n4m3z/ExtractPrompt
skills/ExtractPrompt/SKILL.md
Move bulk reference material from the main SKILL.md body into @-included companion files so the always-loaded content stays lean. USE WHEN an adopted or authored skill's body exceeds its information density because it inlines reference tables, pricing, catalogs, or per-variant guidance.
$ install --global
skillsauthnpx skillsauth add n4m3z/forge-core ExtractPromptInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 10, 2026, 6:01 AM133.3s1 file scanned
SKILL.md
- name:
- ExtractPrompt
- description:
- Move bulk reference material from the main SKILL.md body into @-included companion files so the always-loaded content stays lean. USE WHEN an adopted or authored skill's body exceeds its information density because it inlines reference tables, pricing, catalogs, or per-variant guidance.
- version:
- 0.1.0
- allowed-tools:
- Read, Edit, Write
ExtractPrompt
Move bulk reference material out of SKILL.md into companion files referenced with @ includes. The SKILL.md stays the entrypoint an AI reads to decide behavior; companions load on demand when the AI needs the reference data. Referenced by ForgeAdopt as the extract transform.
Follows [ARCH-0002](docs/decisions/ARCH-0002 Skills Companion Files.md).
What to extract
| Content shape | Extract to a companion? |
| -------------------------------------------------------------------------- | ---------------------------------- |
| Long reference table (model pricing, language-specific rules, catalogs) | Yes |
| Per-variant guidance (one section per framework, language, or ecosystem) | Yes, one companion per variant |
| Command reference (many commands, each with flags and examples) | Yes, if it spans more than a screen |
| Full example project | Yes, always |
| Workflow that decides HOW to use the skill | No, stays in SKILL.md |
| Constraints, red flags, anti-patterns | No, stays in SKILL.md |
| Decision tables with 3-7 rows | No, inline |
Procedure
-
Identify candidate sections — content that is reference material rather than instruction.
-
For each candidate, move it to a companion file named by its scope (
PythonReference.md,Tables.md,ModelPricing.md). -
Replace the extracted block with an
@include inSKILL.md:## Language-specific guidance @python-security.md @typescript-security.md @go-security.md -
Keep the section heading in
SKILL.mdso the AI knows the companion exists. -
Re-read
SKILL.mdalone. It should still be a complete instruction — the AI must be able to decide what to do without loading the companion.
Naming
- Companions live in the same directory as
SKILL.md - PascalCase for conceptual companions (
TemplateReference.md,SchemaValidation.md) - kebab-case for variant-keyed companions (
python-django-security.md) - One companion per topic; do not bundle unrelated reference material
Constraints
SKILL.mdmust remain complete as instruction on its own — companions are reference, not required loading- Never extract decision-making content; the AI needs it to choose which companion to read
- Do not create a companion unless at least 200 words would move; smaller moves are just fragmentation
- Keep companion files under 2000 words each; split further if they grow
- Do not nest companions (a companion cannot
@-include another companion) — compose at the SKILL.md level
Related Skills
n4m3z/Wtf
development
VerifiedTrustedCommunity
Reactive correction and root-cause fix. USE WHEN something went wrong, user is frustrated, demands a correction, says wtf, what the hell, why did you, that's wrong, this is broken, no not that, stop. Executes the immediate fix, then hunts the upstream artifact that caused it and creates a corrective change.
4SKILL.mdUpdated May 28, 2026
n4m3z/ResearchTopic
development
VerifiedTrustedCommunity
Decompose a research question into sub-queries, spawn parallel WebResearcher agents per angle, synthesize findings with citations and explicit confidence. USE WHEN the user asks to research, investigate, look online, look up, dig into, find sources, gather evidence, or survey what's known about a topic. Single-pass; for multi-round adversarial research use ResearchCouncil in forge-council.
4SKILL.mdUpdated May 27, 2026
n4m3z/WriteDocs
tools
VerifiedTrustedCommunity
Author project documentation that future humans (and AI sessions) actually read. Covers TLDRs for tools, READMEs, runbooks, journals. USE WHEN write documentation, create tldr, tool one-pager, document a cli, write readme, runbook, journal entry, capture knowledge about a tool, distill a session into reusable notes.
4SKILL.mdUpdated May 25, 2026
n4m3z/StagedReview
development
VerifiedTrustedCommunity
Review your own staged changes via a code-review TUI before triggering a commit. USE WHEN about to commit, walking through your own staged diff, self-reviewing before approval, tuicr, revdiff, git diff cached.
4SKILL.mdUpdated May 25, 2026