craft
/craft
Wyznacza standard pisania i bramkę jakości dla tekstów instrukcji dla agentów: treść SKILL.md, opisy we frontmatter, definicje agentów, prompty subagentów, opisy narzędzi i szablony przepływów.
- Autor
- nicsuzor ↗
- Repozytorium
- academicops ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 2
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Wyznacza standard pisania i bramkę jakości dla tekstów instrukcji dla agentów: treść SKILL.md, opisy we frontmatter, definicje agentów, prompty subagentów, opisy narzędzi i szablony przepływów.
Oryginalny opis (EN)
Authoring standard and quality gate for agent-facing instruction text and workflow templates. Use when writing, reviewing, or revising SKILL.md bodies, frontmatter descriptions, agent definitions, subagent prompts, tool descriptions, or workflow templates. Exclude for human-facing prose (specs, reports).
Jak działa
- First Principles
- The Deletion Test
- The Description Is the Router
- The Body Is a Budget
- Voice
- Workflow Templates
- Quality Gates
- Agent Definitions
- Schemas and Construction
Podgląd SKILL.md
---
name: craft
description: Authoring standard and quality gate for agent-facing instruction text and workflow templates. Use when writing, reviewing, or revising SKILL.md bodies, frontmatter descriptions, agent definitions, subagent prompts, tool descriptions, or workflow templates. Exclude for human-facing prose (specs, reports).
allowed-tools: Read, Write, Edit
---
# Instruction Craftsmanship
Author and review agent-facing instructions and workflow templates for operational clarity, contract separation, and token efficiency. Consult `references/evidence.md` for empirical findings.
## First Principles
1. **Trust the harness, not today's quirks**: Write for durable capabilities. Avoid hard-coding workarounds for transient model behaviors.
2. **Specify process, not keystrokes**: State when to invoke a capability and what outcome proves it worked. Omit basic sub-steps or flags the agent already knows.
3. **One component, one job**: Keep instructions and templates focused on their singular purpose. Dispatch to peer skills rather than summarizing their internals. Leave another agent's domain to that agent: name the hand-off, never how it does its work.
4. **State the contract, not the neighbour**: Specify what a component needs as input and delivers as output. Never couple to specific neighbour names or slugs; composing agents decide what fills each slot.
5. **Write for a headless worker**: Assume unattended, asynchronous execution with no interactive human in the loop. A step never pauses or waits for human input; explicit approval boundaries terminate the task and wire dependent tasks as blocked.
6. **Promise only what the executor delivers**: Output contracts list only artifacts and state the executing agent itself produces. Another party's subsequent act (human sign-off, reviewer verdict) is never an executor deliverable.
7. **Verification must be real**: Demand direct inspection of live artifacts (outputs, logs, diffs) rather than relying on compliance checklists.
8. **Every line earns its place**: Relocate historical narratives, incident stories, and philosophical justifications to change records.
## The Deletion Test
Delete or relocate any line whose removal leaves the median task unaffected. Confine rare paths to progressive reference files.
## The Description Is the Router
Frontmatter descriptions are the primary routing surface (<1024 chars):
- **Front-load intent**: State the exact trigger conditions in the opening clause.
- **Define exclusions**: Explicitly state when not to invoke to prevent crossover.
- **Consolidate routing**: Place all triggering logic in the description field.
## The Body Is a Budget
Hold operational content strictly under 200 lines (target 30-80 lines):
- **Segment clearly**: Place critical constraints first or last; use markdown headers for navigation anchors.
- **Progressive disclosure**: Place dense reference materials or schemas one level deep in `references/`.
- **Provide shape, not logic**: Provide structural skeletons rather than full worked logic examples that induce overfitting.
## Voice
- Use positive imperatives paired with functional reasoning ("Use X because Y").
- Pair prohibitions with mandatory alternatives and legitimate escape hatches.
- Rely on document structure rather than capitalized absolutes ("ALWAYS", "NEVER").
## Workflow Templates
Workflow templates (`type: template`) govern repeatable multi-stage execution and task composition (<100 lines target).
- **Schema**:
```yaml
---
title: <human name>
type: template
description: <one line: what class of work this covers, so a composer can select it>
tags: [...]
---
```
- **Contract over neighbour**: Define input and output contracts per stage. Never name another template slug in frontmatter or body. A composite lists stages as contract expectations in order ("an independent review verdict on the spec"), never as slugs.
- **Headless execution & approval boundaries**: A step never pauses, waits, or prompts a human mid-task. Where approval is required, the step ends there: the worker files the complete artifact on the record and structures the boundary so downstream work remains strictly blocked until approval is recorded (e.g. releasing as `partial` with an explicit decision task or dependency-wired review task). Cut the composition chain at that boundary; work following the decision belongs in a separate dependent task.
- **Promise only executor deliverables**: Output contracts specify only artifacts and state generated by the executing agent. Future external decisions or approvals are not executor deliverables.
- **`wf-` prefix**: Templates stating an obligation that blocks acceptance rather than a process that proceeds conventionally carry a `wf-` prefix.
## Quality Gates
Every agent instruction, skill, persona definition, and subagent prompt must pass these four gates before merging:
1. **Categorical generality (Categorical Imperative)**: Express rules in general terms covering the full class of situations. Prohibit hyper-specific quotas, rigid interaction numbers, or one-off compromises.
2. **Entity abstraction (Name the process, not the actor)**: Refer to the principal as "the user", never by a personal proper noun or name ("Nic"). Refer to collaborators by role or capability.
3. **No PKB leakage (Data Boundaries)**: Never include private PKB note or task IDs (`aops_...`, `task_...`, `mem_...`, `kb_...`) or Obsidian wikilinks (`[[...]]`) in distributed framework instruction files. Use standard relative markdown links for file references.
4. **Zero historical provenance**: Strictly eliminate incident stories, post-mortem recaps ("after an incident on..."), or PR/commit changelog citations. Instructions define what is true now, never how it came to be true.
## Agent Definitions
Limit agent definition bodies to:
1. **Identity/role**: 1-3 sentences defining the persona.
2. **Behavioral rules**: Terse operational constraints.
3. **Output schema**: Expected report structure and verdict states.
4. **Routing table**: Clean table without per-route narrative.
Name a skill the agent uses; leave its modes, arguments, and when each applies to the skill. A change to a skill's modes or arguments owes the agent definitions that use it no edit.
## Schemas and Construction
- Define strict schemas with `required` fields and `additionalProperties: false`.
- **Static prefix, variable tail**: Emit invariant template text first and append variable content at the end to maximize prompt caching.
Pliki w paczce (2)
- SKILL.md 6 KB
- references/evidence.md 2 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · nicsuzor/academicops | 100 | MIT |
| nicsuzor/academicops | 100 | MIT |
| shubhamgoel27/artifold | 100 | MIT |
| didiansyah/skills | 100 | MIT |
| cameronspears/claude-skills | 100 | MIT |
| brolag/neural-claude-code | 100 | MIT |
| alexiolan/craft-skills | 100 | GPL-3.0 |
| educlopez/ui-craft | 90 | MIT |
| LeoYeAI/openclaw-master-skills | 90 | MIT |
Identyczna treść występuje jeszcze w 5 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.
Migawka bazy z 13.11.2026 · wersja paczki 36d31ec6a1ec (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 90plugin-authoring
Podpowiada dobre praktyki pisania skilli i agentów: opisy, strukturę, frontmatter, oszczędność tokenów i typowe błędy przy tworzeniu SKILL.md. - 100agent-dev
Pomaga tworzyć i dopracowywać definicje subagentów Claude Code: frontmatter YAML, prompty systemowe, dostęp do narzędzi i opisy z przykładami według dobrych praktyk Anthropic. - 100agent-prompt-instruction-refinement
Dostraja prompty systemowe, instrukcje person i opisy narzędzi agentów na podstawie tarć z wykonania zadań. - 91skill_doctor
Sprawdza skille w trybie tylko do odczytu: frontmatter SKILL.md, opisy, rejestrację, testy i jakość instrukcji, bez zmian w plikach. - 100writing-agent-instructions
Opisuje, jak pisać dobre instrukcje dla agentów w aplikacjach agent-native: AGENTS.md, skille i opisy narzędzi, oraz co trafia gdzie. - 90writing-for-agents
Pisze dokumenty dla agentów: skille, definicje agentów, reguły, pliki instrukcji projektu i polecenia dla innych agentów.