agentleFS
HainrixzHainrixz/agente-pagokit/skills/doctor/SKILL.md

doctor

Skill68 starsChanged 6 months agoMITView on GitHub

Audits an existing PagoKit integration in the current project against the generated per-provider checklist, so it covers every provider in the catalog rather than a hardcoded few. Checks .gitignore covers .env, that env vars are present and use test-key prefixes, that the webhook secret looks valid, that the webhook handler verifies signatures, that the minimum events for the integrated provider are routed, and that PAGOKIT_INTEGRATION.md exists. Used by /pagokit:doctor. Read-only — never writes files.

  • Reads credentials

81 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use uninstall, cancel and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    uninstall

    Uninstall a community skill that was installed via the hub. Confirms before deleting files, refuses to touch first-party plugin skills, and logs every action. Use when the user wants to fully remove a community skill ("uninstall [skill]", "remove this skill") rather than just disable it.

    Also in 6 projects that use this

  • woosikkimSkill

    cancel

    Clear any stale OMC-Slim state

    Also in 3 projects that use this

  • ibahgatSkill

    mode

    Inspect or switch omi operating mode/profile for speed, depth, autonomy, or strict quality gates.

    Also in 3 projects that use this

  • BlockSkill

    open

    Open markdown documents in Penpal for collaborative review. Use when you want a human to review a document, plan, or research artifact.

    Also in 3 projects that use this

  • QinghongLinSkill

    editor

    Read analyst.json and detective.json, make all editorial decisions — what the blog argues, which findings matter, narrative arc and section structure. No visual design. Outputs editor.md (prose) and editor.json (structure with edt_xx IDs).

    Also in 3 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 15 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 61 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run each check and report a list of [OK] / [WARN] / [FAIL] lines.

    line 32
  2. Very specific:

    Read skills/doctor/PROVIDER_CHECKS.md and find the section for the integrated provider.

    line 45
  3. Distinctive:

    If the integration declares an ORM (Prisma / Drizzle / SQLAlchemy / Active Record), verify these tables exist in the schema file:

    line 75
  4. Very specific:

    Do NOT echo secret values back to the user when reporting (read .env but report [OK]/[FAIL], never the value).

    line 118
  5. Distinctive:

    Do NOT write files, run migrations, or modify anything — strictly read-only.

    line 119
  6. Distinctive:

    Do NOT fail loudly if the project has no PagoKit-generated artifacts.

    line 120
  7. Distinctive:

    Do NOT recommend fixes that require live keys (e.g., don't tell the user to "go to dashboard and rotate the webhook secret" as the first …

    line 121

“Common” is measured: kept by at least 6 in 10 of the 61 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Copyright (c) 2026 Enrique Rocha (@soyenriquerocha) · tododeia.com · id er-fee52fa9 -->

doctor

You audit an existing PagoKit-generated integration. Read-only. Never write files.

Source of truth

The first thing you read is PAGOKIT_INTEGRATION.md in the project root. It was written by integration-specialist when the integration was generated and contains:

  • The provider id (any entry in the catalog — see PROVIDER_CHECKS.md for the full list)
  • The list of files created
  • The list of events handled vs TODO
  • The deploy target
  • The detected stack/ORM
  • The last_generated_at timestamp
  • The pinned SDK version

If PAGOKIT_INTEGRATION.md does not exist, this is NOT necessarily an error — the user may have an integration that predates PagoKit. In that case, ask the user "I don't see PAGOKIT_INTEGRATION.md. Was this integration generated by PagoKit? If not, I can still audit a known provider — which one are you using?"

Audit checklist

Run each check and report a list of [OK] / [WARN] / [FAIL] lines. Group by category. At the end, summarize: "N OK, M warnings, K failures."

Category 1 — Environment hygiene

CheckHowSeverity
.gitignore exists and includes .env (or .env* minus .env.example)Read .gitignore from project root; walk up to repo root if necessaryFAIL if not covered
.env not committed to gitIf .git/ exists, check git ls-files .env would be emptyFAIL if committed
.env.example existsGlob .env.exampleWARN if missing
.env.example contains only test-mode values (compare each credential's live_prefix from PROVIDER_CHECKS.md)Read it, grep for live prefixesFAIL if live keys present

Category 2 — Required env vars per provider

Read skills/doctor/PROVIDER_CHECKS.md and find the section for the integrated provider. It lists every credential that provider needs, its expected format, its scope and the severity of a miss — generated from the catalog, so it covers every provider PagoKit knows about rather than a handful frozen into this file.

Then read the user's .env (read it, never echo it) and compare.

For each required variable:

  • [OK] — present and matches pattern
  • [FAIL] — missing
  • [FAIL] — present but doesn't match pattern
  • [WARN] — uses _live_ / _prod_ prefix (production key during audit; the user should know)

Category 3 — Webhook handler quality

For each webhook file declared in PAGOKIT_INTEGRATION.md (or detected via expected_filenames in the catalog), check it against the provider's section in PROVIDER_CHECKS.md — which already states the verification family, the correct secret env var, whether the payload is authoritative, and the replay strategy:

  • [OK/FAIL] — the file imports or calls the provider's canonical verifier (or carries the // @pagokit:signature-verified tag).
  • [OK/FAIL] — the route uses raw body capture appropriate for the stack (per Rule 5 / SECURITY_RULES.md).
  • [OK/FAIL] — the handler's switch covers every event in providers.json.webhook.required_events_minimum. Unhandled events should at least be logged with a TODO comment.
  • [WARN] — if the file contains console.log(event) or similar (Rule 6).
  • [OK/FAIL] — replay protection: if replay_mitigation_strategy requires event-id-dedup, look for a query against webhook_events_processed (or equivalent).

Category 4 — Idempotency

  • [OK/FAIL] — the checkout endpoint generates an idempotency key with crypto.randomUUID() / uuid.uuid4() / SecureRandom.uuid (Rule 4).
  • [OK/FAIL] — the DB has an idempotency_keys table (or equivalent file declared in PAGOKIT_INTEGRATION.md).

Category 5 — DB schema

If the integration declares an ORM (Prisma / Drizzle / SQLAlchemy / Active Record), verify these tables exist in the schema file:

  • payments (or provider-named, e.g. stripe_payments)
  • subscriptions (if billing_mode == subscription)
  • customers
  • idempotency_keys
  • webhook_events_processed

Category 6 — Production readiness pointer

Last check: does PAGOKIT_PRODUCTION_CHECKLIST.md exist in the project root?

  • [OK] — exists; remind user to read it before flipping to live keys.
  • [WARN] — missing; suggest re-running /pagokit:start to regenerate it.

Output format

PagoKit Doctor — <provider> integration audit
Generated <last_generated_at> · stack: <stack> · deploy: <deploy_target>

Environment hygiene
  [OK]   .gitignore covers .env
  [OK]   .env not tracked in git
  [OK]   .env.example uses test prefixes
  ...

Webhook handler
  [OK]   app/api/webhook/stripe/route.ts verifies signature
  [OK]   raw body captured correctly (Next.js App Router pattern)
  [FAIL] customer.subscription.updated not routed (expected per Rule providers.json)
  ...

(continue per category)

Summary: 17 OK · 2 warnings · 1 failure

Next steps:
1. Route the missing event customer.subscription.updated (see templates/stripe/subscription.md).
2. Address the warnings before going live.

Anti-patterns

  • Do NOT echo secret values back to the user when reporting (read .env but report [OK]/[FAIL], never the value).
  • Do NOT write files, run migrations, or modify anything — strictly read-only.
  • Do NOT fail loudly if the project has no PagoKit-generated artifacts. Offer to set up an audit for a known provider instead.
  • Do NOT recommend fixes that require live keys (e.g., don't tell the user to "go to dashboard and rotate the webhook secret" as the first step — first verify the test sandbox passes).

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.