ryan-mahoney/specops-orchestrate-spec-create
skills/specops-orchestrate-spec-create/SKILL.md
This skill should be used when the user asks to generate specs for multiple analysis files by orchestrating sequential subagents that apply the specops-make-spec workflow per file.
data-ai
Updated Apr 28, 2026
$ install --global
skillsauthnpx skillsauth add ryan-mahoney/ryan-llm-skills specops-orchestrate-spec-createInstall 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: Apr 28, 2026, 8:46 AM103.7s1 file scanned
SKILL.md
- name:
- specops-orchestrate-spec-create
- description:
- This skill should be used when the user asks to generate specs for multiple analysis files by orchestrating sequential subagents that apply the specops-make-spec workflow per file.
- disable-model-invocation:
- true
- argument-hint:
- [analysis-file-list-or-directory (optional)]
SpecOps Orchestrate Spec Create
You are an orchestrator. Generate one implementation spec per analysis artifact using sequential subagents.
Use specops-make-spec behavior for each analysis file.
Do not implement product code directly unless subagents are unavailable.
Inputs
- Analysis file list or directory from
$ARGUMENTS. - If no argument is provided, discover analysis files from repository conventions (for example
docs/specops/analysis/*.md). - Project standards and conventions files when present.
Before Starting
- Build an ordered list of analysis files to process.
- Exclude clearly non-analysis files (notes, drafts, templates) unless explicitly requested.
- Determine output path per analysis file:
- Default:
docs/specops/specs/<analysis-basename>.md
- Announce execution order and output mapping before delegation.
Execution Model: One Sequential Subagent Per Analysis File
Process analysis files one at a time. Do not parallelize.
For each analysis file invoke:
Agent(
subagent_type: "general-purpose",
description: "Create spec for <analysis-file>",
prompt: "<SPEC_PROMPT>"
)
SPEC_PROMPT Template
You are creating an implementation specification from a completed SpecOps analysis.
Analysis file: <analysis-file>
Output spec file: <spec-output-file>
Follow skills/specops-make-spec/SKILL.md.
Read relevant project standards/conventions.
Write the full specification to <spec-output-file>.
Do not implement code.
Return: summary, file written, assumptions, risks.
Verification After Each Subagent
- Confirm output spec file exists and is non-empty.
- Confirm required sections from
specops-make-specare present. - Confirm acceptance criteria are observable/automatable.
- If incomplete, run one fix-up subagent for that file.
Allow up to 2 fix-up attempts per file. If still failing, stop and report blockers.
Fix-Up Subagent Template
Agent(
subagent_type: "general-purpose",
description: "Fix spec for <analysis-file>",
prompt: "Previous spec output is incomplete or invalid.
Findings: <list>
Re-read skills/specops-make-spec/SKILL.md and the analysis file.
Fix only required gaps and overwrite the same output file.
Return: what changed and why."
)
Completion
After all files complete:
- Provide per-file completion status.
- List spec files created.
- Report risks, ambiguities, and blocked files.
Related Skills
ryan-mahoney/specops-run-spec
testing
VerifiedTrustedCommunity
This skill should be used when the user asks to "run the spec", "implement the spec", or "execute the spec". Implements every step in a SpecOps implementation spec by delegating each step (or logical group of adjacent steps) to a sequential subagent, conventional-committing each one independently, and — when `roborev` is on the path — running `roborev check` on every commit and `roborev fix` (with spec context, so the fix cannot silently drift the implementation away from the spec) on any commit that fails.
SKILL.mdUpdated Apr 29, 2026
ryan-mahoney/ux-auditor
development
VerifiedTrustedCommunity
Exhaustively audit a top-level UI implementation component against an HTML prototype and produce a grouped markdown checklist of corrections. Use when a user asks for UI parity review, visual QA, design implementation audit, pixel-level drift detection, or behavior/style mismatch analysis between prototype HTML and shipped component code.
SKILL.mdUpdated Apr 28, 2026
ryan-mahoney/specops-spec-conformance
development
VerifiedTrustedCommunity
Audit a SpecOps implementation spec against its source analysis spec to find requirements, policies, contracts, edge cases, error modes, invariants, defaults, side effects, or implementation steps that the implementation has dropped, weakened, contradicted, or silently changed — then patch the implementation spec to restore them. Use this skill whenever the user mentions auditing, comparing, conforming, reconciling, or checking an implementation spec against an analysis spec, finding gaps between two specs, ensuring an implementation spec preserves analysis behavior, or verifying spec derivation or traceability. Also trigger when the user describes "did the implementation spec lose anything from the analysis," "does the implementation match the analysis," "verify the implementation spec covers everything," or asks to confirm one spec is faithful to another. Run this before generating code from an implementation spec and after either spec is edited.
SKILL.mdUpdated Apr 28, 2026
ryan-mahoney/specops-spec-coherence
development
VerifiedTrustedCommunity
Audit a set of SpecOps analysis specs for cross-spec coherence — establish a dependency-ordered implementation sequence, then verify pairwise integration contracts at module boundaries plus three cross-cutting consistency dimensions (shared data models, side-effect ownership, terminology) — and patch the affected specs to resolve gaps. Use this skill whenever the user mentions cross-spec consistency, integration gaps between specs, conflicts between specs, duplicate work across specs, implementation order, dependency order for migration, building an implementation-order checklist, ensuring specs interoperate, terminology drift across specs, or shared data model conflicts. Also trigger when the user describes "do my specs agree with each other," "what order should I implement these in," "find inconsistencies across all my specs," or asks to audit a folder of analysis specs as a set rather than individually. Run this once after generating a full set of analysis specs, before deriving implementation specs.
SKILL.mdUpdated Apr 28, 2026