Copiez ce prompt dans l’assistant IA que vous utilisez.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/phuryn/product-engineering.Chargement du README du dépôt…
Maps where a product sits in its lifecycle and names the next step plus the matching skill across discovery, shipping, app stack, and agent harness packs.
Affichage de 40 skills collectés sur 43.
'Ask Claude', 'have Claude build or review this': drive Claude Code headless (claude -p) from another agent as a peer, builder or fresh reviewer.
Langue du texte source : anglais
Before 'ship it', a deploy or release, for 'an independent review', and after each fix until a round is clean: a fresh reviewer that never saw the build.
Langue du texte source : anglais
Is this safe to ship? Documents the app, wires the agent's context, runs the correctness, security and performance reviews and an independent unsteered pass, maps test coverage, and compiles one reviewer-ready shipping packet. Started by name only:…
Langue du texte source : anglais
Planning a SaaS stage, 'what's next', 'where are we', calling a stage done: the detailed path from an idea to production, each stage with its done-when.
Langue du texte source : anglais
Adding analytics, session recordings, heatmaps, 'what did users do', Clarity or PostHog: behaviour analytics without analytics cookies, read back by the agent, and what changes when a cookie comes in.
Langue du texte source : anglais
Before 'push it', 'ship it', a deploy, release or go-live, or calling a stage done: the gate, the owner's preview, go/no-go, promote, prove it serves, roll back.
Langue du texte source : anglais
A Supabase query, RPC or migration, 'db push', 'supabase link', RLS or grants, a Supabase error: server-only keys, deny-all RLS, migrations via the CLI.
Langue du texte source : anglais
Adding a variable or secret, 'set up production', a domain or a provider token, 'which database is this', a leaked key: dev and production for an AI-built app, backups, incidents.
Langue du texte source : anglais
Where to start, and what comes next, along the product lifecycle: from a new idea, new evidence, an agreed change, a bug or a release to the next step and the skill that does it. Started by name only: /product:start-here in Claude Code, $product:start-here in…
Langue du texte source : anglais
Before adding a remote MCP server or tool to a web product, adding OAuth to it, or listing it in a directory: ship it right the first time, tests included.
Langue du texte source : anglais
Writing or restructuring AGENTS.md or CLAUDE.md, adding a rule ('remember this'), or after an agent ignored a rule it had: make each rule get met when it applies.
Langue du texte source : anglais
Setting up or changing Clerk sign-in, organizations, roles or billing on Next.js, or sign-in that does nothing or lands wrong: Clerk in production.
Langue du texte source : anglais
Build a session's learnings into the setup: its friction, what went wrong and why, then an improved instruction, route, hook or script, verified, or 'no setup change warranted'. Started by name only: /agent-harness:retro in Claude Code, $agent-harness:retro…
Langue du texte source : anglais
Privacy policy, terms, a cookie banner, consent at sign-up, a public front door: legal pages drafted from what the code does while it is built, held to it by a test, with the owner's facts and sign-off.
Langue du texte source : anglais
Auditing AI-built code against its docs: where the code does what the docs or permissions don't say, access control against documented roles, cited on both sides.
Langue du texte source : anglais
'I have an idea', 'is this worth building', 'what next': research it and propose what to build, with sources and a prototype to review. Not for agreed changes or bugs.
Langue du texte source : anglais
'Ask Codex', 'check with Codex', handing Codex a build, or stuck between two framings: the Codex CLI as a peer that argues and builds.
Langue du texte source : anglais
Before spawning a subagent or dispatching a build, review or research, and before trusting its report: the brief, the delegate, parallel runs, the handoff.
Langue du texte source : anglais
'Review this', 'find bugs', 'is this fix safe': review code for defects that matter, correctness first, each finding refuted before it's reported.
Langue du texte source : anglais
Writing or running tests, proving a fix, a red or flaky run, a fix that didn't land, 'is it verified', 'run the gate': tests where green means something.
Langue du texte source : anglais
Publishing an app, adding /health or a cron job, 'set up monitoring', 'is it down': content checks, a second location, heartbeats, a tested alert route.
Langue du texte source : anglais
Long agent work that must survive compaction: multi-hour runs, background jobs, work waiting on someone's decision, 'what's the status', 'where were we'.
Langue du texte source : anglais
An agent keeps breaking a rule ('it did it again', 'make this impossible', 'add a hook', 'my hook didn't fire'): make it a hook, permission rule or script.
Langue du texte source : anglais
Write the handover a fresh session starts from: the objective, what is true now, the evidence actually obtained, what is left, the open decisions and the next concrete action, reconciled with the disk first. Started by name only: /agent-harness:handover in…
Langue du texte source : anglais
A coding agent on Windows: Git Bash path rewriting, PowerShell quoting and encoding, CRLF. Use when output comes back garbled, or it works here and breaks there.
Langue du texte source : anglais
'What should we test' or a coverage map: derive the coverage map and missing tests from docs and code; check mode reports staleness.
Langue du texte source : anglais
'Document the app': write or refresh an app's system docs from its code. 'Are the docs right?': check mode, which only reports where docs and code disagree.
Langue du texte source : anglais
Only when a performance audit is asked for (ship-check asks by name; a release proposes one, never runs it): a static audit for N+1 queries, over-fetching, missing indexes and caching.
Langue du texte source : anglais
Only when a security audit is asked for (ship-check asks by name; a release proposes one, never runs it): a static audit of AI-built code against its documented trust boundaries and permissions.
Langue du texte source : anglais
Documenting an AI-built app for handoff, review or audit: the docs that make it reviewable (architecture, flows, permissions, variables, coverage).
Langue du texte source : anglais
Before building, submitting or changing a ChatGPT plugin or Apps SDK app: get it through OpenAI's directory review (auth, package, OAuth, data rules, portal).
Langue du texte source : anglais
Before designing a screen or design system, choosing colours, type or components, or judging the look: design, build and review product UI with its owner.
Langue du texte source : anglais
Only when the Agent SDK is asked for, an agent needs Claude Code's own tools, or the app already runs it: embed Claude agents in a Next.js app with the Agent SDK.
Langue du texte source : anglais
Building, adding or wiring up an agent or an agent chat inside a Next.js app: embed Claude agents on the Messages API, the default way.
Langue du texte source : anglais
Adding sign-in, a role, a route that touches data, API tokens, a webhook or job, or 'is this secure': who may do what in a multi-tenant SaaS.
Langue du texte source : anglais
Adding transactional or alert email, choosing a provider, 'sent twice', 'never arrived': send app email without losing or doubling it, with one-click unsubscribe.
Langue du texte source : anglais
Choosing the first market or customer segment to win, scored on burning pain, willingness to pay, winnable share and referrals.
Langue du texte source : anglais
Competitive research or a competitive brief: competitors and substitutes, their strengths and weaknesses, where to differentiate.
Langue du texte source : anglais
Designing how a product grows: loops that compound (viral, usage, collaboration, user-generated, referral).
Langue du texte source : anglais
Exploring customer segments, audiences or new markets: 3-5 segments with their jobs, pains and product fit.
Langue du texte source : anglais
Le README n’a pas pu être chargé. Vous pouvez toujours consulter les Skills du dépôt ci-dessous.