agentleFS
Sign inStart free
kvantatechkvantatech/RedLine/.github/skills/scope-review/SKILL.md

scope-review

Skill1 starsChanged 3 months agoMITView on GitHub

Type: skill (human gate) · Used by: perf-author (step 4a) · Status: IMPLEMENTED (P1) After script-author drafts a script and before verify-k6-script runs, stop and present the test scope to the human. Do not proceed until the human explicitly confirms or redirects. Inputs: - script_path — path to the drafted script under drafts/<team>/<profile>/script.js - team — team name (e.g. demo-web) - profile — test profile (e.g. benchmark) - test_type — api or browser — asked before exploration begins; determines tooling…

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    After script-author drafts a script and before verify-k6-script runs, stop and present the test scope to the human.

    line 8
  2. Very specific:

    Read script_path and surface exactly:

    line 21
  3. Very specific:

    Hard stop: never call verify-k6-script (step 6) until this skill returns APPROVED

    line 38

≈ “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

scope-review

Present the drafted script's test scope to a human for confirmation before verify rounds are spent.

Type: skill (human gate) · Used by: perf-author (step 4a) · Status: IMPLEMENTED (P1)

Prompt

After script-author drafts a script and before verify-k6-script runs, stop and present the test scope to the human. Do not proceed until the human explicitly confirms or redirects.

Inputs:

  • script_path — path to the drafted script under drafts/<team>/<profile>/script.js
  • team — team name (e.g. demo-web)
  • profile — test profile (e.g. benchmark)
  • test_type — api or browser — asked before exploration begins; determines tooling and script shape

What to present

Read script_path and surface exactly:

  1. Endpoints under test — every HTTP call, grouped by step, with method + URL pattern
  2. What is NOT tested — known pages/APIs discovered during exploration that were excluded, and why
  3. Auth flow — how login is handled (SSO type, steps, what k6 manages automatically)
  4. Metrics being captured — each Trend metric, what it measures, its threshold
  5. Profile — executor, VUs, iterations, maxDuration
  6. Open questions — anything the agent is uncertain about or that a human should decide

Format as a short, scannable brief — not a wall of text.

Gate behaviour

  • Human says confirm / looks good / yes / proceed → skill returns APPROVED; workflow continues to step 5
  • Human redirects (e.g. "also test the jobs page", "remove the IdP lookup") → agent edits the script, re-presents the brief, waits again
  • Hard stop: never call verify-k6-script (step 6) until this skill returns APPROVED

Tools

  • Read — read the drafted script

Data

  • Reads: drafts/<team>/<profile>/script.js
  • Writes: nothing (gate only)

Frozen skill registry: AGENTS.md in this repo

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.

Check your setup, free