MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements.
Install Skill Forge Evolve
$ npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AgriciDaniel/skill-forge skill-forge-evolve --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AgriciDaniel/skill-forge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-forge-evolve .claude/skills/skill-forge-evolve && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skill-forge-evolve" agent skill from https://github.com/AgriciDaniel/skill-forge/tree/main/skills/skill-forge-evolve into .claude/skills/skill-forge-evolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-forge-evolve", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AgriciDaniel/skill-forge/tree/main/skills/skill-forge-evolveType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AgriciDaniel/skill-forge skill-forge-evolve --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgriciDaniel/skill-forge.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-forge-evolve .agents/skills/skill-forge-evolve && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-forge-evolve" agent skill from https://github.com/AgriciDaniel/skill-forge/tree/main/skills/skill-forge-evolve into .agents/skills/skill-forge-evolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-forge-evolve", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AgriciDaniel/skill-forge skill-forge-evolve --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgriciDaniel/skill-forge.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-forge-evolve .cursor/skills/skill-forge-evolve && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-forge-evolve" agent skill from https://github.com/AgriciDaniel/skill-forge/tree/main/skills/skill-forge-evolve into .cursor/skills/skill-forge-evolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-forge-evolve", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AgriciDaniel/skill-forge.git --path skills/skill-forge-evolve--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AgriciDaniel/skill-forge skill-forge-evolve --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgriciDaniel/skill-forge.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-forge-evolve .gemini/skills/skill-forge-evolve && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-forge-evolve" agent skill from https://github.com/AgriciDaniel/skill-forge/tree/main/skills/skill-forge-evolve into .gemini/skills/skill-forge-evolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-forge-evolve", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AgriciDaniel/skill-forge skill-forge-evolveInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AgriciDaniel/skill-forge.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-forge-evolve .github/skills/skill-forge-evolve && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-forge-evolve" agent skill from https://github.com/AgriciDaniel/skill-forge/tree/main/skills/skill-forge-evolve into .github/skills/skill-forge-evolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-forge-evolve", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AgriciDaniel/skill-forge skill-forge-evolve --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgriciDaniel/skill-forge.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-forge-evolve .opencode/skills/skill-forge-evolve && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-forge-evolve" agent skill from https://github.com/AgriciDaniel/skill-forge/tree/main/skills/skill-forge-evolve into .opencode/skills/skill-forge-evolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-forge-evolve", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
skill-forge-evolve- GitHub stars
- 177
- Token cost
- ~1.8k tokens
- SKILL.md length
- 652 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements.
- Works in 5 steps: Diagnose the Issue → Apply Fix by Category → Iteration Workspace Protocol → …
- User says improve skill
- SKILL.md covers Process and Common Evolution Patterns
- Calls python
What it does
Skill Forge Evolve is an agent skill from AgriciDaniel/skill-forge. Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements. Handles under/over-triggering fixes, instruction refinement, new sub-skill addition, and architecture evolution. Use when user says "improve skill", "fix skill", "skill not triggering", "skill triggers too much", "update skill", or "evolve skill".
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. The repository describes itself as: Ultimate Claude Code skill creator — design, scaffold, build, review, evolve, and publish production-grade AI agent skills. The licence is MIT.
When your agent uses it
- User says improve skill
- Skill not triggering
- Skill triggers too much
Example prompts
- “improve skill”
- “fix skill”
- “skill not triggering”
- “/skill-forge-evolve”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 2872ee9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Skill Forge Evolve loads about 1.8k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 652 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from AgriciDaniel/skill-forge at commit 2872ee9, republished under its MIT licence (© AgriciDaniel). 652 words, ~1,754 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-forge-evolve/SKILL.md (or your agent's skills folder).- name
- skill-forge-evolve
- description
- Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements. Handles under/over-triggering fixes, instruction refinement, new sub-skill addition, and architecture evolution. Use when user says "improve skill", "fix skill", "skill not triggering", "skill triggers too much", "update skill", or "evolve skill".
Skill Evolution & Improvement
Process
Step 1: Diagnose the Issue
Ask the user or analyze logs to identify the problem category:
Category A: Triggering Issues
- Under-triggering: Skill doesn't activate when it should
- Over-triggering: Skill activates when it shouldn't
- Mis-triggering: Wrong sub-skill activates
Category B: Execution Issues
- Incomplete workflows: Skill stops before finishing
- Incorrect output: Results don't match expectations
- Missing error handling: Failures not handled gracefully
- Performance: Too slow or too many token used
Category C: Architecture Issues
- Missing capability: New use case not covered
- Scale issues: Skill too large, needs decomposition
- Cross-reference problems: Links to non-existent files
Category D: Quality Issues
- Inconsistent results: Different outputs for same input
- Vague instructions: Claude interprets differently each time
- Missing examples: No concrete guidance
Step 2: Apply Fix by Category
Fix: Under-Triggering
- Read current description
- Identify missing trigger phrases
- Add domain keywords and paraphrases
- Add file type mentions if relevant
- Test with 5 queries that should now trigger
Common causes:
- Description too generic
- Missing common paraphrases
- Technical jargon without lay terms
Fix template:
# Before (under-triggers)
description: Analyzes code quality
# After (specific triggers)
description: >
Static code analysis and quality assessment. Checks code style,
complexity, security vulnerabilities, and test coverage. Use when
user says "code review", "code quality", "lint", "static analysis",
"code smell", "code audit", or "check my code".Fix: Over-Triggering
- Read current description
- Identify why unrelated queries trigger it
- Add negative triggers ("Do NOT use for...")
- Make description more specific
- Test with 5 queries that should NOT trigger
Fix template:
# Before (over-triggers)
description: Processes documents for review
# After (specific + negative triggers)
description: >
Processes PDF legal documents for contract clause extraction and
compliance review. Use for legal contracts, NDAs, terms of service.
Do NOT use for general document editing, formatting, or non-legal PDFs.Fix: Execution Issues
- Identify the failing step in the workflow
- Add explicit validation gates between steps
- Add error handling with clear recovery instructions
- Add "If X fails, then Y" fallback paths
- Consider adding a script for fragile operations
Fix: Quality Issues
- Replace vague instructions with specific ones
- Add concrete examples of expected input/output
- Add explicit "do this, not that" comparisons
- Add quality check steps before final output
- Consider adding a validation script
Step 3: Iteration Workspace Protocol
Use structured workspaces to track improvements across iterations:
eval-workspace/
iteration-1/ # First version
eval-0/with_skill/ # Eval results
eval-0/baseline/
benchmark.json # Aggregated metrics
benchmark.md # Human-readable report
feedback.json # User feedback
iteration-2/ # After first improvement
eval-0/with_skill/
eval-0/baseline/
benchmark.json
benchmark.md
feedback.jsonThe iteration loop:
- Apply the fix to the skill
- Run
/skill-forge eval <path>intoiteration-<N+1>/ - Run
/skill-forge benchmark <path>with--previous iteration-<N>/ - Review benchmark comparison for regressions
- Collect user feedback into
feedback.json - Read feedback and iterate (back to Step 2)
Stop iterating when:
- User says they're happy
- All feedback is empty (everything looks good)
- Benchmark shows no meaningful progress between iterations
- Pass rate meets the defined thresholds
Step 3b: Self-Annealing Loop
For quick fixes without full eval pipeline:
1. Apply the fix
2. Test with the original failing case
3. Test with 3 other cases (regression check)
4. If fix works:
-> Update the directive/SKILL.md
-> Document the learning in references or SKILL.md
5. If fix fails:
-> Diagnose why
-> Try alternative approach
-> RepeatShow full SKILL.md (263 more words)Show less
Step 3c: Description Optimization Loop
For triggering issues (Category A), use the automated optimization loop:
- Generate trigger eval set:
python scripts/generate_eval_set.py <path> - Review and refine the eval set with the user
- Run optimization:
python scripts/optimize_description.py <path> --eval-set evals.json - Review the train/test split scores and improvement suggestions
- Apply suggested description changes
- Re-run optimization to measure improvement
- Select the description with the highest test score (not train — avoids overfitting)
- Iterate up to 5 times or until test score plateaus
Step 4: Architecture Evolution
When a skill outgrows its tier:
Tier 1 -> Tier 2 (needs scripts):
- Identify the fragile/deterministic operation
- Create script in
scripts/ - Update SKILL.md to reference the script
- Test script independently
Tier 2 -> Tier 3 (needs sub-skills):
- Identify distinct workflows that can be separated
- Extract each into its own
skills/{parent}-{child}/SKILL.md - Update main SKILL.md with routing table
- Move shared knowledge to
references/ - Update install.sh
Tier 3 -> Tier 4 (needs agents):
- Identify workflows that can run in parallel
- Create agent definitions in
agents/ - Update the audit/full-analysis sub-skill to delegate to agents
- Test parallel execution
Step 5: Version Management
After evolution:
- Update
metadata.versionin frontmatter (if present) - Add learning to SKILL.md or reference file
- Update any affected cross-references
- Re-run validation:
python scripts/validate_skill.py <path> - Test full workflow end-to-end
Common Evolution Patterns
Pattern: Adding Industry Detection
When a skill needs to adapt behavior by user type:
## Industry Detection
Detect user type from context:
- **Type A**: [signals] -> [behavior]
- **Type B**: [signals] -> [behavior]Pattern: Adding Quality Gates
When output quality is inconsistent:
## Quality Gates
Before delivering output:
- [ ] [Check 1]
- [ ] [Check 2]
- [ ] [Check 3]Pattern: Adding Scoring
When users need measurable output:
## Scoring (0-100)
| Category | Weight |
|----------|--------|
| Category A | 30% |
| Category B | 30% |
| Category C | 20% |
| Category D | 20% |© AgriciDaniel, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/skill-forge-evolve of AgriciDaniel/skill-forge.
Open the folder on GitHubat commit 2872ee9
Compare with similar skills
Skill Forge Evolve next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Forge Evolve this skillAgriciDaniel/skill-forge | 177 | — | ~1.8k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 37k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 34 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
More from AgriciDaniel/skill-forge
All 9 skills in this repoSkill Forge
AgriciDaniel/skill-forge
Ultimate Claude Code skill creator and architect. An agent skill from AgriciDaniel/skill-forge.
Skill Forge Benchmark
AgriciDaniel/skill-forge
Benchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage across iterations.
Skill Forge Build
AgriciDaniel/skill-forge
Scaffold and build Claude Code skills from plans or descriptions.
Skill Forge Convert
AgriciDaniel/skill-forge
Convert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor.
Skill Forge Eval
AgriciDaniel/skill-forge
Run evaluation pipelines on Claude Code skills to test triggering accuracy, workflow correctness, and output quality.
Skill Forge Plan
AgriciDaniel/skill-forge
Architecture and design planning for new Claude Code skills.
Related
Categories
Questions about Skill Forge Evolve
What does Skill Forge Evolve do?
Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements. Skill Forge Evolve is an agent skill from AgriciDaniel/skill-forge. Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements.
When should I use Skill Forge Evolve?
Skill Forge Evolve fits situations like: user says improve skill; skill not triggering; skill triggers too much.
How do I install Skill Forge Evolve in Claude Code?
Run `npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a claude-code`. Or copy the skill folder (skills/skill-forge-evolve in AgriciDaniel/skill-forge) into .claude/skills/skill-forge-evolve in your project. Claude Code loads it when a task matches its description.
How do I install Skill Forge Evolve in Codex?
Run `npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a codex`. Or copy the skill folder (skills/skill-forge-evolve in AgriciDaniel/skill-forge) into .agents/skills/skill-forge-evolve in your project. Codex loads it when a task matches its description.
Can I use Skill Forge Evolve in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-forge-evolve, .gemini/skills/skill-forge-evolve, .github/skills/skill-forge-evolve and .opencode/skills/skill-forge-evolve in your project.
What does Skill Forge Evolve need to run?
Going by SKILL.md and its folder, Skill Forge Evolve needs the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Skill Forge Evolve access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Skill Forge Evolve safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Skill Forge Evolve use?
Skill Forge Evolve is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Skill Forge Evolve use?
About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Skill Forge Evolve?
Skills that share tags, products or a category with Skill Forge Evolve: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 37k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Forge Evolve?
AgriciDaniel (a GitHub user) maintains it in AgriciDaniel/skill-forge, which has 177 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on April 10, 2026.
Source: AgriciDaniel/skill-forge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.