From skill-forge
Audits Claude Code skills for structure compliance, triggering accuracy, instruction quality, and best practices. Scores 0-100 with prioritized improvement recommendations.
npx claudepluginhub agricidaniel/skill-forgeThis skill uses the workspace's default tool permissions.
Accept input as:
Evaluates Claude Skills for description quality, content organization, writing style, and structural integrity. Generates weighted scores, grades, and improvement plans in score-only, remediation, or batch modes.
Audits Claude skills against Anthropic prompting best practices including positive framing, motivation, and XML structure. Use after creation/modification, before release, or for inconsistent results.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Share bugs, ideas, or general feedback.
Accept input as:
~/.claude/skills/)Read all .md files, scripts, and asset files.
Run python scripts/validate_skill.py <path> for programmatic checks.
Manual verification:
name field| Check | Pass Criteria |
|---|---|
| Name format | kebab-case, 1-64 chars, no leading/trailing hyphens |
| Description present | Non-empty, 1-1024 characters |
| Description has WHAT | Explains capabilities |
| Description has WHEN | Includes trigger phrases |
| Description has keywords | Domain-specific terms included |
| No XML tags | No < or > characters |
| Optional fields valid | license, compatibility (<500 chars), metadata |
Assess the description for activation quality:
Under-triggering risks:
Over-triggering risks:
Generate test queries:
| Criterion | Score (0-10) |
|---|---|
| Specificity | Are instructions actionable? (not "validate properly") |
| Completeness | All workflows covered? |
| Error handling | Common failures addressed? |
| Examples | Concrete examples provided? |
| Progressive disclosure | Detailed docs in references/ not SKILL.md? |
| Length | Under 500 lines / 5000 tokens? |
| Cross-references | Clear links to references/scripts? |
For skills with sub-skills:
parent-child conventionScoring methodology (0-100):
| Category | Weight | Checks |
|---|---|---|
| Frontmatter Quality | 25% | Name, description, format |
| Trigger Accuracy | 20% | WHAT + WHEN + keywords |
| Instruction Quality | 25% | Specificity, completeness, examples |
| Structure Compliance | 15% | File naming, organization, references |
| Script Quality | 10% | If applicable (full marks if no scripts needed) |
| Progressive Disclosure | 5% | Proper use of 3-level system |
After reviewing, generate a structured trigger eval set for ongoing testing:
python scripts/generate_eval_set.py <path> to auto-generate a starter setevals/evals.json in the skill directoryGood queries are realistic and specific (include file paths, context, domain details). Bad queries are overly generic ("format this data") or obviously irrelevant.
python scripts/optimize_description.py <path> --eval-set evals/evals.json
to score the current description and get improvement suggestions/skill-forge eval <path> for full functional evaluation# Skill Review: [name]
## Health Score: [X]/100
## Summary
[2-3 sentence assessment]
## Scores by Category
| Category | Score | Notes |
|----------|-------|-------|
| Frontmatter | X/25 | [issues] |
| Triggering | X/20 | [issues] |
| Instructions | X/25 | [issues] |
| Structure | X/15 | [issues] |
| Scripts | X/10 | [issues] |
| Disclosure | X/5 | [issues] |
## Critical Issues (fix immediately)
- [issue 1]
- [issue 2]
## High Priority (fix within 1 week)
- [issue 1]
## Recommendations
- [suggestion 1]
- [suggestion 2]
## Suggested Test Queries
### Should Trigger
1. [query]
2. [query]
3. [query]
### Should NOT Trigger
1. [query]
2. [query]
3. [query]