Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →truthandstories07-sudo/skill-forge
Create, evaluate, and improve agent skills (SKILL.md format) using an evidence-based methodology distilled from 244 top skills across the Anthropic, OpenAI, vendor, and community ecosystems.
Passed 15 of 20 test cases with the skill, and 5 of 20 without it.
and 12 more in the full report
13 fixed4 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
The instructions your model reads when the skill loads.
Create, judge, and improve skills. Every rule in this skill traces to evidence from a corpus study of 1400+ public skills, deep-analyzed in waves (anthropics/skills, obra/superpowers, openai/skills, Vercel/Cloudflare/Supabase/Expo/HF/Microsoft/Trail of Bits, Matt Pocock, Addy Osmani, baoyu, marketing/PM verticals, K-Dense). Rule IDs like U7/S8/R15 and the spike exemplars in references/exemplars.md trace to that study (methodology summarized in the project README). The skill works standalone; the evidence is provenance, not a runtime dependency.
A skill is not a document. It is three layers of machinery: a corrective patch for the model's bad defaults (not a restatement of domain knowledge), an optimal allocation of knowledge across context budget (progressive disclosure), and a falsifiable quality loop (tests that can fail). Drop any layer and you produce one of the twenty documented anti-patterns.
| User intent sounds like | Mode | Read next |
|---|---|---|
| "turn this into a skill", "create a skill for X", 做成技能 | A: Create | below + references/type-playbooks.md |
| "is this skill good?", "audit/score this skill", 评估这个skill | B: Judge | references/rubric.md |
| "improve/fix/refresh this skill", 优化这个skill | C: Improve | references/rubric.md then below |
| "the skill doesn't trigger / triggers too much" | D: Tune description | references/description-engineering.md |
Output language for user-facing reports: Chinese. Skill bodies you produce: English by default (instructions read by models), bilingual trigger terms in the description when the user works in Chinese; follow the user's explicit preference if stated.
Eight steps. Steps 1-2 are gates — they can kill the project, which is a success, not a failure. Do not skip gates to be agreeable; a skill that shouldn't exist costs context on every future session.
A skill must be built from real, observed expertise. Acceptable sources:
If none exists, say so and offer two honest paths: do the task once for real and harvest it, or produce a thin draft with explicit OPEN QUESTIONS the user must answer. Never fabricate procedures from general knowledge — the corpus shows this produces "vague, generic procedures" (the #1 supply-side failure; U9).
Ask: if this skill did not exist, would the model acting on its priors get it wrong?
Also apply per-section while drafting: "delete this paragraph — does model behavior change?" If not, cut it.
test cases passed, vs 5 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.