Creates a complete product feature specification. Use when defining new features, writing user stories, or planning product work. Generates structured specs in docs/specs/.
Scanned 5/28/2026
Install via CLI
openskills install ArtemioPadilla/agent-triforce---
name: feature-spec
description: >
Creates a complete product feature specification. Use when defining new features,
writing user stories, or planning product work. Generates structured specs in docs/specs/.
context: fork
agent: prometeo-pm
---
Create a feature specification for: $ARGUMENTS
Follow these steps:
**SIGN IN:**
- Run the SIGN IN checklist from your agent file
- Surface any initial concerns about this feature request
**TIER SELECTION:**
1. Ask the user which spec tier to use:
- **S (Small)**: Bug fix, tweak, minor enhancement (~10 min)
- **M (Medium)**: Standard feature — default choice (~30-60 min)
- **L (Large)**: Epic, multi-phase, API-heavy (~60-90 min)
2. If the user does not specify, default to M
**RESEARCH (READ-DO):**
3. Read existing specs in `docs/specs/` to understand current patterns and avoid conflicts
4. Identify dependencies on existing features or systems
**BUILD:**
5. Create the spec at `docs/specs/{feature-name}.md` using the tier-appropriate template from your system prompt
6. For each user story, validate against INVEST:
- **I**ndependent: can be delivered separately
- **N**egotiable: not a rigid contract, allows discussion
- **V**aluable: delivers value to user or business
- **E**stimable: Dev can estimate effort
- **S**mall: fits in one iteration
- **T**estable: has clear acceptance criteria
7. For M/L tiers, verify IEEE 830 quality attributes: completeness, consistency, unambiguity, verifiability
8. For M/L tiers, fill in testing considerations: identify the 2-3 highest-risk acceptance criteria, recommend a test design technique for each (BVA for bounded inputs, EP for categorical inputs, Decision Table for complex branching, State Transition for lifecycle objects), note test data needs, and flag non-functional test requirements
**TIME OUT -- Run Spec Completion Checklist (DO-CONFIRM):**
8. Run through every item in the Spec Completion checklist from your agent file
9. Fix any gaps BEFORE proceeding
**SIGN OUT:**
10. Write the Handoff-to-Forja using the communication checklist
11. Run the SIGN OUT checklist from your agent file
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.