- name
SKILL.md
स्किल फ़ाइल पब्लिशर की रिपॉज़िटरी में ही रहती है।
कॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add ericrisco/rsc-harness --skill author-skill -a cursor -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add ericrisco/rsc-harness --skill author-skill -a claude-code -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add ericrisco/rsc-harness --skill author-skill -a codex -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add ericrisco/rsc-harness --skill author-skill -a grok -yकॉपी किया गया संदेश Grok Bot चैट में भेजें। Bot यह SKILL.md GitHub से लाता है और उसे उन स्किल में जोड़ देता है जो आपके सभी Bot साझा करते हैं।
Install this skill: https://github.com/ericrisco/rsc-harness/tree/HEAD/skills/author-skillपब्लिशर से
This is the meta skill: it authors and edits the other skills in the rsc catalog. A skill is two things bolted together — a description that fires at the right moment, and a body that makes the agent better once it fires. Most skills fail on the first. Treat them as two separate engineering problems with two separate quality bars.
Where the SDD chain (specify → plan → … → ship) builds product, author-skill builds the tools that build product. Use it whenever a skill is born or edited.
Not this skill — delegate: a product feature specced or planned → ../specify/SKILL.md, ../plan/SKILL.md. An autonomous agent or tool-calling loop → ../building-agents/SKILL.md. Generic project docs or a wiki article → the ../harness/SKILL.md 02-DOCS engine. Bootstrapping a workspace or profiling the user → ../init/SKILL.md.
Read 02-DOCS/wiki/harness/user-profile.md and speak in the register its technical_level records (technical terms, or plain words with analogies); ../init/SKILL.md sets it, and orient owns the voice. With no profile, use analogies and ask once "technical or with analogies?" — skill authoring is itself a technical act, so a non-technical author needs each convention explained, not just named.
skills/<id>/
├── SKILL.md the body: frontmatter (name + description + origin) then the prose
├── references/ progressive-disclosure detail, loaded only when the body points to it
│ └── <topic>.md
├── evals/
│ ├── cases.yaml trigger + capability test cases
│ └── README.md how to run the evals, honestly
└── scripts/ optional; verify.sh + helpers for skills with a checkable artifact
└── verify.sh
The frontmatter decides if the skill loads. The body decides how good the agent is once it does.
The description sits in context on every turn the skill is installed, invoked or not. The body is only paid for when the skill fires; the description is paid for always. So length here is a cost, never a credit. A vague description is a skill that never fires; an over-broad one hijacks unrelated turns. Get this right before anything else.
Rules, all enforced:
Use when … clause naming the situation, then only the capabilities that separate this skill from its neighbours. Do not append a Triggers: '…', '…' phrase list: the model matches on meaning, so a keyword bank in three languages buys nothing and is charged on every turn. The test is discrimination, not coverage — could a reader pick this skill over its nearest sibling from this line alone?NOT <x> (that is <sibling>) clause, naming a sibling that actually exists under skills/. Negative space prevents hijacking as much as positive matching causes firing.origin: risco on its own line. This marks it as ours.# Good — situation, the few capabilities that discriminate, a real boundary
description: "Use when X happens or the user shows symptom Y — doing A, fixing B, choosing C. NOT Z (that is `sibling`)."
# Bad — first person, no situation, no boundary; competes with every sibling on every turn
description: "I help you write great skills and make them work."
The full recipe, the budget tactics, and a worked before/after → references/description-recipe.md.
The body is loaded in full whenever the skill fires, so every line competes for the agent's attention. Write the smallest body that still routes correctly: 400 lines is a ceiling, not a target, and there is no floor — a skill that does its job in 60 lines beats the same skill padded to 200. Push anything long, reference-like, or rarely-needed into references/<topic>.md and link it inline at the point of use ("full table → references/foo.md").
Decide where a paragraph lives:
Every file under references/ must be linked from the body. An unlinked reference is never loaded, so it is dead weight in the package — link it or delete it.
references/ to look complete; a single-file skill is fine.cases.yaml + README.md. A skill with no evals is unverifiable and does not ship.verify.sh; their evals carry a capability scenario instead.Every new skill MUST end with the orientation footer so the harness never leaves the user in seco. Append verbatim:
## Orientación (siempre)
Habla con la voz de `orient`: frases cortas, una idea por frase, y cada respuesta se entiende sola. Registro técnico o con analogías según `technical_level` en `02-DOCS/wiki/harness/user-profile.md`. Cierra cada turno con el **bloque-brújula** (📍 dónde estás · ➡️ siguiente, terminando en pregunta; ✅ y 🧭 cuando hay algo hecho o decidido). **Nunca termines en seco.** Protocolo completo: skill `orient` → `skills/orient/references/orientation-contract.md`. (Defiere a `suggest` el "¿instalo la skill que falta?".)
The full protocol lives once in the orient skill; the footer only references it.
Run in order. Each step gates the next.
<id> that is the job, not the domain. If you can not say the job in one sentence, the scope is wrong — split it. Check no sibling already owns this; if one half-owns it, decide edit the sibling vs new skill before writing.references/description-recipe.md.cases.yaml then README.md. → references/eval-authoring.md.tags, recommends, npm run manifest, and indexing any artifact in 02-DOCS/wiki/index.md — the Knowledge map; root CLAUDE.md keeps only a short pointer). → references/rsc-conventions.md.Match the catalog, do not invent a new register:
*-reviewer-prompt.md files, no verbatim flowcharts. The rsc identity is its own.../<sibling>/SKILL.md, only ones that actually exist.Before you write an instruction, name the failure it's meant to prevent — then pick the form that actually fixes that failure. The instinct is to write a prohibition ("don't do X") for everything. That instinct is wrong for most failures, and measurably counter-productive for one class: a prohibition aimed at output shape tends to summon the very thing it forbids (the model attends to the named token), and can do worse than saying nothing at all. Match deliberately:
So: an anti-patterns table earns its place when it names concrete failure modes the flow above does not already state. A table that re-lists rules from the body is pure cost — delete it and move each rule to its step. And when you catch yourself writing "don't make it X" about the shape of an output, rewrite it as the shape to hit.
A skill ships only when every box is checked or a miss is consciously justified.
name matches the directory <id>; origin: risco present.Use when… lead, an explicit NOT … (that is sibling) boundary naming a real sibling, ≤ 350 chars target / ≤ 1024 hard limit — judged on discrimination against the nearest sibling, not coverage.references/.references/ file linked inline from the body; none orphaned.technical_level from the profile and picks the register; short sentences, every answer understandable on its own.02-DOCS/wiki/ and indexed in 02-DOCS/wiki/index.md (the Knowledge map; root CLAUDE.md keeps only a short pointer), if the skill produces any.cases.yaml (≥5 should_trigger incl. non-obvious, ≥4 should_not_trigger each with a real-sibling route_to, ≥1 capability with a must_include rubric) + an honest README.md. scripts/eval-lint.sh passes — but it only checks presence and the counts (≥5/≥4/≥1) and that those keys are lists; the -points-at-a-real-sibling, non-obvious phrasings, and quality are yours to verify here, not the linter's.Full rubric rationale and the rsc plumbing steps → references/rsc-conventions.md.
The rubric above scores the skill as a document. That is one of two gates — a skill ships only when both are green:
Static — the rubric above / scripts/skill-rubric.md, weighted score ≥ 8.5.
Behavioral — scripts/skill-behavior-rubric.md: run the skill on its capability
scenarios with and without it loaded, blind-grade both outputs, require absolute ≥ 8.5
and lift ≥ +1.0. Run it:
# 1) execute + grade — invoke the Workflow tool:
# scriptPath: scripts/skill-behavior-eval.workflow.js args: "<skill-id>"
# save the returned object to /tmp/<skill>-raw.json
# 2) score + gate (exit 0 pass / 1 fail):
node scripts/skill-behavior-eval.js --score /tmp/<skill>-raw.json
A failing lift means the body adds nothing a bare agent didn't already do — fix the body,
don't game the checklist.
When authoring produces a durable design note (a skill's scope decision, a description rationale worth keeping), persist it under 02-DOCS/wiki/sdd/ and index it in 02-DOCS/wiki/index.md (the Knowledge map; root CLAUDE.md keeps only a short pointer), per the ../harness/SKILL.md convention — never a stray file at the repo root. The skill's own evals/ is the executable record of intent; the wiki note is the human-readable why.
Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its eval
---name: author-skilldescription: Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description…---# skills/author-skill/SKILL.mdओवरव्यू
Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its evals, auditing it against the rubric. NOT building a product feature (that is `specify`) and NOT designing an agent loop (that is `building-agents`).
FAQ
पब्लिशर से skills/author-skill/SKILL.md डाउनलोड करें, या पाथ कॉपी करके रिपॉज़िटरी खोलें। PlugMCP स्किल को सूचीबद्ध करता है, फ़ाइल होस्ट नहीं करता।
पब्लिशर इसे https://github.com/ericrisco/rsc-harness पर रखता है।
Claude, Cursor, Codex और Grok Build वह SKILL.md पढ़ सकते हैं जिसे आप पब्लिशर की रिपॉज़िटरी से जोड़ते हैं। जब आप चैट में स्किल के GitHub फ़ोल्डर का लिंक भेजते हैं, तो Grok Bot उसे इंस्टॉल कर देता है।
route_tomust_includemust_include item discriminates — answerable by the scenario's task, plausibly caused by the skill and plausibly missed without it. An item both arms fail measures nothing and lowers the absolute; it has turned a real PASS into a FAIL here. → references/eval-authoring.md.../x/SKILL.md points to a skill that exists.tags + recommends set, npm run manifest re-run, and npm run validate / npm run manifest:check pass (manifest current, no dangling recommends).