Skip to content
Back to search

dev-skills

Agent skills for dev.to - write in your voice, audit what worked, feed the results into the next draft.

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/naheel0--dev-skills/badge.svg)](/listings/naheel0--dev-skills)

HTML

<a href="/listings/naheel0--dev-skills"><img src="/api/listings/naheel0--dev-skills/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.

git clone https://github.com/naheel0/dev-skills.git
cp -r dev-skills/dev-* ~/.config/opencode/skills/     # OpenCode
cp -r dev-skills/dev-* ~/.claude/skills/              # Claude Code
cp dev-skills/dev-learn.py ~/.config/opencode/skills/

If you install somewhere other than `~/.config/opencode/skills`, set the path so `dev-learn.py` knows where the skills live:

export DEVTO_SKILLS_DIR=~/.claude/skills

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 · 80 lines
  1. # dev-skills
  2. A set of agent skills for writing dev.to posts in your own voice, auditing what actually worked, and feeding those results into the next draft. Works with OpenCode, Claude Code, and other agents that load `SKILL.md` files.
  3. ![Why my AI writer waits 10 posts before learning — the dev-skills learning loop](docs/cover.jpeg)
  4. ## Why
  5. Generic writing advice is a prior. Your own posts are the evidence. These skills close the loop:
  6. ```
  7. dev-learn.py audit --apply <-- /dev-audit <-- analytics + ~/.claude/devto/log.md
  8. | promotes winning formulas/tags, demotes losers
  9. +----------------------> /dev-post's next draft
  10. ```
  11. ## Install
  12. ```bash
  13. git clone https://github.com/naheel0/dev-skills.git
  14. cp -r dev-skills/dev-* ~/.config/opencode/skills/ # OpenCode
  15. cp -r dev-skills/dev-* ~/.claude/skills/ # Claude Code
  16. cp dev-skills/dev-learn.py ~/.config/opencode/skills/
  17. ```
  18. If you install somewhere other than `~/.config/opencode/skills`, set the path so `dev-learn.py` knows where the skills live:
  19. ```bash
  20. export DEVTO_SKILLS_DIR=~/.claude/skills
  21. ```
  22. ## Skills
  23. | skill | what it does |
  24. |---|---|
  25. | `/dev-post` | Turn one raw idea into a full draft, three title options, and a copy-ready block. Never publishes without your "yes". |
  26. | `/dev-human` | Strip AI tells from a draft and score it against a human-sounding check. |
  27. | `/dev-comment` | Write a comment on someone else's post — three angles, one full comment. |
  28. | `/dev-audit` | Post-mortem on your published posts using analytics + `log.md`. Rank by engagement rate, not views. |
  29. | `/dev-learn` | Apply the audit's findings: promote winning formulas/tags, demote losers. |
  30. | `/dev-profile` | Score your dev.to profile out of 100 and rewrite the parts that lose points. |
  31. | `/dev-repurpose` | Turn a long asset (video, newsletter, transcript) into a dev.to article with a canonical URL. |
  32. ## First-time setup
  33. Create `~/.claude/devto/`:
  34. ```bash
  35. mkdir -p ~/.claude/devto
  36. ```
  37. **`voice.md`** — your voice profile. `/dev-post` will ask for three of your own past posts and write this file if it does not exist. Do not skip it; a draft in the wrong voice is worse than no draft.
  38. **`log.md`** — your post history. This is the data `/dev-audit` and `dev-learn.py` read. Start it with this header and append one row per post:
  39. ```markdown
  40. # dev.to post log
  41. | date | title | formula_id | tags | cover | canonical | series | published | engagement_rate | comment_ratio | reach_multiple | human_score | audit_rank | first line |
  42. |------|-------|------------|------|-------|-----------|--------|-----------|-----------------|---------------|----------------|-------------|------------|------------|
  43. ```
  44. `/dev-post` appends the date, title, formula, tags, and metadata. `/dev-audit` fills in the engagement metrics later. `dev-learn.py` will not change any weights until at least 10 posts are audited.
  45. ## The learning loop
  46. After a post has collected data:
  47. ```bash
  48. /dev-audit # find what worked
  49. python3 ~/.config/opencode/skills/dev-learn.py audit # dry-run: show proposed changes
  50. python3 ~/.config/opencode/skills/dev-learn.py audit --apply
  51. /dev-post # next draft uses the new weights
  52. ```
  53. `dev-learn.py` never deletes a formula or tag — it drops the weight to 0 and moves it to `archive`. Slop words in `dev-human/slop.json` are left alone; they are voice-specific and need your review.
  54. ## License
  55. MIT. See [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

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