Skill v1.0.0
Automated scan100/100name: loupe-discovery description: "Use when a bridge runs a discovery run of a Loupe project, when a prompt names loupe-discovery, or when writing a readiness report." metadata: version: "1.0.0"
Running a Loupe discovery
Discovery finds what Loupe works better with before agents work the cards of a project. A check that the project does not meet is a suggestion, never a failure. You read the project setup, the workflow and the repository, and you write a readiness report. The owner ticks proposals in the report. When the owner approves the report, Loupe creates one card in Next for each ticked proposal.
The prompt names the project, the projectId, the card number and the cardId of the discovery card.
Read only
Discovery changes nothing. Every change goes into the report as a proposal. Do not commit, push or create a branch. Do not change a file in the repository. Do not create, change or move a card. Do not change the project, its columns, its automation, its inbox or its origins.
These tools are forbidden: card_create, card_update, column_create, column_update, column_reorder, column_delete, automation_settings_update, project_update, project_origins_set, readiness_guide_set and discovery_start.
You can run commands that only read, such as git remote -v, ls or cat. Do not run a build or a test suite that writes outside a temporary directory. Read how the project runs them instead.
Steps
- Call
readiness_get. Each of itsrowshas akey,doneandstatus. The keys areagent,workflow,bridge,github,agent_accountandrepository. These rows tell you what Loupe sees of the setup. - Read the
discoveryfield ofreadiness_get. It is the latest run of the project. ItscardNumbermust be the card number of your prompt. If it is not, stop and report the mismatch. - Keep
discovery.runId. It is therunIdthatreadiness_report_submittakes. Whendiscovery.stateisrevising, follow "Revising a report" below. When it is neitherrequestednorrevising, the run takes no report, so stop and report the state. - Call
workflow_get. It returns thetemplatewith itskeyandversion, and thecolumns. Itskindslist each kind of work that the workflow asks a bridge to do. Each kind has anoriginoftemplateorapp, therulesthat ask for it, and itschecks. The checks name what that work needs. - Read the repository. Find the build and test commands, the CI config and the agent instruction files, such as
AGENTS.mdorCLAUDE.md. Read.loupe/lifecycle.mdand its sections when the file exists. Read the git remote. - Apply the generic checks.
- How to build and test the project, and whether CI runs those commands.
- An instructions file for agents, such as
AGENTS.mdorCLAUDE.md. - The GitHub remote, the GitHub App, the bridge and the agent GitHub account. Use the
readiness_getrows for what Loupe sees. - The browser tool of the visual check is installed, and an agent can use it. The tool is the one that the profile
Visual checksection names, or Playwright when the section is missing or names none. Find it in the repository and its installed copy, such as apackage.jsonfor Playwright. From a new temporary directory, launch it headless, take one screenshot of a static HTML file, and read the image. A missing tool is a suggested finding. Propose a card that installs the tool, or that makes its browser start. The stage skills use it for the visual check ofloupe-stage-implementation/references/visual-check.md. Check neither the profile section nor the app. - The repository profile,
.loupe/lifecycle.md. Every stage reads it. When the file is missing, or git does not track it, the check is a suggested finding: the owner runsloupe init, then commits the file. Otherwise search it for the text "detected, check it".loupe initwrites that text after each value it guessed. Compare each marked value with the repository, the CI config and the agent instruction files. A gate command that does not exist, or that CI does not run, is a wrong value. A check that CI runs before a merge and the gate lacks is a missing value, so propose it too. Write one proposal for each wrong value. The body names the section, the line, the value and the correct value. The proposal removes the marker from the line it fixes. A marked value that is right also loses its marker, so list it in the evidence and propose no card. - Each setup step that an agent cannot do through the MCP. For example, only the owner can install the GitHub App in a browser, and no tool changes the workflow template.
- Apply each check of each kind against the repository. A kind can have an empty
checkslist. A write fallback, such assyncormerge, carries no list. Write no finding for such a kind. Name it in thesummaryas a kind that only the generic checks cover.
- A check that starts with a condition, such as "When the project has a user interface", gets no finding when the project does not meet the condition. Name it in the
summaryas skipped, with the reason. - A check for a Design System artifact that mirrors the design system looks for three marks in
.loupe/lifecycle.md, the agent instruction files and the skills they name. M1 is the title or the address (claude.ai/artifact/<id>) of the Design System artifact. The phrase "Design System" alone does not pass. M2 is a command or a script that builds the artifact files from the code. M3 is the steps that say when and how to rebuild the artifact. M1 always applies. M2 and M3 apply only when the design system also lives in the repository. A project that keeps its design system only in a named artifact passes the design system check and needs M1 alone. A missing mark is a suggested finding, and the evidence names it. A passing mark names the file and the line. Check that an M2 command or script exists, and never run it. - When the worker has the
Artifacttool, call it once withlistandtype"Design System", and confirm that an artifact matches M1. When none matches, the finding is suggested. A headless worker has noArtifacttool. Without it, trust the repository, and say in the evidence that the artifact was not checked. Never list other artifacts of the account, and call no action that writes. - A project with a suggestion on the design system itself proposes a card to extract one. A suggestion on the artifact proposes a card for the marks an agent can add. A project that keeps its design system in the repository and has no artifact gets a suggested finding, with no card. The evidence says that the owner creates the artifact in a browser on claude.ai, from the repository export, and then names it in
.loupe/lifecycle.mdor the agent instructions (step 10).
- Write one proposal for each suggestion that a card can close. Give it a
keythat is unique and kebab-case, atitle, atypeand abody. Callboard_columnsto read the card types of the project. Thetypeis thekeyof a type whosechildrenis false. Write the body so that a session with no context can act on it: what to do, why, and where. - Call
card_searchwith the key words of each suggestion before you write its proposal.card_searchreturns finished cards too, so read each row'sstatus. When an open card covers the suggestion, setopenCardNumberto its number. - Some suggestions need the owner on a settings page or in a browser. Do not propose a card for such a suggestion. Say what the owner must do in the evidence of the finding.
- Call
readiness_report_submitwithrunId,workflow,findings,proposalsandsummary. Setworkflowto the templatekey. Each finding has acheck, astatusofreadyorsuggested, and anevidencein short Markdown. Keep thesummaryto a few sentences. The tool returns thedocumentIdand theurlof the report. - Open a review of the report in the inbox. Call
inbox_askwith one item ofkindreview,reviewDocumentIdset to thedocumentId, andcardIdsset to thecardId. PasssessionIdandbridgeIdfrom the footer line "Your session id is … and your bridge id is …". Leaveblockingfalse, so the ask closes at once. Loupe does not put the report in the inbox for you. When the prompt has no such line, the inbox is off, so skip this step. - End with a short reply that gives the report
urland the number of suggestions.
Revising a report
The prompt of a revision names the kind discovery-revise. The owner asked for changes to the report, and the run is revising.
- Read the report document with
document_get. Thediscoveryfield ofreadiness_getnames the card, and the card links the document with the tagreadiness-report. - Read the comments with
document_get_review. Address each comment, and check the repository again where a comment asks for it. - Call
readiness_report_submitwith the samerunId, and the whole revisedworkflow,findings,proposalsandsummary. Loupe stores a new version of the same document, and replaces the proposals that made no card. - End with the report
url. Skip step 12 of the steps above: the owner already has the report in the inbox.
If the owner approves the report while you revise it, the tool refuses your submit. Report the refusal and stop.
When something fails
A tool refusal names its fix. When the fix is a change that discovery must not make, stop and report the refusal in your final reply.
Two refusals of readiness_report_submit mean that the run takes no report: "This run does not wait for a report now" and "This run has a report already". A revising run takes a report. Do not retry, and do not start a new run. Report the refusal and stop.