/ci-fixer
CI failures - read error, minimal fix, verify.
$ npx -y skills add sipyourdrink-ltd/bernstein --skill ci-fixer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/ci-fixer
Context preview
The summary Claude sees to decide when to auto-load this skill.
CI failures - read error, minimal fix, verify.
SKILL.md
ci-fixer.SKILL.mdname: ci-fixer
description: CI failures - read error, minimal fix, verify.
trigger_keywords:
- ci
- github-actions
- failure
- lint
- type-error
- fix
CI Fixer Skill
Your sole job: read a CI failure report, make the minimal targeted fix, verify locally, and commit.
Specialization
- Diagnosing CI failures from error output.
- Making minimal, targeted fixes.
- Verifying lint, format, and test compliance.
Work style
1. Read the failure context in the task description carefully. 2. Identify the root cause from the error output and affected files. 3. Make the smallest change that fixes the failure - no refactoring, no improvements. 4. Verify locally before committing.
Rules
- Fix ONLY what is broken. Do not touch unrelated files.
- If a test is failing, fix the code, not the test - unless the test is
wrong.
- If a lint rule is violated, fix the code to comply. Do not disable the
rule.
- If a type error is reported, add or correct type annotations. Do not
use `type: ignore` unless there is no other option.
- If a dependency is missing, add it to `pyproject.toml`.
- If you cannot determine the fix, report the failure details and mark
the task as failed. Do not guess.
Project conventions
- Python 3.12+, strict typing (Pyright strict). No `Any`, no untyped dicts.
- Ruff: `uv run ruff check src/`, `uv run ruff format src/`.
- Test runner: `uv run python scripts/run_tests.py -x` (NEVER
`uv run pytest tests/` directly).
Read more
name: ci-fixer description: CI failures - read error, minimal fix, verify. trigger_keywords: - ci - github-actions - failure - lint - type-error - fix
CI Fixer Skill
Your sole job: read a CI failure report, make the minimal targeted fix, verify locally, and commit.
Specialization
- Diagnosing CI failures from error output.
- Making minimal, targeted fixes.
- Verifying lint, format, and test compliance.
Work style
1. Read the failure context in the task description carefully. 2. Identify the root cause from the error output and affected files. 3. Make the smallest change that fixes the failure - no refactoring, no improvements. 4. Verify locally before committing.
Rules
- Fix ONLY what is broken. Do not touch unrelated files.
- If a test is failing, fix the code, not the test - unless the test is
wrong.
- If a lint rule is violated, fix the code to comply. Do not disable the
rule.
- If a type error is reported, add or correct type annotations. Do not
use `type: ignore` unless there is no other option.
- If a dependency is missing, add it to `pyproject.toml`.
- If you cannot determine the fix, report the failure details and mark
the task as failed. Do not guess.
Project conventions
- Python 3.12+, strict typing (Pyright strict). No `Any`, no untyped dicts.
- Ruff: `uv run ruff check src/`, `uv run ruff format src/`.
- Test runner: `uv run python scripts/run_tests.py -x` (NEVER
`uv run pytest tests/` directly).
Deterministic orchestrator for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). No model in the coordination loop, so parallel runs in per-task git worktrees replay byte-identically. Signed lineage plus an opt-in HMAC audit chain a reviewer checks offline, without rerunning it. Cluster mode, air-gap deploy. https://bernstein.run
Repo: sipyourdrink-ltd/bernstein
Other skills on bernstein.
- /bernstein-agents
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one.
Open skill - /bernstein-alerts
Show active alerts from Bernstein - failed tasks, stalled agents, budget warnings, blocked tasks needing human intervention. Use when the user asks about problems, errors, warnings, or what needs attention.
Open skill - /bernstein-approve
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.
Open skill - /bernstein-cost
Show detailed cost breakdown and budget status for the Bernstein orchestrator. Use when the user asks about spending, budget, cost per model, cost per agent, or wants a cost projection.
Open skill - /bernstein-create-task
Create a new task in the Bernstein orchestrator. Use when the user wants to add a task, delegate work to an agent, file a bug fix, or queue up work for the orchestrator to handle.
Open skill - /bernstein-plan
Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.
Open skill

