01-package-scaffolding/skill-description-optimizer/SKILL.md
Rewrite a skill's description field to fix routing problems — undertriggering, overtriggering, or passive language that fails to match user intent. Use when a skill isn't being found by agents, evaluation shows low trigger recall, or batch-auditing descriptions for a library release. Do not use when the skill's scope is the problem (not just description text) or when the description is already performing correctly.
npx skillsauth add chelch5/skilllibrary skill-description-optimizerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The description field is routing logic — it determines when hosts invoke the skill. Bad descriptions cause undertriggering (skill never fires) or overtriggering (fires for wrong tasks).
Assess:
| Mode | Symptoms | Cause | |------|----------|-------| | Undertrigger | Skill never fires for intended tasks | Description too narrow, technical, or missing user vocabulary | | Overtrigger | Fires for unrelated tasks | Description too broad, overlaps siblings, no DO NOT USE boundary | | Passive | Inconsistent triggering | Describes what skill is, not when to invoke it |
What words predict THIS skill and not siblings?
Structure (40-70 words):
Anti-patterns to avoid:
Read 2-3 similar skill descriptions. Does the new description discriminate correctly? Add a distinguishing clause if needed.
| Prompt | Type | Should Match? | |--------|------|---------------| | "[specific task in scope]" | positive | YES | | "[specific task in scope]" | positive | YES | | "[task for a sibling skill]" | negative | NO | | "[task for a sibling skill]" | negative | NO |
## Description Optimization: [skill-name]
### Failure Mode
[Undertrigger | Overtrigger | Passive]
### Before
"[original description]"
### After
"[optimized description]"
### Discrimination Check
| Similar Skill | Differentiated By |
|---------------|-------------------|
| [sibling] | [distinguishing signal] |
### Test Prompts
| Prompt | Expected | Matches? |
|--------|----------|----------|
testing
Manages context window budgets, loading strategies, and compaction techniques for AI-assisted coding sessions. Trigger on 'context window', 'what to load', 'context management', 'context overflow', 'token budget'. DO NOT USE for loading specific project docs into agent context (use project-context) or prompt wording and optimization (use prompt-crafting).
development
Implements authentication, session, token, and authorization patterns for the current stack. Trigger on 'add auth', 'JWT', 'OAuth', 'login endpoint', 'session management', 'API key auth'. DO NOT USE for OWASP hardening checklists (use security-hardening), threat modeling (use security-threat-model), or secret rotation/storage (use security-best-practices).
tools
Defines request/response shapes, versioning, validation, and compatibility rules for API-first work. Trigger on 'design API', 'OpenAPI spec', 'REST schema', 'API versioning', 'generate client SDK'. DO NOT USE for GraphQL schemas, gRPC/protobuf definitions (use stack-standards), auth endpoint logic (use auth-patterns), or external API client wrappers (use external-api-client).
development
Create a repo-local ticket system with an index, machine-readable manifest, board, and individual ticket files. Use when a repo needs task decomposition that autonomous agents can follow without re-planning the whole project each session. Do not use for executing tickets (use ticket-execution) or quick fixes that don't warrant formal tickets.