Agent skill
skill-editor
Use when asked to draft, revise, or review an agent skill specification so frontmatter alone routes correctly and the body is a compact, non-redundant, internally consistent execution guide.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/skill-editor
SKILL.md
Skill Editor
Draft, revise, or review an agent skill specification to improve routing precision and execution usability.
Response Contract
- Deliverable: return the revised skill specification.
- Chat output: no additional output beyond the deliverable.
Skill Model
Definitions used to reason about skill specifications and edits.
Semantic Layers
A skill specification has two semantic layers.
-
Frontmatter Routing description. It expresses when the skill should be selected.
-
Body Execution description. It expresses how to perform the task once selected.
Editing Standards
Apply these standards throughout the edit. Each standard is single-sourced here and referenced elsewhere by its ID.
-
layers.no_overlap — Separate routing and execution Keep routing description in frontmatter and execution description in the body. Do not duplicate the same guidance across layers.
-
routing.alone — Frontmatter routes alone Frontmatter must be sufficient for correct selection without reading the body. Use user-intent phrasing and common request language for the intended task family.
-
routing.boundary — Constrain routing Frontmatter must not claim general capabilities beyond the intended task family. Remove wording that would cause overreach or overlap with nearby skills.
-
body.responsibilities — Organize the body by responsibility Structure the body into responsibility-based sections so each rule has a stable home and boundaries are clear.
-
rules.single_source — Single-source rules and definitions Each rule and definition appears once. Merge overlaps, remove restatement, and avoid parallel formulations.
-
conflicts.priority — Make tradeoffs explicit Where constraints trade off, state an explicit priority rule that resolves the conflict.
-
examples.minimal — Examples only for disambiguation Use examples only to resolve ambiguity. Keep them minimal and neutral, and do not introduce conventions through examples.
Workflow
- Rewrite frontmatter so it routes correctly on its own. Apply
routing.alone,routing.boundary. - Restructure the body into responsibility-based sections and relocate content into its responsible home. Apply
body.responsibilities. - Remove layer overlap by moving routing language out of the body and moving execution guidance out of frontmatter. Apply
layers.no_overlap. - De-duplicate and consolidate rules and definitions until each appears once. Apply
rules.single_source. - Add priority rules where tradeoffs exist. Apply
conflicts.priority. - Add or trim examples strictly to resolve ambiguity. Apply
examples.minimal. - Run acceptance checks.
Acceptance Criteria
A revision is complete only if all checks pass.
- Response: Output satisfies the Response Contract.
- Standards satisfied:
layers.no_overlap,routing.alone,routing.boundary,body.responsibilities,rules.single_source,conflicts.priority,examples.minimal.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?