How do I install the Dh Glossary skill?

Run npx skillmds@latest add jamie-bitflight/dh-glossary in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dh Glossary safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dh Glossary?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dh Glossary free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Dh Glossary?

Jamie-BitFlight (@jamie-bitflight) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dh Glossary by jamie-bitflight — Agent Skill

Name: Dh Glossary
Rating: 4.2 (5 reviews)
Author: Jamie-BitFlight

Dh Glossary

One-line definitions of development-harness (dh) plugin terminology — RT-ICA, ARL, SAM, the S1-S7 pipeline stage names, Impact Radius — each with a pointer to its canonical source file. Use when a dh skill, agent, or workflow step references a term without defining it, before guessing what the term means from its observed outputs, or when asked what a dh concept or acronym stands for.

File contents

dh Glossary

A mandate that names a dh concept states only the name, not the method — the orchestrator sees the outcome (a verdict, a gate, a report) and can misinfer the mechanism from watching what it does. Load this skill instead of inferring; each entry states the method, not just the outcome, and points to the file that is authoritative if this entry ever drifts from it.

Terms

RT-ICA (Reverse Thinking - Information Completeness Assessment) — works backward from the stated goal through its prerequisite chain: what must exist to reach the goal, then what each of those things requires, recursively back to the current state. Classifies each prerequisite as AVAILABLE, DERIVABLE, or MISSING. dh:rt-ica blocks planning on any MISSING condition (S2 implementation gate); dh:planner-rt-ica is the non-blocking sister used during grooming, which localizes a MISSING condition to the affected task instead of halting. Canonical: skills/rt-ica/SKILL.md.

ARL (Autonomous Refinement Loop) — research into the prerequisites for autonomous agent execution without synchronous human blocking gates: failure categories, and the conditions under which a machine-verifiable check can replace human judgment. dh's human-touchpoint model is ARL-derived — see the S1-S7 entry below. Canonical: plugins/plugin-creator/skills/arl/SKILL.md.

SAM (Stateless Agent Methodology) — the 7-stage development pipeline this harness implements (S1-S7, below). "Stateless" means each stage's state lives in a provider-owned artifact, never in conversation history — a stage reads its input from the prior stage's registered artifact, not from what an agent remembers saying earlier. Canonical: plugins/development-harness/AGENTS.md ("SAM 7-Stage Pipeline").

S1-S7 — the SAM pipeline stage names, in order: S1 Discovery (understand the feature, codebase, constraints) → S2 Planning + RT-ICA (generate a plan, gated by dh:rt-ica) → S3 Context Integration (validate the plan against actual codebase state) → S4 Task Decomposition (break the plan into executable tasks) → S5 Execution (implement tasks via language-specific specialists) → S6 Forensic Review (verify each task against its acceptance criteria) → S7 Final Verification (certify the feature meets the original requirements). Not every stage requires human review — ARL-derived constraint analysis decides when to escalate, not a fixed checkpoint per stage. Canonical: plugins/development-harness/AGENTS.md ("How It Works").

Impact Radius — the backlog-item section listing every system a proposed change affects (code, docs, configuration, CI, tests, agent instructions), written by @dh:impact-analyst before planning. The feasibility gate and grooming staleness checks read this section to size a change's blast radius; an item using an older grooming template may have this content under a Resources section instead — readers of the primary key fall back to it. Canonical: plugins/development-harness/agents/impact-analyst.md.

---name: dh-glossarydescription: One-line definitions of development-harness (dh) plugin terminology — RT-ICA, ARL, SAM, the S1-S7 pipeline stage names, Impact Radius — each with a pointer to its canonical source file. Use when a dh skill, agent, or workflow step references a term without defining it, before guessing what the term means from its observed outputs, or when asked what a dh concept or acronym stands for.---# dh GlossaryA mandate that names a dh concept states only the name, not the method — the orchestrator sees theoutcome (a verdict, a gate, a report) and can misinfer the mechanism from watching what it does.Load this skill instead of inferring; each entry states the method, not just the outcome, andpoints to the file that is authoritative if this entry ever drifts from it.## Terms**RT-ICA** (Reverse Thinking - Information Completeness Assessment) — works backward from thestated goal through its prerequisite chain: what must exist to reach the goal, then what each ofthose things requires, recursively back to the current state. Classifies each prerequisite asAVAILABLE, DERIVABLE, or MISSING. `dh:rt-ica` blocks planning on any MISSING condition (S2implementation gate); `dh:planner-rt-ica` is the non-blocking sister used during grooming, whichlocalizes a MISSING condition to the affected task instead of halting. Canonical:[`skills/rt-ica/SKILL.md`](../rt-ica/SKILL.md).**ARL** (Autonomous Refinement Loop) — research into the prerequisites for autonomous agentexecution without synchronous human blocking gates: failure categories, and the conditions underwhich a machine-verifiable check can replace human judgment. dh's human-touchpoint model isARL-derived — see the S1-S7 entry below. Canonical:`plugins/plugin-creator/skills/arl/SKILL.md`.**SAM** (Stateless Agent Methodology) — the 7-stage development pipeline this harness implements(S1-S7, below). "Stateless" means each stage's state lives in a provider-owned artifact, never inconversation history — a stage reads its input from the prior stage's registered artifact, notfrom what an agent remembers saying earlier. Canonical: `plugins/development-harness/AGENTS.md`("SAM 7-Stage Pipeline").**S1-S7** — the SAM pipeline stage names, in order: **S1 Discovery** (understand the feature,codebase, constraints) → **S2 Planning + RT-ICA** (generate a plan, gated by `dh:rt-ica`) → **S3Context Integration** (validate the plan against actual codebase state) → **S4 TaskDecomposition** (break the plan into executable tasks) → **S5 Execution** (implement tasks vialanguage-specific specialists) → **S6 Forensic Review** (verify each task against its acceptancecriteria) → **S7 Final Verification** (certify the feature meets the original requirements). Notevery stage requires human review — ARL-derived constraint analysis decides when to escalate, nota fixed checkpoint per stage. Canonical: `plugins/development-harness/AGENTS.md` ("How It Works").**Impact Radius** — the backlog-item section listing every system a proposed change affects(code, docs, configuration, CI, tests, agent instructions), written by `@dh:impact-analyst` beforeplanning. The feasibility gate and grooming staleness checks read this section to size a change'sblast radius; an item using an older grooming template may have this content under a `Resources`section instead — readers of the primary key fall back to it. Canonical:`plugins/development-harness/agents/impact-analyst.md`.

Frequently asked questions