Skip to content
Back to search

claude-skills

MarketplaceWorks with Claude CodeGitHub

Personal Claude Code skills as a plugin marketplace

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/dknathalage--claude-skills/badge.svg)](/listings/dknathalage--claude-skills)

HTML

<a href="/listings/dknathalage--claude-skills"><img src="/api/listings/dknathalage--claude-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

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

/plugin marketplace add dknathalage/claude-skills
/plugin install claude-skills@claude-skills

Update with `/plugin marketplace update claude-skills`. The small `marketplace.json` exists only because `/plugin` installs through a marketplace; it points at this repo root.

**`build` needs workflows enabled.** The desktop app has them on. For the CLI, set `"enableWorkflows": true` in your Claude Code settings.

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.

.claude-plugin/marketplace.json · Manifest · 13 lines
  1. {
  2. "name": "claude-skills",
  3. "owner": {
  4. "name": "dknathalage"
  5. },
  6. "plugins": [
  7. {
  8. "name": "claude-skills",
  9. "source": "./",
  10. "description": "Personal Claude Code skills bundle."
  11. }
  12. ]
  13. }
README.md · README · 73 lines
  1. # claude-skills
  2. Personal [Claude Code](https://claude.com/claude-code) skills in one plugin, `claude-skills`. It replaces [superpowers](https://github.com/obra/superpowers). The discipline is the same (spec → plan → build → review), but the build phase runs **parallel Haiku workers in a Claude workflow**, not one strong-model agent per task in sequence.
  3. ## Install
  4. ```
  5. /plugin marketplace add dknathalage/claude-skills
  6. /plugin install claude-skills@claude-skills
  7. ```
  8. Update with `/plugin marketplace update claude-skills`. The small `marketplace.json` exists only because `/plugin` installs through a marketplace; it points at this repo root.
  9. **`build` needs workflows enabled.** The desktop app has them on. For the CLI, set `"enableWorkflows": true` in your Claude Code settings.
  10. ## Skills
  11. | Skill | Use it when |
  12. |---|---|
  13. | `using-claude-skills` | Loaded at session start by a hook. Lists the skills and the rule to check them first. |
  14. | `spec` | A new feature or change isn't fully specified. A short conversation and 2–3 approaches lead to an approved design doc in `docs/specs/`. |
  15. | `plan` | An approved spec needs a task graph (`docs/plans/*.json`) where each task owns its files. |
  16. | `build` | A task graph is ready to run. It runs a Claude workflow: parallel Haiku workers, a Haiku check-and-fix loop per task, one integration step and a whole-branch review on the session model. Per-agent timeouts and a build deadline apply. |
  17. | `test-driven-development` | You are writing any feature or bugfix code. |
  18. | `systematic-debugging` | There is a bug, failing test or crash. Find the root cause before any fix. |
  19. | `verification-before-completion` | You are about to say done, fixed or passing. |
  20. | `code-review` | You are reviewing work outside a build, or acting on review feedback. |
  21. | `worktrees` | Work needs isolating in a git worktree. |
  22. | `finish-branch` | Tests pass and the branch needs merging, a PR, keeping or discarding. |
  23. | `writing-skills` | You are adding or changing a skill in this plugin. |
  24. All `SKILL.md` files together come to about 6,800 words, against about 22,000 for superpowers.
  25. ## How `build` works
  26. ```
  27. plan.json ──validate──▶ waves ──▶ Workflow
  28. ├─ T1: implement (Haiku) → check (Haiku) → up to 2 fix rounds
  29. ├─ T2: implement (Haiku) → check (Haiku) each task starts as soon
  30. └─ T3 (needs T1): … as its dependencies pass
  31. ▼
  32. integrate (Haiku): merge swarm/<topic>/<id> into build/<topic>, run verify_all
  33. ▼
  34. review (session model): whole branch against the spec, one summary back
  35. ```
  36. Workers edit only the files their task owns. A task that keeps failing, or runs past its time limit, comes back `stuck` for the session to re-plan. It is never retried on a bigger model.
  37. ## Benchmarks
  38. Headless A/B runs against superpowers on .NET fixtures, scored by hidden tests and a blind judge. Details are in [`bench/results/`](bench/results/).
  39. Results on F-medium (8 tasks), median of 3 runs each:
  40. | Arm | Time | Cost | Hidden tests | Review |
  41. |---|---|---|---|---|
  42. | swarm | 401 s | $1.48 | 20/20 | 8 |
  43. | same tasks one at a time | 570 s | $1.50 | 20/20 | 8 |
  44. | superpowers | 695 s | $3.88 | 20/20 | 9 |
  45. Run one session with `bench/run.sh`, or the E1 set with `bench/e1.sh`. `npm test` runs the harness and workflow tests.
  46. ## Adding or changing a skill
  47. See the `writing-skills` skill. In short:
  48. 1. Edit `skills/<name>/SKILL.md`.
  49. 2. Bump `version` in `.claude-plugin/plugin.json`.
  50. 3. Run `claude plugin validate .`.
  51. 4. Commit, push, then run `/plugin marketplace update claude-skills`.
  52. ## License
  53. MIT. Several skills are rewritten from superpowers by Jesse Vincent, also MIT; see [NOTICE](NOTICE).

Ratings and comments

Sign in to rate this skill.

Sign in

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