Skill Forge
AgriciDaniel/skill-forge
Ultimate Claude Code skill creator and architect. An agent skill from AgriciDaniel/skill-forge.
Walks you through creating, running and reading waza evals for an agent skill, then proposes concrete fixes when tasks fail or the score is low.
Install Waza Interactive
$ npx skills add microsoft/waza --skill waza-interactive -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/waza waza-interactive --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/microsoft/waza.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/waza-interactive .claude/skills/waza-interactive && 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 "waza-interactive" agent skill from https://github.com/microsoft/waza/tree/main/skills/waza-interactive into .claude/skills/waza-interactive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waza-interactive", 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/microsoft/waza/tree/main/skills/waza-interactiveType 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 microsoft/waza --skill waza-interactive -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/waza waza-interactive --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/waza.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/waza-interactive .agents/skills/waza-interactive && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "waza-interactive" agent skill from https://github.com/microsoft/waza/tree/main/skills/waza-interactive into .agents/skills/waza-interactive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waza-interactive", 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 microsoft/waza --skill waza-interactive -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/waza waza-interactive --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/waza.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/waza-interactive .cursor/skills/waza-interactive && 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 "waza-interactive" agent skill from https://github.com/microsoft/waza/tree/main/skills/waza-interactive into .cursor/skills/waza-interactive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waza-interactive", 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/microsoft/waza.git --path skills/waza-interactive--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 microsoft/waza --skill waza-interactive -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/waza waza-interactive --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/waza.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/waza-interactive .gemini/skills/waza-interactive && 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 "waza-interactive" agent skill from https://github.com/microsoft/waza/tree/main/skills/waza-interactive into .gemini/skills/waza-interactive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waza-interactive", 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 microsoft/waza waza-interactiveInstalls 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 microsoft/waza --skill waza-interactive -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/waza.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/waza-interactive .github/skills/waza-interactive && 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 "waza-interactive" agent skill from https://github.com/microsoft/waza/tree/main/skills/waza-interactive into .github/skills/waza-interactive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waza-interactive", 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 microsoft/waza --skill waza-interactive -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microsoft/waza waza-interactive --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/waza.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/waza-interactive .opencode/skills/waza-interactive && 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 "waza-interactive" agent skill from https://github.com/microsoft/waza/tree/main/skills/waza-interactive into .opencode/skills/waza-interactive/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "waza-interactive", 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
waza-interactive- GitHub stars
- 1.4k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 636 words
- Files
- 2
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- MIT
At a glance
Walks you through creating, running and reading waza evals for an agent skill, then proposes concrete fixes when tasks fail or the score is low.
- Works in 8 steps: Ask which skill to evaluate — get the… → Call waza_eval_list to check for… → If none exist, run waza init via… → …
- Setting up an eval suite for a skill you are building
- SKILL.md covers Available MCP Tools, Scenario 1: Create a New Eval, Scenario 2: Run and Interpret… and Scenario 3: Compare Models, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The agent acts as a conversational partner for waza, a framework for measuring how well agent skills perform. It works through waza's MCP tools, which list eval suites, fetch an eval spec, validate the YAML, start a benchmark run, poll or cancel it, summarize scores, show per-task results and check a skill for compliance.
For a new eval it asks which skill to test, checks for existing suites, runs `waza init` in the terminal if none exist, explains the generated `eval.yaml` and helps write three to five tasks covering the happy path, an edge case and error handling. After a run it reports pass rate, weighted score and duration, treats 90% and above as strong and anything under 70% as a serious problem, and digs into failed tasks when the pass rate drops below 80%. The excerpt also begins a model-comparison scenario but is cut off there.
When your agent uses it
- Setting up an eval suite for a skill you are building
- Running waza benchmarks and making sense of the pass rate and weighted score
- Finding out why particular eval tasks keep failing
- Comparing how two models score on the same skill eval
Example prompts
- “Create an eval suite for my pdf-extractor skill in ./skills/pdf-extractor.”
- “Run the evals for the changelog skill and explain why the pass rate is under 80%.”
- “Compare gpt-4o and claude-sonnet-4 on the code-review eval.”
- “Is my release-notes skill ready to ship?”
Requirements
- The waza CLI
- Access to the waza MCP tools
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Ask which skill to evaluate — get the skill name and path
- Call waza_eval_list to check for existing evals for this skill
- If none exist, run waza init via terminal to scaffold
- Explain the generated eval.yaml structure — name, skill, executor, tasks
- Help define tasks: ask what behaviors to test, suggest validators (code, regex)
- For each task, help write the prompt and expected output
- Call waza_eval_validate to confirm the YAML is valid
- Suggest running with waza_eval_run to verify the first task passes
What it can do on your machine
Read from SKILL.md and the folder at commit 774df00. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Waza Interactive loads about 1.3k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 636 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 microsoft/waza at commit 774df00, republished under its MIT licence (© microsoft). 636 words, ~1,323 tokens.
Download SKILL.mdSave it as
.claude/skills/waza-interactive/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- waza-interactive
- description
- Interactive workflow partner for creating, testing, and improving AI agent skills with waza. USE FOR: run my evals, check my skill, compare models, create eval suite, debug failing tests, is my skill ready, ship readiness, interpret results, improve score. DO NOT USE FOR: general coding, non-skill work, writing skill content (use skill-authoring), improving frontmatter only (use sensei).
Waza Interactive
You are a workflow partner that orchestrates waza evaluations conversationally. Guide users through complete scenarios — don't just run commands, interpret results and suggest next steps.
Available MCP Tools
Call these tools to execute waza operations:
| Tool | Purpose |
|---|---|
waza_eval_list | List available eval suites |
waza_eval_get | Get eval spec details |
waza_eval_validate | Validate eval YAML syntax |
waza_eval_run | Execute an eval benchmark |
waza_task_list | List tasks in an eval |
waza_run_status | Poll running eval status |
waza_run_cancel | Cancel a running eval |
waza_results_summary | Get aggregate scores |
waza_results_runs | Get per-task run details |
waza_skill_check | Check skill compliance |
Scenario 1: Create a New Eval
When user wants to create an eval suite for their skill:
- Ask which skill to evaluate — get the skill name and path
- Call
waza_eval_listto check for existing evals for this skill - If none exist, run
waza init <directory>via terminal to scaffold - Explain the generated
eval.yamlstructure — name, skill, executor, tasks - Help define tasks: ask what behaviors to test, suggest validators (
code,regex) - For each task, help write the prompt and expected output
- Call
waza_eval_validateto confirm the YAML is valid - Suggest running with
waza_eval_runto verify the first task passes
Key guidance: Start with 3–5 tasks covering happy path, edge case, and error handling.
Scenario 2: Run and Interpret Results
When user wants to run evals and understand scores:
- Call
waza_eval_runwith the eval spec path and context dir - Poll
waza_run_statusuntil complete (check every 10s) - Call
waza_results_summaryto get aggregate scores - Interpret the results for the user:
- Pass rate — percentage of tasks that passed all validators
- Weighted score — 0.0–1.0 aggregate across all tasks
- Duration — total and per-task execution time
- If pass rate < 80%, identify which tasks failed and why
- Call
waza_results_runsfor per-task details on failures - Suggest specific improvements: prompt rewording, validator tuning, fixture updates
Thresholds: ≥90% pass rate = strong, 70–89% = needs work, <70% = significant issues.
Scenario 3: Compare Models
When user wants to compare model performance:
- Ask which models to compare (e.g., gpt-4o vs claude-sonnet-4)
- Call
waza_eval_runwith model A — save results - Call
waza_eval_runwith model B — save results - Compare results side by side:
- Per-task pass/fail differences
- Score deltas (which model scores higher on which tasks)
- Duration differences (speed vs quality tradeoff)
- Provide a recommendation: which model is better for this skill and why
- Suggest next steps: try a third model, tune prompts for the weaker model, or adjust validators
Guidance: Run each model 2–3 times to account for variance before drawing conclusions.
Show full SKILL.md (214 more words)Show less
Scenario 4: Debug a Failing Skill
When user's skill is failing evals or behaving unexpectedly:
- Call
waza_skill_checkto verify skill compliance (frontmatter, triggers, token count) - If compliance issues found, fix those first — they affect routing
- Call
waza_eval_runwith--verboseand--transcript-dirflags - Call
waza_results_runsto get per-task failure details - Analyze failure patterns:
- All tasks fail → prompt or fixture issue, check skill instructions
- Some tasks fail → specific edge cases, review failed task prompts
- Validator failures → regex too strict, code validator language mismatch
- Suggest targeted fixes based on the pattern
- Re-run with
waza_eval_runto verify the fix
Scenario 5: Ship Readiness Check
When user asks "is my skill ready?" or wants a pre-ship checklist:
- Call
waza_skill_check— verify compliance score ≥ medium-high - Call
waza_eval_validate— confirm eval YAML is valid - Call
waza_eval_run— execute full eval suite - Call
waza_results_summary— check aggregate scores - Render the readiness verdict:
SHIP READINESS CHECKLIST:
☐ Skill compliance: [score] (need: medium-high+)
☐ Eval YAML valid: [yes/no]
☐ Pass rate: [X]% (need: ≥90%)
☐ Weighted score: [X.XX] (need: ≥0.85)
☐ No task timeouts
☐ Consistent across 2+ runs
VERDICT: [READY / NOT READY — fix items marked ✗]- If NOT READY, route to the appropriate scenario (Scenario 4 for failures, Scenario 1 for missing evals)
Conversation Style
- Always explain why before what — context before commands
- After every tool call, interpret the result in plain language
- When something fails, diagnose before suggesting fixes
- Offer the next logical step — don't wait to be asked
- Use the checklist format for multi-step validations
© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/waza-interactive of microsoft/waza.
- SKILL.md
- tests/eval.yaml
Open the folder on GitHubat commit 774df00
Compare with similar skills
Waza Interactive 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 |
|---|---|---|---|---|---|---|
| Waza Interactive this skillmicrosoft/waza | 1.4k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Skill ForgeAgriciDaniel/skill-forge | 177 | — | ~1.9k | Automated safety check: Notes | MIT | |
| Skill CreatorZS520L/HanakoPro | 102 | — | ~7.4k | Automated safety check: Pass | Apache-2.0 | |
| Octocode Graph Eval Loopbgauryy/octocode | 946 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Create Skilldavekilleen/Dex | 493 | — | ~2.9k | Automated safety check: Pass | Custom licence | |
| Skill Creatorhimself65/finance-skills | 3.4k | — | ~3.8k | Automated safety check: Pass | MIT |
Similar skills
Skill Creator
ZS520L/HanakoPro
Create new skills, modify and improve existing skills, and measure skill performance.
Octocode Graph Eval Loop
bgauryy/octocode
Runs a measurable keep-or-discard improvement loop against a runnable sensor, from framing a goal and KPI through baseline, judging and held-out verification.
Create Skill
davekilleen/Dex
Author a new Dex skill that actually fires and passes the quality bar.
Skill Creator
himself65/finance-skills
Create, improve, and evaluate agent skills (SKILL.md plus reference files).
- Official
Benchmark Agents
vercel/vercel-plugin
Advanced AI agent benchmark scenarios that push Vercel's cutting-edge platform features — Workflow SDK, AI Gateway, MCP, Chat SDK, Queues, Flags, Sandbox, and multi-agent orchestration.
More from microsoft/waza
All 16 skills in this repo- Official
Squad Commands Menu
microsoft/waza
Shows a categorized, interactive menu of common Squad operations, such as install, upgrade and team management, and collects arguments before running anything.
- Official
Squad Agent Collaboration Patterns
microsoft/waza
Shared collaboration rules for a team of squad agents covering worktree awareness, writing decisions to an inbox, cross-agent requests and reviewer lockout.
- Official
waza azd Extension Publisher
microsoft/waza
Walks through releasing a new version of the waza azd extension: changelog from commits, semver bump with your confirmation, and a release PR.
- Official
Squad Git Branching Workflow
microsoft/waza
Dev-first branching model for the Squad project: feature work branches from dev, issue branches follow a naming rule and parallel issues use git worktrees.
- Official
Waza Skill Evaluator
microsoft/waza
Evaluates agent skills with a Go CLI that runs YAML-defined benchmarks, compares runs and scores the quality of SKILL.md frontmatter.
- Official
Reviewer Protocol
microsoft/waza
Reviewer rejection workflow and strict lockout semantics. An agent skill from microsoft/waza.
Related
Works with
Categories
Questions about Waza Interactive
What does Waza Interactive do?
Walks you through creating, running and reading waza evals for an agent skill, then proposes concrete fixes when tasks fail or the score is low. The agent acts as a conversational partner for waza, a framework for measuring how well agent skills perform. It works through waza's MCP tools, which list eval suites, fetch an eval spec, validate the YAML, start a benchmark run, poll or cancel it, summarize scores, show per-task results and check a skill for compliance.
When should I use Waza Interactive?
Waza Interactive fits situations like: setting up an eval suite for a skill you are building; running waza benchmarks and making sense of the pass rate and weighted score; finding out why particular eval tasks keep failing; comparing how two models score on the same skill eval.
How do I install Waza Interactive in Claude Code?
Run `npx skills add microsoft/waza --skill waza-interactive -a claude-code`. Or copy the skill folder (skills/waza-interactive in microsoft/waza) into .claude/skills/waza-interactive in your project. Claude Code loads it when a task matches its description.
How do I install Waza Interactive in Codex?
Run `npx skills add microsoft/waza --skill waza-interactive -a codex`. Or copy the skill folder (skills/waza-interactive in microsoft/waza) into .agents/skills/waza-interactive in your project. Codex loads it when a task matches its description.
Can I use Waza Interactive 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 microsoft/waza --skill waza-interactive -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/waza-interactive, .gemini/skills/waza-interactive, .github/skills/waza-interactive and .opencode/skills/waza-interactive in your project.
What does Waza Interactive need to run?
SKILL.md names no scripts, command-line tools or credentials: Waza Interactive is instructions for the agent only. Our summary lists: The waza CLI; Access to the waza MCP tools.
Does Waza Interactive 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 Waza Interactive 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 Waza Interactive use?
Waza Interactive 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 Waza Interactive use?
About 1.3k tokens (SKILL.md is roughly 5.3k 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 Waza Interactive?
Skills that share tags, products or a category with Waza Interactive: Skill Forge (AgriciDaniel/skill-forge, 177 stars), Skill Creator (ZS520L/HanakoPro, 102 stars), Octocode Graph Eval Loop (bgauryy/octocode, 946 stars) and Create Skill (davekilleen/Dex, 493 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Waza Interactive?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/waza, which has 1,400 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 6, 2026.
Source: microsoft/waza on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.