agentsclimarketplace

Fp add spec

Skill endorhq/flightplanner/skills/fp-add-spec

Create a new E2E_TESTS.md specification file for a packageFrom its SKILL.md

Install
npx -y skills add endorhq/flightplanner --skill fp-add-spec

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.3 KB, as published. Nobody here has run it

Add E2E Spec

Create a new E2E_TESTS.md specification file for a package by analyzing its source code, commands, and public API.

Additional instructions from the user: "$ARGUMENTS". Ignore if empty.

Phase 1: Analyze Package

  1. Identify the target package:

    • If $ARGUMENTS specifies a package path, use that.
    • If in a package directory, use the current package.
    • Otherwise, ask the user which package to analyze.
  2. Read the package to understand:

    • What the package does (README, package manifest, main entry points)
    • Public API / exported commands / CLI interface
    • External dependencies (what it calls: Docker, HTTP APIs, CLI tools)
    • Configuration files it reads or creates
    • State it manages (databases, file stores, caches)
  3. Check if an E2E_TESTS.md already exists for this package. If it does, inform the user and suggest using update-spec instead.

Phase 2: Draft Spec

  1. Determine the suites. Each major command, workflow, or feature area becomes a suite.

  2. Include an Index section at the top of the spec (after the title and description) with a markdown link to every suite (e.g., - [Suite Name](#suite-name)).

  3. For each suite, draft these sections using heading levels appropriate to their nesting depth (e.g., if the suite is an H2, then these sections are H3; if the suite is an H3, they are H4; and so on):

    • Preconditions (heading with bullet list): What setup is needed (temp dir, git repo, config files, mock tools)
    • Features (heading) containing individual features as flat peer subheadings one level deeper. Do NOT create intermediate category headings (e.g., #### Core, #### Edge) — categories are specified only via <!-- category: ... --> HTML comments on each feature. Aim for a mix of features across these categories:
      • core: Primary happy-path scenarios
      • edge: Boundary conditions (empty inputs, very long strings, special characters)
      • error: Failure modes (missing config, invalid input, unavailable dependencies)
      • side-effect: Observable interactions (hooks, notifications, file creation)
      • idempotency: Safe repetition (re-running commands, re-creating resources)
    • Postconditions (heading with bullet list): Verifiable end states
  4. For features requiring real external services, add <!-- skip: ... --> metadata with clear documentation on how to unskip.

  5. Ensure every feature has:

    • A <!-- category: ... --> comment
    • At least one concrete, testable assertion bullet
    • Present tense, declarative language

Phase 3: Review

  1. Present the complete draft spec to the user.
  2. Show a summary:
    • Number of suites
    • Features per suite by category
    • Total feature count
    • Any features marked as skip
  3. Ask the user for feedback and adjustments.

Phase 4: Write

  1. Write the approved spec to E2E_TESTS.md in the package directory.
  2. If a root-level docs/E2E_TESTS.md or E2E_TESTS.md doesn't exist yet, offer to create one with project-wide testing constraints (isolation rules, cleanup patterns, environment variable conventions).
  3. Inform the user they can now run:
    • review-spec to validate the format
    • generate to create test files from the spec

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.