agentleFS
BagelHoleBagelHole/BagelSkills/skills/launch-forensics/SKILL.md

launch-forensics

Skill2 starsChanged 4 months agoMITView on GitHub

Use this skill when preparing for a public release, major launch, or production rollout and the actual product must be investigated rather than covered by a generic checklist. Verify critical journeys, discoverability, accessibility, performance, observability, security basics, deployment, and rollback with evidence; rank only launch-relevant findings.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a required input is retrievable from available tools or artifacts, retrieve it rather than asking the user.

    line 41
  2. Distinctive:

    Verify configuration, migrations, secrets handling, health checks, logs, alerts, capacity assumptions, backups where relevant, deployment …

    line 65
  3. Very specific:

    Verify titles, descriptions, canonical/robots/sitemap behavior, social previews, links, contact/support, legal/privacy surfaces, email …

    line 71
  4. Distinctive:

    Never execute purchases, messages, destructive actions, DNS changes, or production rollouts without explicit authorization.

    line 84
  5. Distinctive:

    Do not call inaccessible controls “missing”.

    line 85

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Launch Forensics

Outcome

Find the defects and missing controls most likely to damage a real launch, backed by direct verification.

This skill changes the agent's process: it requires evidence, explicit claim strength, and a checkable completion boundary. Load references/playbook.md only when deeper prompts or rubrics are needed. Use assets/output-template.md when producing the final artifact.

When to use

  • The user asks whether a product is ready to launch, ship, release, announce, or deploy broadly.
  • A website or application needs a preflight across product, engineering, growth, and operations.
  • A major release needs go/no-go evidence and rollback confidence.

Do not use when

  • The request is an early design critique with no imminent release.
  • The user asks for a single specialist audit and broader launch scope would distract.

Required inputs

  • Release target, date, audience, and traffic expectations
  • Production-like environment and safe test credentials
  • Deployment/runbook/monitoring access available
  • Business-critical journeys and irreversible actions

If a required input is retrievable from available tools or artifacts, retrieve it rather than asking the user. Ask only when a missing answer represents authority, preference, or risk that tools cannot resolve.

Workflow

1. Define launch truth

Record the exact artifact, commit, environment, audience, launch mechanism, owner, and decision deadline. Define go/no-go criteria before testing.

Complete when: artifact, environment, criteria, and authority are fixed

2. Map critical journeys

Identify acquisition, activation, core value, payment if any, recovery, support, and deletion/export paths. Mark destructive or external actions that require authorization.

Complete when: critical paths and forbidden actions are explicit

3. Inspect the product directly

Execute safe journeys on representative desktop and mobile environments. Capture screenshots, console/network failures, metadata, accessibility signals, and performance evidence.

Complete when: journeys have direct evidence or are marked unverified

4. Inspect operational reality

Verify configuration, migrations, secrets handling, health checks, logs, alerts, capacity assumptions, backups where relevant, deployment sequence, and rollback procedure.

Complete when: release and recovery controls have evidence or explicit gaps

5. Check discoverability and trust

Verify titles, descriptions, canonical/robots/sitemap behavior, social previews, links, contact/support, legal/privacy surfaces, email identity, and honest claims as applicable.

Complete when: applicable trust surfaces are verified

6. Issue the launch verdict

Classify blockers, launch risks, and post-launch improvements. Attach evidence, owner, fix/retest condition, and confidence. Give go, conditional go, or no-go against the predeclared criteria.

Complete when: the verdict follows declared criteria and every blocker has a retest

Operating rules

  • A checklist item is not passed until inspected or tested.
  • Never execute purchases, messages, destructive actions, DNS changes, or production rollouts without explicit authorization.
  • Do not call inaccessible controls “missing”; mark them unverified.
  • Separate launch blockers from ordinary backlog quality.
  • Retest blockers after fixes before changing the verdict.

Output contract

The final result must contain:

  • Artifact/environment and coverage statement
  • Critical journey results
  • Evidence-backed blocker and risk register
  • Operational and rollback verification
  • Discoverability/trust findings
  • Go, conditional-go, or no-go verdict with rationale

Distinguish observed, inferred, assumed, and unverified claims. Link to files, commits, screenshots, commands, logs, or supplied sources when those artifacts support a consequential conclusion. Keep the executive result concise; move detail behind appendices when necessary.

Common pitfalls

  • Checklist completion without touching the product.
  • Scope explosion into every possible improvement.
  • No-go by taste rather than declared criteria.
  • Assuming deployment success proves user-journey success.

Verification checklist

  • The requested outcome—not merely the procedure—has been satisfied.
  • Every consequential claim is supported, qualified, or explicitly unverified.
  • The workflow's completion criteria are met in order.
  • Safety boundaries and forbidden side effects were respected.
  • The output follows assets/output-template.md or contains equivalent information.
  • Remaining unknowns have an owner, next action, or stated consequence.

Resources

  • references/playbook.md — deeper domain prompts and evaluation guidance.
  • assets/output-template.md — reusable final-output structure.
  • evals/evals.json — output-quality cases.
  • evals/trigger-evals.json — positive and negative description-trigger cases.

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.