◂ Skills Catalog
● forge · agent-skill-creator · v6.0.0

Turn any workflow into
reusable AI agent software.

Describe a workflow in plain English — or hand over a PDF, a link, a script. Get back a complete, validated, security-scanned agent skill with functional code, its own eval spec, and a cross-platform installer. No spec writing. No prompt engineering. No coding.

Terminal recording: validate, security_scan, and eval --rollout all passing on a generated skill

Genuine output from a real run — validate → security_scan → eval --rollout on a generated skill.

17
install targets
5
pipeline phases
2
hard gates: validate + security
3–6
eval checks per skill
MIT
license
How it works

Five phases, three stages, two hard gates.

You don't need to understand any of this to use it — the agent reads your material, uncovers the implicit requirements, and builds from a deeper spec than what you typed.

Understand

Discovery + Design

Reads all your material, researches APIs, and derives what you actually need — not just what you typed.

  • Phase 1 Discovery — compare APIs by cost, rate limits, docs; decide with justification
  • Phase 2 Design — 4–6 priority use cases, artifact assessment, eval criteria (3–6 checks + 3 golden cases)
Build

Architecture + Detection

Decides simple skill vs. multi-agent suite, then writes activation keywords so agents actually discover it.

  • Phase 3 Architecture — single SKILL.md or complex component suite
  • Phase 4 Detection — ≤1024-char description with domain keywords for cross-platform activation
Verify

Implementation + Gates

Generates every file, then blocks delivery unless it passes validation and a security scan.

  • Phase 5 SKILL.md, AGENTS.md, scripts, references, eval spec, install.sh, README
  • Gates spec validation, security scan (keys, injection), pipeline check, eval --validate
Try it

Three runnable examples

Each ships in references/examples/ and passes the same gates the creator applies to skills it generates — validate.py, check_pipeline.py, and its own bundled eval spec.

You'd say…

weekly-crm-report

"Clean this CRM export and total sales by region."

→ a deduped regional-totals JSON summary
references/examples/weekly-crm-report/
You'd say…

pr-blocker-summarizer

"Summarize my open PRs, blockers first."

→ a standup digest: blocked vs. ready, one-line count
references/examples/pr-blocker-summarizer/
You'd say…

stock-analyzer

"Analyze AAPL with RSI and MACD."

→ indicators + a buy/sell/hold signal with reasoning
references/examples/stock-analyzer/
Why this vs. the alternatives

Built-in gates that others leave to you

Agent Skill CreatorHand-writing a SKILL.mdAnthropic's skill-creator
Time to a working skill~minutes, one promptHours of spec + iterationMinutes (interactive Q&A)
Coding requiredNone — it writes the codeYesSome
Cross-platform install17 platforms, auto-detectedOne tool, by handClaude-focused
Validation + security scanYes, hard gatesManualPartial
Ships an eval specYes, per skillNoNo
Optimizable (autoresearch handoff)YesNoNo
Input you can hand itProse, PDF, URL, code, transcriptYou write it from scratchGuided prompts
What's new — v6

Artifacts, and a metric for every skill

Artifacts-first

Interactive React artifacts, no React written

When output is visualizable — time series, comparisons, KPIs, tables — Phase 2 inlines one of four bundled templates (line-chart, bar-chart, kpi-cards, data-table) plus the artifact protocol into the generated SKILL.md. Hosts that don't render artifacts get honest degradation: fenced code, unchanged markdown analysis. Suppress with --no-artifact, or force one with --artifact <name>.

Eval specs

Every skill ships its own metric

Each generated skill carries evals/<name>.eval.md plus scripts/run_evals.py — 3–6 binary checks and ≥3 golden cases, seeded from your own files. run_evals.py exits non-zero on failure and drops into CI. --rollout --promote captures the first passing baseline. On by default; skip with --no-eval.

Quick start

Install, then describe what you do

No clone, no pip, no API key to get started — just git and any one of 17 supported tools.

curl -fsSL https://raw.githubusercontent.com/FrancyJGLisboa/agent-skill-creator/main/scripts/bootstrap.sh | sh

Then open your AI tool and describe what you do:

/agent-skill-creator Every Friday I clean the CRM export, calculate regional totals, and email a PDF sales report.

Auto-detected on install:

Claude CodeCursorGitHub CopilotGemini CLI WindsurfKiroClineRoo Code Kilo CodeFactory DroidGooseOpenCode + 5 more