tech-pack
Skill2 starsChanged 25 days agoMITView on GitHub
Use when a garment design for your apparel line must become a factory- or POD-ready tech pack (artwork files, placements, colourways, BOM, labels, size spec, QC points). Runs the creative-director in a fresh context and writes the pack with provider file specs and FTC label elements quoted from fetched pages.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-reviewSkill
- ai-mesh-cleanSkill
- cad-buildSkill
- couponSkill
- curriculumSkill
- dfm-reviewSkill
- fileSkill
- gddSkill
- ip-checkSkill
- led-budgetSkill
- lesson-learnedSkill
- makerworld-publishSkill
- material-pickSkill
- mcp-new-toolSkill
- ortho-sheetSkill
- pi-power-budgetSkill
- preprint-checkSkill
- promo-planSkill
- qa-gateSkill
- render-criticSkill
- research-oneSkill
- research-topicSkill
- retopoSkill
- safety-sheetSkill
- sculptSkill
- slicer-questionSkill
- style-bibleSkill
- unit-costSkill
- verifySkill
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 17
Read the brand's style-bible.md and voice guide if present, and any apparel notes in knowledge\ (link, do not restate).
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Overview
Tech pack for: $ARGUMENTS
Output on disk, in your brand folder (default work\brand\<brand-slug>\): tech-packs\<garment-slug>\tech-pack.md, an artwork\ folder with print files at the fetched spec, check_artwork.py beside them, and a claims table research\inbox\apparel\tech-pack-<garment-slug>.md for /verify.
When to use
A garment is leaving the sketch stage for a POD provider or a cut-and-sew factory. Not for the brand's visual law (/style-bible), not for the garment's cost or channel (business-strategist), not for IP clearance of the artwork (/ip-check first).
Steps
- Read the brand's
style-bible.mdand voice guide if present, and any apparel notes inknowledge\(link, do not restate). Existing material you point to is read only. - Fetch this run: Printful file guidelines https://help.printful.com/hc/en-us/articles/50264019148177; the Printify print-file requirements page under https://help.printify.com/ (record the exact URL fetched); the FTC textile labelling guide https://www.ftc.gov/business-guidance/resources/threading-your-way-through-labeling-requirements-under-textile-wool-acts. Record format, colour space, DPI, pixel dimensions per placement and the required label elements, each with page date (short quotes, paraphrase the rest).
- Print-method section: DTG vs screen vs embroidery, with the conditions each fetched page states (minimums, fabric, colour limits, minimum text size). Undecided becomes numbered NEEDS MAKER (quantity, blank, budget).
- Pack structure: cover (brand, style number, season); flats front and back (from
/ortho-sheetif a 3D garment exists, else vector flats); placements with dimensions in mm and inches from named garment reference points; colourways (hex from the style bible plus ink or thread references); BOM (blank SKU, vendor URL, label stock); label artwork and placement with the FTC elements marked "facts, not legal advice"; size spec table; packaging; QC points. - Artwork files: export to
artwork\at the recorded spec. Writecheck_artwork.py(run with.venv\Scripts\python.exe) that reads each PNG's width, height and bit depth from the IHDR chunk and compares against the spec table; paste its output in the pack. - Facts (specs, label elements, method limits) also go into the claims table for
/verify; mark them[pending /verify]in the pack until aresearch\verified\apparel\...path exists. - Return paths,
check_artwork.pyoutput, claims-table path, NEEDS MAKER questions.
Common rationalizations
| Rationalization | Reality |
| "300 DPI is the universal rule." | Each provider states its own spec per product and placement. Cite the fetched page with date. |
| "The label just needs the brand name." | Record the FTC elements from the fetched guide; what is missing is a fact with a URL, and the decision is yours (and your attorney's). |
| "I can eyeball the placement." | Placements are dimensions in mm and inches from named reference points, or the factory guesses. |
| "The PNG exported, it must match the spec." | Run check_artwork.py. Exported-but-wrong files pass a glance and fail at the printer. |
Red flags (stop and fix)
- A spec or label element without a fetched URL and date.
- Artwork in
artwork\thatcheck_artwork.pyflags or that was never checked. - A placement without numeric dimensions.
- Hex values that are not in the style bible and not marked as a new colourway proposal.
Verification
- Printful, Printify and FTC pages fetched this run; URLs and dates in the pack.
check_artwork.pyrun; every file inartwork\passes or is listed as failing with the reason.- Every placement has mm and inch dimensions from a named reference point.
- Claims table written under
research\inbox\apparel\; path returned. - NEEDS MAKER questions numbered.
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.

