code-first-responder
- Repo stars 0
- Author updated Live
- Author repo nano-core
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @0-CYBERDYNE-SYSTEMS-0 · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: code-first-responder
description: "Guides the agent through a short, repeatable debug loop: capture Use when the user request matc…
category: ai
runtime: no special runtime
---
# code-first-responder output preview
## PART A: Task fit
- Use case: "Guides the agent through a short, repeatable debug loop: capture Use when the user request matches this skill's domain and capabilities. Refer to templates/fix_checklist.md and ensure every box is addressed: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “When to use this skill / When not to use this skill / When to load this skill” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “"Guides the agent through a short, repeatable debug loop: capture Use when the user request matches this skill's domain and capabilities. Refer to templates/fix_checklist.md and ensure every box is addressed: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “When to use this skill / When not to use this skill / When to load this skill” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Validate with a small run
Start with a small task and check whether the result follows “When to use this skill / When not to use this skill / When to load this skill”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: code-first-responder
description: "Guides the agent through a short, repeatable debug loop: capture Use when the user request matc…
category: ai
source: 0-CYBERDYNE-SYSTEMS-0/nano-core
---
# code-first-responder
## When to use
- "Guides the agent through a short, repeatable debug loop: capture Use when the user request matches this skill's domai…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “When to use this skill / When not to use this skill / When to load this skill” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "code-first-responder" {
input -> user goal + target files + boundaries + acceptance criteria
context -> When to use this skill / When not to use this skill / When to load this skill
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Code First Responder
When to use this skill
- Use when the user request matches this skill's domain and capabilities.
- Use when this workflow or toolchain is explicitly requested.
When not to use this skill
- Do not use when another skill is a better direct match for the task.
- Do not use when the request is outside this skill's scope.
When to load this skill
- Incoming task references failing tests, stack traces, or recent merges.
- User explicitly wants a "quick triage", "first look", or "rough fix plan".
- Another skill (e.g., Rapid Research) flagged new code issues that need confirmation.
Guardrails
- Never edit files before the failure is reproduced locally.
- Capture the exact command + exit code inside the debug report template.
- Prefer minimal diffs; defer major refactors to a follow-up task.
- If the failure cannot be reproduced quickly, escalate with the captured evidence and leave the repo untouched.
Five-step micro-playbook
- Snapshot context
- Record branch, latest commit hash, and dirty files.
- Paste the failure summary into
templates/debug_report_template.md.
- Reproduce fast
- Run the narrowest test or script possible.
- Store the exact CLI command and snippet of output.
- Isolate scope
- Identify the component or file set causing the issue.
- Outline suspected root causes without editing yet.
- Propose fix plan
- List concrete actions (edit file X, update test Y, run command Z).
- Mark each action as
must,optional, orblocked.
- Optional patch
- If the fix is obvious (<30 lines), apply it and run validation.
- Update the debug report with the diff summary and test status.
Output checklist
Refer to templates/fix_checklist.md and ensure every box is addressed:
- Failure reproduced?
- Minimal scope understood?
- Plan or patch documented?
- Validation command + result captured?
- Handover note written?
Response snippet to send back to the user
## Debug Status
- Branch/commit: ...
- Failure reproduced: yes/no (command)
- Root-cause hypothesis: ...
- Next actions: ...
## Attachments
- debug_report_template.md (updated)Companion tools
run_commandfor fast tests.read_file+search_codefor targeted inspection.write_filefor updating the templates and final report.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review