v4-best-practices
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
- License 许可
- MIT
- 最近更新
- 2026-11-01
- Stars
- ★ 8
- Forks
- 0
01 前言 Front Matter
- name
- v4-best-practices
- description
- Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
03 SKILL.md 正文
V4 Best Practices
Rules for multi-step V4 thinking-mode workflows. Each rule prevents a specific, observable failure class.
1. Verify references before writing
Before referencing a file path, function, or type in code or plan output,
call grep_files or read_file to confirm it exists in the workspace.
# Bad: edit_file path="src/config/loader.rs" (assumed from memory)
# Good: grep_files pattern="pub fn load_config" → confirms src/config/mod.rs:42
# then reference src/config/mod.rs:42
Failure avoided: edit_file errors on non-existent paths; LSP diagnostics
on hallucinated symbols.
2. Spawn a verifier sub-agent before multi-file execution
Before executing a plan that touches 3+ files, spawn a deepseek-v4-flash
sub-agent (thinking off) to read the target files and confirm path/symbol
assumptions still hold.
agent type="verifier" model="deepseek-v4-flash"
prompt: "Read these files and confirm: [list assumptions]. Report mismatches."
Failure avoided: multi-step edits fail partway because file structure changed since the plan was drafted.
3. Plan output must use confirmed path:line references
In plan-mode output, replace vague location pointers with path:line
references drawn from a prior grep_files result.
# Bad: "Update the retry logic in the client module"
# Good: "Update retry loop at crates/tui/src/client.rs:187"
Failure avoided: agent-mode execution cannot locate the intended edit target when plan directions are imprecise.
04 同仓库更多 Skills
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
gh-find-prs
Survey open GhostyCode PRs and triage each for mergeability and disposition against the real landing branch.
gh-file-issue
Use when filing a new GhostyCode GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.
gh-compile-issues
Triage N GitHub issues into a coverage matrix: fetch each, check current code, classify already-done/quick-fix/design/defer with cited evidence.
gh-close-issues
Close resolved GhostyCode issues only after verifying the landed commit/behavior, with a positive crediting comment; never from title alone.