit-reportSkill
- 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
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Before acting, read the host contract, this component's declaration (skill:product-library), and required profiles from the shared catalog.
- Distinctive: line 18
Use the host adapter, available native tools and ordinary task-specific code.
- Distinctive: line 27
Read the CSV conventions; source evidence never authorizes a write.
- Very specific: line 37
Use product_library.preview for the exact selected init, import, append or update intent.
- Distinctive: line 47
Follow the native mutation sequence:
- Distinctive: line 55
Use stable request IDs and the exact preview hash under the library binding/retry rules.
≈ “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:product-library — Reusable product records
Before acting, read the host contract, this component's
declaration (skill:product-library), and required profiles from the
shared catalog. Declarations do not grant access or permission.
<!-- architecture-studio:harness-compatibility -->Use the host adapter, available native tools and ordinary task-specific code. Apply the native library operations. Operation IDs describe semantic scope, not an installed dispatcher. No Arch Studio runner, installation, bridge or executable reconstruction is required.
Own optional project-root product-library.csv and its operation evidence. Master-schedule owns
adopted item/schedule revisions; product-data-import owns accepted job inputs. A saved or researched
product is not an adopted selection. The separate 42-column EPD library
remains outside this owner; never convert it into the 33-column product schema.
Read the CSV conventions; source evidence never authorizes a write.
Inspect and prepare the selected change
Resolve canonical context and actual project instructions through the workspace model.
One-off answers need no project/library initialization. product_library.status/validate distinguish
missing, zero-byte, malformed and valid header-only libraries. Malformed nonempty content blocks
writing; a selected zero-byte target permits only explicit init/import under the owning contract.
Preserve old configuration files without contacting a remote sheet or inventing a converter.
Use product_library.preview for the exact selected init, import, append or update intent.
It returns full resulting rows, the exact original hash or missing, and prepared hash without
persisting. Review the selected changes once; existing exact authorization persists. Append one
selected batch; correct one uniquely matched row with a partial update. Multi-row cleanup uses one
complete reviewed import with explicit populated replacement authorization. Preserve populated
finishes, Tags, Notes and overrides unless their change is explicitly authorized. Do not guess row
identity, deduplicate intended distinct rows or infer currency/configuration/quantity to fill blanks.
Before changing records
Follow the native mutation sequence: Inspect → Prepare → Verify preparation → Apply → Verify result → Complete. Inspect pending work first. Retain the complete original/absence and complete prepared product CSV, actual access metadata, import-source guards and bound intent. Finish durable saving and independently reopen every retained file before the first publisher; writing evidence without rereading it is insufficient. Validate the entire actual prepared CSV. Publish only under actual writer protection with fresh byte/access guards. Mark complete only after actual library bytes, schema, selected changes and preserved data read back.
Use stable request IDs and the exact preview hash under the library binding/retry rules.
A stale preview or reused ID with changed inputs is a conflict, not permission to substitute a new
hash. Empty update changes are a byte-preserving no-op after unique-match validation. Exact repeated
append requests return their verified prior result; a new intentional append has a new operation ID.
product_library.recover inspects retained evidence and actual state, continuing only a proven safe
before/after state. Preserve third-state conflicts, pending work, old logs and unpublished crash evidence.
Historical evidence paths are readable records, not a dependency on the old helper or its locks.
Report the observed result
Return target, request ID, before/after/current hashes and readback-supported outcome, with any
pending recovery reference. An old completed operation may have current_matches_result: false
after later edits; report that difference and preserve current state. Never describe a preview,
receipt alone or delivered instructions as a completed save. Use the completion contract.
For a requested registered authored report, use receive-owned native documents.resolve/register/query
with confirmed coordinates and its complete document/register publication set. One-off derived files
need no registration. No report or library save authorizes adopted schedule, project-fact or EPD changes.
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.

