Claude skills for Writing Skills, tested
Skills for writing skills work, measured on skill authoring tasks. Each was the same task, run twice, once with the skill loaded and once without it, and what is below is what changed. Ranked by how many models the rule found a clear effect on, never by the size of one.
Measured on 3 models (Claude, GPT & Gemini): Claude Haiku 4.5, GPT-5 mini, Gemini 3.1 Flash Lite.
The model is given a short brief and asked to write a complete SKILL.md. The score is the share of the open Agent Skills specification's requirements the result meets, counting only the 14 defined requirements that apply to the document written; requirements for optional fields the document does not use are not counted. A second reading against this site's own house style is shown on each skill's page but is not ranked, because one of the skills tested is ours.
What helped, and on how many models
Tied for first · shared with 4 others, and the tie is broken by nothing
skills/skill-creation-walkthrough rampstackco/claude-skills*
Skill authoring
Helped clearly on Gemini 3.1 Flash Lite and GPT-5 mini. Measured against the same task with a one-line instruction.
Found 100% of the specification requirements, against 76% with no skill loaded. Against 68% with a one-line instruction instead.
Via API
- Gemini 3.1 Flash Lite · helped
- GPT-5 mini · helped
In Claude Code
- Claude Fable 5, First run, single attempt · unclear
- Claude Opus 5, First run, single attempt · not measured
- Claude Fable 5, Second run, every task twice · unclear
- Claude Haiku 4.5, Second run, every task twice · helped
- Claude Opus 5, Second run, every task twice · not measured
- Claude Sonnet 5, Second run, every task twice · unclear
- Claude Fable 5.1, Fable 5.1, single attempt · not measured
- Claude Fable 5.1, Wider run, three ways · unclear
- Claude Haiku 4.5, Wider run, three ways · helped
- Claude Opus 5, Wider run, three ways · not measured
- Claude Sonnet 5, Wider run, three ways · unclear
Cost per task, with the skill loaded: about $0.00415. Adds about 8,200 tokens of context to every request.
Tied for first · shared with 4 others, and the tie is broken by nothing
skills/skill-creator anthropics/skills
Skill authoring
Helped clearly on Gemini 3.1 Flash Lite and GPT-5 mini. Measured against the same task with a one-line instruction.
Found 100% of the specification requirements, against 82% with no skill loaded. Against 70% with a one-line instruction instead.
Via API
- Gemini 3.1 Flash Lite · helped
- GPT-5 mini · helped
In Claude Code
- Claude Fable 5, First run, single attempt · not measured
- Claude Opus 5, First run, single attempt · not measured
- Claude Fable 5, Second run, every task twice · not measured
- Claude Haiku 4.5, Second run, every task twice · helped
- Claude Opus 5, Second run, every task twice · unclear
- Claude Sonnet 5, Second run, every task twice · unclear
- Claude Fable 5.1, Fable 5.1, single attempt · worse
- Claude Fable 5.1, Wider run, three ways · worse
- Claude Haiku 4.5, Wider run, three ways · helped
- Claude Opus 5, Wider run, three ways · not measured
- Claude Sonnet 5, Wider run, three ways · not measured
Cost per task, with the skill loaded: about $0.0199. Adds about 10,900 tokens of context to every request.
Tied for first · shared with 4 others, and the tie is broken by nothing
skills/skill-creation-walkthrough rampstackco/claude-skills*
Skill authoring
Helped clearly on Claude Haiku 4.5 and GPT-5 mini; helped a little on Gemini 3.1 Flash Lite, under our bar. Measured against no skill loaded.
Found 100% of the specification requirements, against 74% with no skill loaded. Instruction arm: not measured.
Via API
- Claude Haiku 4.5 · helped
- Gemini 3.1 Flash Lite · unclear
- GPT-5 mini · helped
In Claude Code
- Claude Fable 5, First run, single attempt · unclear
- Claude Opus 5, First run, single attempt · not measured
- Claude Fable 5, Second run, every task twice · unclear
- Claude Haiku 4.5, Second run, every task twice · helped
- Claude Opus 5, Second run, every task twice · not measured
- Claude Sonnet 5, Second run, every task twice · unclear
- Claude Fable 5.1, Fable 5.1, single attempt · not measured
- Claude Fable 5.1, Wider run, three ways · unclear
- Claude Haiku 4.5, Wider run, three ways · helped
- Claude Opus 5, Wider run, three ways · not measured
- Claude Sonnet 5, Wider run, three ways · unclear
Cost per task, with the skill loaded: about $0.00826. Adds about 8,400 tokens of context to every request.
Tied for first · shared with 4 others, and the tie is broken by nothing
distribution/claude-plugin/skills/skill-builder yusufkaraaslan/Skill_Seekers
Skill authoring
Helped clearly on Gemini 3.1 Flash Lite and GPT-5 mini. Measured against the same task with a one-line instruction.
Found 99% of the specification requirements, against 70% with no skill loaded. Against 73% with a one-line instruction instead.
Via API
- Gemini 3.1 Flash Lite · helped
- GPT-5 mini · helped
In Claude Code
- Claude Fable 5.1, Wider run, three ways · not measured
- Claude Haiku 4.5, Wider run, three ways · helped
- Claude Opus 5, Wider run, three ways · not measured
- Claude Sonnet 5, Wider run, three ways · not measured
Cost per task, with the skill loaded: about $0.00288. Adds about 1,200 tokens of context to every request.
Tied for first · shared with 4 others, and the tie is broken by nothing
skills/skill-creator anthropics/skills
Skill authoring
Helped clearly on Claude Haiku 4.5 and GPT-5 mini; helped a little on Gemini 3.1 Flash Lite, under our bar. Measured against no skill loaded.
Found 100% of the specification requirements, against 74% with no skill loaded. Instruction arm: not measured.
Via API
- Claude Haiku 4.5 · helped
- Gemini 3.1 Flash Lite · unclear
- GPT-5 mini · helped
In Claude Code
- Claude Fable 5, First run, single attempt · not measured
- Claude Opus 5, First run, single attempt · not measured
- Claude Fable 5, Second run, every task twice · not measured
- Claude Haiku 4.5, Second run, every task twice · helped
- Claude Opus 5, Second run, every task twice · unclear
- Claude Sonnet 5, Second run, every task twice · unclear
- Claude Fable 5.1, Fable 5.1, single attempt · worse
- Claude Fable 5.1, Wider run, three ways · worse
- Claude Haiku 4.5, Wider run, three ways · helped
- Claude Opus 5, Wider run, three ways · not measured
- Claude Sonnet 5, Wider run, three ways · not measured
Cost per task, with the skill loaded: about $0.0116. Adds about 11,500 tokens of context to every request.
Second
skills/skill-creator openclaw/openclaw
Skill authoring
Helped on Gemini 3.1 Flash Lite; helped a little on GPT-5 mini, under our bar. Measured against the same task with a one-line instruction.
Found 99% of the specification requirements, against 75% with no skill loaded. Against 77% with a one-line instruction instead.
Via API
- Gemini 3.1 Flash Lite · helped
- GPT-5 mini · unclear
In Claude Code
- Claude Fable 5.1, Wider run, three ways · not measured
- Claude Haiku 4.5, Wider run, three ways · helped
- Claude Opus 5, Wider run, three ways · not measured
- Claude Sonnet 5, Wider run, three ways · not measured
Cost per task, with the skill loaded: about $0.00457. Adds about 600 tokens of context to every request.
The numbers
How to read these tables
How to read these tables
- Without -> with
- The score on the task set with no skill loaded, then with the skill loaded. For classes scored against an answer key, this is the share of seeded items found. For classes scored by blind comparison, it is how often a grader preferred the skill's output over the baseline's, with the baseline shown as the complement.
- Effect (range)
- With minus without, averaged over the models tested, with the lowest and highest per-model value in brackets. Per-model intervals are on each skill's page.
- Orbit
- Stable: delta at or above the pass threshold, and the interval excludes zero
- Past the horizon: delta at or below the failure floor, and the interval excludes zero
- In free drift: the interval spans zero, or the delta sits between the floor and the threshold
- Unobservable: the cell cannot be classified: sub-case (a) an unbounded scale, or sub-case (b) both arms at the same bound
A fifth value, Decaying, is defined and appears once a skill has been re-tested: a cell previously Stable that has fallen below the pass threshold on a later run.
- Cohort
- The repository that publishes the skill. Rows marked with an asterisk come from the repository the operator of this site maintains, so those are the operator measuring its own work. The rest were chosen by a stated rule and not by preference.
- Commit
- The exact version tested. Later commits are not covered by this verdict.
- Injected context tokens
- How much text the skill adds to the model's context. This is cost, not quality; a bigger number is not a better one. Measured from the input tokens the API reported on the with arm, averaged over that skill's records.
- Tested
- The date. Verdicts age as models change.
Skill authoring
| Skill | Cohort | Without -> with | Effect (range) | Orbit | Injected context tokens | Tested |
|---|---|---|---|---|---|---|
| No skill loaded Wider run, three ways | baseline | 76% | 0 by definition | 0 | 2026-09-05 | |
| One-line instruction instead Wider run, three ways | baseline | 72% | 0 by definition | 0 | 2026-09-05 | |
skills/skill-creation-walkthrough from rampstackco/claude-skills 047924252254 Wider run, three ways Best result in this test | rampstackco/claude-skills* | 76% -> 100% | +0.32 [+0.25, +0.38] | Stable | 8,190 | 2026-09-05 |
skills/skill-creator from anthropics/skills 3b3fad96af16 Wider run, three ways | anthropics/skills | 82% -> 100% | +0.30 [+0.25, +0.34] | Stable | 10,872 | 2026-09-05 |
distribution/claude-plugin/skills/skill-builder from yusufkaraaslan/Skill_Seekers f3972efa33fa Wider run, three ways | yusufkaraaslan/Skill_Seekers | 70% -> 99% | +0.26 [+0.25, +0.27] | Stable | 1,203 | 2026-09-05 |
skills/skill-creator from openclaw/openclaw 61b08f0ebb7a Wider run, three ways | openclaw/openclaw | 75% -> 99% | +0.22 [+0.19, +0.25] | Mixed, see page | 587 | 2026-09-05 |
| No skill loaded First run, with and without the skill | baseline | 74% | 0 by definition | 0 | 2026-08-30 | |
| One-line instruction instead First run, with and without the skill | baseline | instruction arm: not measured | 0 by definition | 0 | 2026-08-30 | |
skills/skill-creation-walkthrough from rampstackco/claude-skills 047924252254 First run, with and without the skill Best result in this test | rampstackco/claude-skills* | 74% -> 100% | +0.26 [+0.13, +0.38] | Stable on 2 of 3 | 8,390 | 2026-08-30 |
skills/skill-creator from anthropics/skills 3b3fad96af16 First run, with and without the skill | anthropics/skills | 74% -> 100% | +0.26 [+0.13, +0.38] | Stable on 2 of 3 | 11,514 | 2026-08-30 |
| Averaged over three models; per-model results on each skill's page. Ranked within this class only. | ||||||
Ranked within this topic by how many models the rule found a clear effect on, which is a count of verdicts and never the size of one. Two classes are two answer keys on two scales, so no effect here is compared with another. Every class, with its full table.