Skip to content
Back to search

deepseek-stack

Agent skills that make DeepSeek models plan, verify and ship like frontier models. npx skills add aicodeking/deepseek-stack

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/aicodeking--deepseek-stack/badge.svg)](/listings/aicodeking--deepseek-stack)

HTML

<a href="/listings/aicodeking--deepseek-stack"><img src="/api/listings/aicodeking--deepseek-stack/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npx skills add aicodeking/deepseek-stack

Add `-g` to install for every project. To install one skill only:

npx skills add aicodeking/deepseek-stack --skill ds-verify-loop

Manual install: copy `skills/*` into `~/.claude/skills/`, `~/.codex/skills/` or your harness's skills folder.

Not sure where to start? Run `/ds-help`.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 94 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # deepseek-stack
  2. Skills that make DeepSeek models (V4.1 Flash, V4 Pro) work like a much more expensive model. Cheap models usually fail in the same few ways: they skip the plan, claim a fix works without running it, retry a broken idea over and over, and drift on long runs. Each skill here closes one of those gaps with a short loop, a hard stop condition and a demand for real evidence.
  3. It works in any harness that reads `SKILL.md` files: Claude Code, Codex, Cline, OpenCode, PandaCode and others.
  4. ## Install
  5. ```bash
  6. npx skills add aicodeking/deepseek-stack
  7. ```
  8. Add `-g` to install for every project. To install one skill only:
  9. ```bash
  10. npx skills add aicodeking/deepseek-stack --skill ds-verify-loop
  11. ```
  12. Manual install: copy `skills/*` into `~/.claude/skills/`, `~/.codex/skills/` or your harness's skills folder.
  13. Not sure where to start? Run `/ds-help`.
  14. ## Skills
  15. ### Core
  16. | Skill | What it does |
  17. |---|---|
  18. | `ds-mode` | Always-on working style: restate, read first, small verified steps, evidence before "done". |
  19. | `ds-principles` | 21 engineering rules of thumb, each with a trigger. |
  20. | `ds-help` | Picks the right skill for a task. |
  21. ### Loops
  22. | Skill | What it does |
  23. |---|---|
  24. | `ds-plan-loop` | Plan with a check per step, critique once in a fresh pass, then build one step at a time. |
  25. | `ds-verify-loop` | Edit, run the real check, read the real error, fix the root cause. Max 5 rounds. |
  26. | `ds-unstick` | Same failure twice: name the shared assumption, test it, pick a different approach. |
  27. | `ds-context-reset` | Keep a `PROGRESS.md` and continue in a fresh context when the run gets long. |
  28. | `ds-ledger` | One row per decision for long or unattended runs, re-read before each step. |
  29. | `ds-review-loop` | Author plus fresh-context reviewer until both agree. Max 4 rounds. |
  30. | `ds-jury` | Reviews from two or three different models until they agree. |
  31. | `ds-best-of-n` | N parallel attempts, pick the best, graft in the strong parts of the rest. |
  32. | `ds-swarm` | Fan out parallel workers and merge their results into one report. |
  33. ### Build
  34. | Skill | What it does |
  35. |---|---|
  36. | `ds-sharpen` | Restate the goal, make the task deeper, rewrite the prompt. |
  37. | `ds-blueprint` | Types, signatures and module layout first, then implement. |
  38. | `ds-tdd` | A failing test first, then the smallest fix. |
  39. | `ds-blast-radius` | Find what a change could break outside its diff and prove it is safe. |
  40. | `ds-design` | Build a frontend with a clear visual direction, not the generic AI look. |
  41. | `ds-design-audit` | Score an existing UI with evidence, fix the top problems, re-check. |
  42. ### Ship
  43. | Skill | What it does |
  44. |---|---|
  45. | `ds-pr` | File a short PR that leads with the problem. |
  46. | `ds-watch-pr` | Watch CI and review bots, fix real findings. |
  47. | `ds-ship` | From change to merged PR, unattended. |
  48. | `ds-ready` | Same as `ds-ship`, but stops before the merge. |
  49. | `ds-adopt` | Finish someone else's PR or branch and keep their credit. |
  50. | `ds-revive` | Rebase an old PR, or decide it should be closed. |
  51. | `ds-pr-comments` | Format comments an agent posts for you. |
  52. ### Understand
  53. | Skill | What it does |
  54. |---|---|
  55. | `ds-explain` | How code works and why it is built that way, in plain words. |
  56. | `ds-catchup` | What changed while you were away, and what is waiting on you. |
  57. | `ds-lessons` | Turn repeated agent mistakes into types, lints or tests. |
  58. | `ds-unslop` | Remove AI tells from prose and comments. |
  59. ## Tips for DeepSeek
  60. - Use thinking mode at max effort for planning and review. It matters more than any skill.
  61. - Run big jobs at off-peak hours, when the API price is lower.
  62. - DeepSeek is cheap, so spend tokens on quality: `ds-best-of-n`, `ds-review-loop` and `ds-jury` cost little and catch a lot.
  63. - Pair a stronger planner with DeepSeek as the implementer if your harness supports separate plan and act models.
  64. ## Requirements
  65. - `gh` (GitHub CLI), signed in, for the Ship skills.
  66. - `python3` for `ds-watch-pr/scripts/watch_pr.py`.
  67. - Subagents or a second model for `ds-jury`, `ds-best-of-n` and `ds-swarm`. Without them, the skills run attempts one after another in fresh contexts.
  68. ## License
  69. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.