agentleFS
IamK77IamK77/Skill/skills/surface/lookout/SKILL.md

lookout

Skill2 starsChanged 31 days agoApache-2.0View on GitHub

Establish delivery observation and decision-linked frontend telemetry for a chosen release. Use for preview, measurement, and post-release checks with privacy and rollback boundaries.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    When this stage is fulfilled: checklist advance plan --run "$RUN".

    line 41
  2. Distinctive:

    Create or inspect the preview and relevant health/performance observations.

    line 45
  3. Very specific:

    If an input or permission is missing, name the blocker and leave the relevant item pending.

    line 73
  4. Very specific:

    After all required work and stage closures is recorded, use checklist done --run "$RUN".

    line 79

≈ “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
<!-- Copyright 2026 IamK77 — Licensed under the Apache License, Version 2.0. See ./LICENSE and ./NOTICE · https://www.apache.org/licenses/LICENSE-2.0 -->

lookout

Establish delivery observation and decision-linked frontend telemetry for a chosen release. Use for preview, measurement, and post-release checks with privacy and rollback boundaries.

Inputs

Change or release; intended user outcome; authorised environments; success/abort signals; permitted telemetry and retention.

Run record

Use checklist 0.5 or newer for this SOP. Reading or reloading the skill must not reset work. For a new task, run checklist init "${CLAUDE_SKILL_DIR}" --new --path "/absolute/project"; retain its returned ID as RUN. For existing work, use checklist resume "$RUN", then checklist show --run "$RUN". Outside Claude, replace the skill-directory variable with this directory’s actual path.

Commands below record work after it is done. Replace evidence placeholders with concise artifact locations and observations. Manual confirmations are not independent proof; a sensor pass covers only the command and inputs it observed. verify does not close a stage; advance checks that its required readings are fulfilled. Use report --run "$RUN" for the retained history.

Procedure

plan

Define the decision each signal informs and the environment to observe. Choose a representative preview path and rollback/disable action. Avoid collecting data merely because it is available.

Record these artifacts after doing the work:

  • Signals link to explicit release or product decisions. checklist check plan decision --run "$RUN" --evidence "<artifact and observation>"
  • Environment, rollback, and telemetry/privacy boundaries are recorded. checklist check plan boundary --run "$RUN" --evidence "<artifact and observation>"

When this stage is fulfilled: checklist advance plan --run "$RUN".

instrument

Create or inspect the preview and relevant health/performance observations. Validate event schemas and sampling, and exercise a known success and failure so the telemetry has meaning.

Record these artifacts after doing the work:

  • The changed journey is observable in the intended preview environment. checklist check instrument preview --run "$RUN" --evidence "<artifact and observation>"
  • Health and event instrumentation were exercised with known cases. checklist check instrument signals --run "$RUN" --evidence "<artifact and observation>"

When this stage is fulfilled: checklist advance instrument --run "$RUN".

handoff

Record measured baselines, release thresholds, owners, and what happens when a signal trips. Stop before external rollout unless specifically authorised.

Record these artifacts after doing the work:

  • Baselines, thresholds, and their limitations are documented. checklist check handoff thresholds --run "$RUN" --evidence "<artifact and observation>"
  • Each material signal has an owner and response action. checklist check handoff response --run "$RUN" --evidence "<artifact and observation>"

When this stage is fulfilled: checklist advance handoff --run "$RUN".

Branches

For local-only work, document a proposed production measurement rather than adding external tracking. Consent, retention, and access requirements come from the actual product context.

If an input or permission is missing, name the blocker and leave the relevant item pending. A changed requirement may need a new run; an accepted checklist edit uses resume "$RUN" --refresh and requires fresh readings. To abandon work, use checklist reset --run "$RUN" --reason "<reason>"; history is retained.

Completion

A decision-linked observation plan and tested instruments. A dashboard is evidence to interpret, not a self-proving claim of product health.

After all required work and stage closures is recorded, use checklist done --run "$RUN". This archives the result without deleting its history; it does not authorise any external action.

Reference shelf

Open the technique relevant to the current step. These notes provide concrete methods and examples, not additional phases; this entrypoint defines the run's completion conditions.

  • Prepare observations for an authorised frontend delivery
  • Make telemetry and delivery constraints concrete
  • Measure a relevant frontend performance problem
  • Validate event meaning before interpreting a graph
  • Observation that informs a release decision

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.