All skills
simota avatar

/accord

@7e6967c
by shingo imotasimota/agent-skills85 stars
15

Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision, L1 Requirements, L2 Team Detail, L3 Acceptance Criteria). Use for cross-team specs.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/accord

This session only. Nothing lands on disk.

referencebusiness-tech-translation.md

≈706 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Business-Tech Translation

Purpose: Use this file when business language must be turned into implementable requirements without losing intent.

Contents

  • Translation loop
  • Intent mapping
  • Scope-creep detection
  • Glossary cues
  • Communication anti-patterns

Translation Loop

CLARIFY -> ALIGN -> GUARD -> DOCUMENT

Phase Goal Typical action
CLARIFY convert vague business intent into explicit requirements turn vague language into measurable L1 items
ALIGN remove expectation gaps compare business and technical interpretations
GUARD prevent scope creep flag new asks, impact, and trade-offs
DOCUMENT preserve decisions record assumptions, rationale, and decisions

Intent Mapping

Business says Translate as Accord action
"make it fast" performance requirement define measurable SLA or KPI
"simple to use" usability requirement define usability criteria in L2-Design
"secure" security requirement define scope and threat expectations in L1/L2-Dev
"scalable" load or growth requirement define load targets
"like [competitor]" feature parity request map the exact capability, not the brand
"ASAP" urgency, not scope propose a cut or phased delivery
"can you just..." likely scope expansion flag as change impact
"it should be obvious" implicit requirement make it explicit in L1

Scope-Creep Signals

Signal Risk Response
"while we're at it..." high defer or split
"can we also add..." medium estimate impact and trade-off
"it would be nice if..." low track as future enhancement
growing acceptance criteria high compare with original L1 scope
new stakeholder late in the process medium re-align L0 and scope

Glossary Cues

Business term Technical translation
downtime service unavailability or SLA target
response API or UI latency target
security auth, authorization, encryption, auditability
scalability load capacity and scaling model
usability task completion, accessibility, cognitive load
performance measurable latency or throughput targets
quality defect rate, testability, reliability

Communication Anti-Patterns

Anti-pattern Failure mode Prevention
jargon dumping business readers disengage translate through glossary
silent assumptions each team imagines something different list assumptions explicitly
scope ambiguity "phase 1" means different things define deliverables and out-of-scope work
missing why teams cannot prioritize correctly keep L0 and L2-Biz clear
one-way specs teams read but do not align use L3 plus cross-references

Source: SKILL.md on GitHub

No alerts4mo5 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    Accord is a specification authoring skill designed for cross-functional team alignment. It focuses on generating documentation, requirements, and BDD scenarios. The security audit found no evidence of malicious behavior, data exfiltration, or unauthorized command execution.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: LOW · No issues

  • Runlayer6mo

    1/12 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 7e6967c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 months ago

README badge

README badge for simota/agent-skills/accord