hardisgroupcom/sfdx-hardis

hardisgroupcom/sfdx-hardis

Agent Claude Code

Gather requirements by asking clarifying questions until the problem is fully understood. Use before designing or implementing any change.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Write one concise CHANGELOG.md entry for a user-visible change, following the sfdx-hardis changelog style rules. Use to add a single entry under the beta section.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Design a solution and write a technical specification based on requirements analysis. Use after /analyze.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Propagate new or changed i18n keys across all 9 sfdx-hardis locale files, following the project translation rules. Use when one or more i18n keys need to be added or updated in every locale.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Implement code changes following the technical specification. Use after /design.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Fix the errors reported by ONE MegaLinter linter, following the linter's fix guide. Spawned by the megalinter-fix skill, one instance per failing linter, so several linters can be fixed in parallel. Edits source files but never commits, pushes, or disables anything (linters, rules, inline suppressions) — disables are…

hardisgroupcom/sfdx-hardis

Agent Claude Code

Run MegaLinter locally with npx mega-linter-runner (full flavor run or standalone single-linter image), digest the reports, and return only a compact error list. Use to keep verbose linter output out of the main context. Runs and reports only — never fixes source files.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Watch a MegaLinter CI job (GitHub Actions, GitLab CI, Azure Pipelines or Bitbucket Pipelines) until completion, download its logs, and return only the parsed lint error list. Use to keep large CI logs out of the main context. Observes only — never fixes, edits or pushes.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Analyze one or more failing CI jobs on a GitHub PR (using logs already collected) and fix them - edit sources, validate locally, commit and push. Use after pr-watch reports failures. Returns a request for the user when it cannot fix cleanly.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Collect the current CI state of a GitHub PR and the logs of any failing jobs. Mechanical data-gathering only - it classifies and reports, it does not fix anything. Use to snapshot PR status before deciding what to do.

hardisgroupcom/sfdx-hardis

Agent Claude Code

Build, lint, and run tests to verify the implementation. Use after /implement.

hardisgroupcom/sfdx-hardis

Agent Claude Code

The three definitions in this folder use the Claude Code agent format (YAML frontmatter: name, description, tools, optional model; markdown body with the instructions). The bodies are platform-agnostic — only the frontmatter and the target folder change per platform.