project-skill-scripts
Find and create supporting scripts for plugin skills. Use when auditing skills for script opportunities, improving token efficiency, or extracting bash blocks from SKILL.md.
What this skill does
# /project:skill-scripts
Analyze plugin skills to identify opportunities where supporting scripts would improve performance (fewer tokens, faster execution, consistent results), then optionally create those scripts.
## When to Use This Skill
| Use this skill when... | Use alternative when... |
|------------------------|--------------------------|
| Analyzing skill improvement opportunities | Need to create a single script for a skill |
| Bulk script creation across plugins | One-off script for one specific need |
| Measuring coverage of scripts across portfolio | Script generation is already done |
## Context
- Plugin root: !`git rev-parse --show-toplevel`
- Total plugins: !`find . -maxdepth 2 -name 'plugin.json' -type f`
- Skills with scripts: !`find . -name 'scripts/*.sh' -type f`
## Parameters
Parse `$ARGUMENTS` for:
- `--analyze`: Scan all skills, report candidates (default)
- `--create <plugin/skill>`: Create script for specific skill only
- `--all`: Analyze and create scripts for all high-scoring candidates
## Execution
Execute this skill script analysis and creation workflow:
### Step 1: Run analysis script
Execute analyzer to get structured data on all skills:
1. Run analyzer: `bash "${CLAUDE_PLUGIN_ROOT}/skills/project-discovery/scripts/analyze-skills.sh" $(git rev-parse --show-toplevel 2>/dev/null || echo '.')`
2. Parse output to identify:
- Current coverage (skills with scripts)
- High-scoring candidates (score >= 8)
- Script type recommendations
### Step 2: Analyze candidates (--create or --all modes)
For each candidate skill:
1. Read SKILL.md to understand the workflow
2. Identify script opportunity patterns:
- Multiple sequential git/gh commands → context-gather script
- Multi-phase workflow → workflow script
- Project type detection + conditional execution → multi-tool script
- Repeated command with different args → utility script
3. Evaluate benefit: >= 4 tool calls, consistency, error handling, reuse frequency
4. Skip if: single simple commands, interactive/creative, already well-structured
### Step 3: Create scripts
For approved candidates:
1. Use standard script template with structured output (KEY=value, section markers)
2. Follow design principles: structured output, error resilience, bounded output, portable
3. Place in `<plugin>/skills/<skill-name>/scripts/<script-name>.sh`
4. Make executable: `chmod +x <path>`
5. Update SKILL.md with "Recommended" section referencing the script
6. Update `modified:` date in frontmatter
### Step 4: Report results
Present findings:
- Current coverage (X/Y skills have scripts)
- Scripts created (plugin, skill, script, type, commands replaced)
- Remaining candidates (plugin, skill, score, type, recommendation)
- Next steps (test, commit)
### Step 5: Commit changes
If scripts created:
```
feat(<affected-plugins>): add supporting scripts to skills
```
Include in body:
- Which scripts were created
- What they replace (token/call savings)
- Which SKILL.md files were updated
## Examples
### Analyze Only
```
$ /project:skill-scripts --analyze
Skill Scripts Analysis
Current Coverage: 5/191 skills have supporting scripts
Top Candidates:
git-plugin/gh-cli-agentic score=14 type=context-gather
kubernetes-plugin/kubectl-debugging score=12 type=multi-tool
testing-plugin/playwright-testing score=10 type=workflow
```
### Create for Specific Skill
```
$ /project:skill-scripts --create testing-plugin/playwright-testing
Analyzing testing-plugin/playwright-testing...
Found: 6 bash blocks, 3 phases, 12 commands
Creating scripts/run-tests.sh...
- Consolidates: test discovery, execution, report parsing
- Replaces: 5 individual tool calls
- Output: structured test results with file:line references
Updated SKILL.md with "Recommended" section.
```
## Error Handling
| Situation | Action |
|-----------|--------|
| Skill has no bash patterns | Skip, report "no script opportunity" |
| Script already exists | Report existing, ask to overwrite |
| SKILL.md is read-only | Report error, suggest manual update |
| Plugin not found | List available plugins |
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.