update-skill-content
About
This skill updates existing SKILL.md documentation to improve accuracy and clarity by refining procedures, expanding pitfalls, and syncing related skills. It's used when documentation references outdated tools, has thin troubleshooting sections, or contains broken cross-references. The skill handles version bumping and content refinement based on user feedback.
Quick Install
Claude Code
Recommendednpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/update-skill-contentCopy and paste this command in Claude Code to install this skill
Documentation
Update Skill Content
Improve existing SKILL.md by refining procedure steps, expanding Common Pitfalls with real failure modes, syncing Related Skills section, bumping version. Use this after skill passes format validation but has content gaps, stale references, or incomplete procedures.
When Use
- Skill procedure steps reference outdated tools, APIs, version numbers
- Common Pitfalls section thin (fewer than 3 pitfalls) or missing real failure modes
- Related Skills section has broken cross-references or missing relevant links
- Procedure steps lack concrete code examples or have vague instructions
- New skill added to library that should be cross-referenced from existing skills
- After feedback that skill procedures unclear or incomplete
Inputs
- Required: Path to SKILL.md file to update
- Optional: Specific section(s) to focus on (e.g., "procedure", "pitfalls", "related-skills")
- Optional: Source of updates (changelog, issue report, user feedback)
- Optional: Whether to bump version (default: yes, minor bump)
Steps
Step 1: Read Current Skill, Assess Content Quality
Read entire SKILL.md. Evaluate each section for completeness, accuracy.
Assessment criteria per section:
- When to Use: Triggers concrete, actionable? (3-5 items expected)
- Inputs: Types, defaults, required/optional clearly separated?
- Procedure: Each step has concrete code, Expected, On failure?
- Validation: Checklist items objectively testable? (5+ items expected)
- Common Pitfalls: Pitfalls specific with symptoms, fixes? (3-6 expected)
- Related Skills: Referenced skills exist? Obvious related skills missing?
Got: Clear picture of which sections need improvement. Specific gaps identified.
If fail: Skill cannot be read (path error)? Verify path. SKILL.md has broken YAML frontmatter? Fix frontmatter first using review-skill-format before attempting content updates.
Step 2: Check for Stale References
Scan procedure steps for version-specific references, tool names, URLs, API patterns that may have changed.
Common staleness indicators:
- Specific version numbers (e.g.,
v1.24,R 4.3.0,Node 18) - URLs that may have moved or expired
- CLI flags or command syntax changed
- Package names renamed or deprecated
- Configuration file formats evolved
# Check for version-specific references
grep -nE '[vV][0-9]+\.[0-9]+' skills/<skill-name>/SKILL.md
# Check for URLs
grep -nE 'https?://' skills/<skill-name>/SKILL.md
Got: List of potentially stale references with line numbers. Each reference verified as current or flagged for update.
If fail: Too many references to check manual? Prioritize: procedure code blocks first (most likely to cause runtime failures), then Common Pitfalls (may reference old workarounds), then informational text.
Step 3: Update Procedure Steps for Accuracy
For each procedure step identified as needing improvement:
- Verify code blocks still execute correct or reflect current best practices
- Add missing context sentences explaining why step needed
- Ensure concrete commands use real paths, real flags, real output
- Update Expected blocks to match current tool behavior
- Update On failure blocks with current error messages, fixes
When updating code blocks, preserve original structure:
- Keep step numbering consistent
- Maintain
### Step N: Titleformat - No reorder steps unless original order was incorrect
Got: All procedure steps contain current, executable code. Expected/On failure blocks reflect actual current behavior.
If fail: Unsure whether code block still correct? Add note: <!-- TODO: Verify this command against current version -->. No remove working code blocks to replace with untested alternatives.
Step 4: Expand Common Pitfalls
Review Common Pitfalls section. Expand if gaps exist.
Quality criteria for pitfalls:
- Each pitfall has bold name followed by specific description
- Description includes symptom (what goes wrong) and fix (how to avoid or recover)
- Pitfalls drawn from real failure modes, not hypothetical concerns
- 3-6 pitfalls = target range
Sources for new pitfalls:
- Procedure steps with complex On failure blocks (likely pitfalls)
- Related skills that warn about same tools or patterns
- Common issues reported by users of procedure
Got: 3-6 pitfalls, each with specific symptom and fix. No generic pitfalls like "be careful" or "test thoroughly".
If fail: Only 1-2 pitfalls can be identified? Acceptable for basic-complexity skills. For intermediate, advanced skills, fewer than 3 pitfalls suggests author has not fully explored failure modes — flag for future expansion.
Step 5: Sync Related Skills Section
Verify all cross-references in Related Skills section are valid. Add any missing links.
- For each referenced skill, verify exists:
# Check if referenced skill exists test -d skills/referenced-skill-name && echo "EXISTS" || echo "NOT FOUND" - Search for skills that reference this skill (should be cross-linked):
# Find skills that reference this skill grep -rl "skill-name" skills/*/SKILL.md - Check obvious related skills based on domain, tags
- Use format:
- \skill-id` — one-line description of relationship`
Got: All referenced skills exist on disk. Bidirectional cross-references in place. No orphaned links.
If fail: Referenced skill doesn't exist? Either remove reference or note as planned future skill with comment. Many skills reference this one but not listed in Related Skills? Add most relevant 2-3.
Step 6: Bump Version in Frontmatter
Update metadata.version field following semantic versioning:
- Patch bump (1.0 to 1.1): Typo fixes, minor clarifications, URL updates
- Minor bump (1.0 to 2.0): New procedure steps, significant content additions, structural changes
- Note: Skills use simplified two-part versioning (major.minor)
Also update any date fields if present in frontmatter.
Got: Version bumped appropriately. Change magnitude matches update scope.
If fail: Current version cannot be parsed? Set to "1.1". Add comment noting version history gap.
Checks
- All procedure steps contain current, executable code or concrete instructions
- No stale version references, URLs, or deprecated tool names remain
- Every procedure step has Expected: and On failure: blocks
- Common Pitfalls section has 3-6 specific pitfalls with symptoms, fixes
- All Related Skills cross-references point to existing skills
- Bidirectional cross-references in place for closely related skills
- Version in frontmatter bumped appropriately
- Line count remains under 500 after updates
- SKILL.md still passes
review-skill-formatvalidation after changes
Pitfalls
- Update code without testing: Changing command in procedure step without verifying it works = worse than leaving old command. Uncertain? Add verification comment rather than untested replacement.
- Over-expand pitfalls: Adding 10+ pitfalls dilutes section. Keep 3-6 most impactful pitfalls. Move edge cases to
references/file if needed. - Break cross-references during updates: When renaming skill or changing domain, grep entire skills library for references to old name. Use
grep -rl "old-name" skills/to find all occurrences. - Forget to bump version: Every content update, no matter how small, should bump version. Allows consumers to detect when skill changed.
- Scope creep into refactoring: Content updates improve what skill says. Find yourself restructuring sections or extracting to
references/? Switch torefactor-skill-structureskill instead.
See Also
review-skill-format— Run format validation before content updates. Ensure base structure soundrefactor-skill-structure— When content updates push skill over 500 lines, refactor structure to make roomevolve-skill— For deeper changes beyond content updates (e.g., creating advanced variant)create-skill— Reference canonical format spec when adding new sections or procedure stepsrepair-broken-references— Use for bulk cross-reference repair across entire skills library
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
polymarket
MetaThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
creating-opencode-plugins
MetaThis skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
