Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lingtai-ai/dev-guide-skill-stewardship
Nested lingtai-dev-guide reference for turning one-off experience into durable skills: when to write a skill vs leave it as notes, the router-vs-nested- reference pattern, distilling experience (归一) and session journals into triggered/executable SKILL.md files, de-privatizing and parameterizing local paths and human-specific details, a lightweight pre-publish benchmark/checklist, grooming shared-library candidates, and PR-ready skill cleanup.
Passed 22 of 22 test cases with the skill, and 11 of 22 without it.
and 13 more in the full report
11 fixed12 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
An author submitted a draft with frontmatter identifier `name: Advanced_Skill_V1!`. What structural error exists in this name field?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies that the name field must contain only letters, numbers, and hyphens. | Missed | Passed |
The instructions your model reads when the skill loads.
Nested lingtai-dev-guide reference. Read this after the top-level router sends you here when deciding whether to write a skill, distilling experience into one, or cleaning a skill up so it can ship in a PR.
This consolidates the skill-distillation meta-method (归一), skill audit/triage,
the experience-to-skill side of session-journal handoff, the skill-benchmark
checklist, and shared-library grooming. It governs LingTai's skill hygiene; for
generic authoring mechanics (frontmatter spec, trigger syntax, file layout)
cross-link to skills-manual rather than duplicating it here.
A skill turns a repeated experience into something triggered, executable, verifiable, and maintainable. Write one when the technique would otherwise be re-derived ad hoc across sessions or agents — and only after it is de-privatized and lightly benchmarked. Skills shipping in this repo's preset tree must be parameterized: no private paths, no human-specific details, no secrets.
Write one when the technique was not intuitively obvious and you would reference it again; when multiple agents/sessions keep re-implementing the same workflow with divergent quality (convergent discovery is the strongest signal); or when the pattern is broadly reusable rather than a one-off.
Do not write a skill for one-off solutions or single-incident narratives; for
standard practices already documented elsewhere (link instead); for
project-specific conventions (those belong in CLAUDE.md/repo docs); or for
mechanical constraints a test/regex could enforce (automate, don't document).
If it is real but not yet skill-worthy, leave it as a session-journal entry or a shared-library candidate (§5) until the pattern repeats.
LingTai utility skills use progressive disclosure: a short router SKILL.md at
the root plus focused nested references under reference/<topic>/SKILL.md.
test cases passed, vs 11 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.