Index of every page on this site: llms.txt
All skills
jeremylongshore avatar

/algolia-local-dev-loop

@820dfc8
Run it yourself

Create a fast local development loop for Algolia record transforms and search behavior without contaminating shared indices. Use when iterating on search code, fixtures, or client wrappers. Trigger with "Algolia local development", "mock Algolia", or "test search locally".

Use this Skill: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/algolia-local-dev-loop

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈74 tokens for metadata: the name and description. ≈814 when used: this file. ≈333 more on demand in 1 file.

Description uses 3.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈298 characters, or 3.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Algolia Local Development Loop

Overview

This skill combines deterministic offline tests with an optional disposable-index integration test. It makes the local loop useful without pretending a mock reproduces provider ranking, task timing, or authorization.

Prerequisites

  • A named repository, environment, and Algolia application or index in scope
  • The local lockfile and installed client types as implementation authority
  • A safe read-only query or explicitly disposable test target
  • Current first-party documentation for any provider behavior that affects the change

Tool Discipline

Use Read, Glob, and Grep to inspect local code, configuration names, tests, and dependency versions. Use WebFetch only for current official Algolia documentation. Use Write or Edit only after identifying the target files, constraints, and verification plan.

Current Contract

  • Keep record transformation and query construction in pure functions that can be tested offline.
  • Mock only the application-owned client boundary, not internal SDK implementation details.
  • Use unique disposable index names for live checks and never reuse production credentials.
  • Wait for write tasks and clean up live fixtures explicitly.

Authentication

Offline tests need no credential. Optional live tests use a custom key restricted to the disposable prefix and are disabled when credentials are absent.

Instructions

  1. Inspect the current client wrapper, package scripts, fixtures, and test framework.
  2. Extract pure record-shaping and query-building functions with focused unit tests.
  3. Create a typed adapter and mock its application-level responses and failures.
  4. Add an opt-in live test that validates a generated disposable index name.
  5. Write known records, wait, query, assert, and clean up while retaining task receipts.
  6. Document how developers select offline versus live mode and how stale test indices are reported.

Approval Boundaries

Do not require live credentials for the default test command, share a personal Admin key, or clean up any index outside the validated disposable prefix.

Output

Return the local scripts, test boundary, fixtures, live-test guard, cleanup behavior, and evidence for both credential-free and optional integration modes.

Error Handling

Condition Response
Credential absent Run offline tests and report the live test as skipped.
Mock diverges from adapter Update the adapter contract and its typed fixture together.
Disposable prefix invalid Fail before any network write.
Cleanup fails Report the exact retained index for manual review.

Examples

Use this compact input and expected handoff to calibrate scope and evidence quality.

Input:

mode=offline-default; integration=ALGOLIA_LIVE_TEST=1; prefix=dev-$USER-$RUN

Expected handoff:

unit=pass; live=skipped; production-index-access=none

Resources

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill facilitates a safe local development loop for Algolia by emphasizing the use of mocks and disposable indices. It explicitly warns against using production credentials and focuses on offline testing. The only security finding is a standard surface for indirect prompt injection, as the skill is designed to ingest and process local repository code.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at 820dfc8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
What it can do
Reads files Network Edits files
Modelinherit
argument-hint
[repository-path] [test-mode]
version
1.8.0
author
Jeremy Longshore <jeremy@intentsolutions.io>
All 6 allowed tools
ReadGlobGrepWebFetchWriteEdit
Other metadata
tags
[
  "saas",
  "algolia",
  "development"
]
model
inherit
effort
medium
compatibility
Designed for Claude Code

README badge

README badge for jeremylongshore/tons-of-skills-marketplace/algolia-local-dev-loop