prd-to-issues
Use to break a plan, spec/PRD, or the current conversation into a set of tracer-bullet tickets — each a narrow-but-complete vertical slice, declaring its…
Skill by KSriki
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ksriki-prd-to-issues
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/prd-to-issues
What's inside
- Skill name
prd-to-issues- Description
- Use to break a plan, spec/PRD, or the current conversation into a set of tracer-bullet tickets — each a narrow-but-complete vertical slice, declaring its blocking edges — published to the configured tracker. Triggers on "break this into issues/tickets", "turn the PRD into issues", "create the tickets", "slice this into work", "what's the dependency order". Do NOT use to write the product spec itself (`write-a-prd`, run before this), to map open DECISIONS for fuzzy work (`wayfinder`), or to run parallel agents on the tickets (`orchestrate-agents`, run after).
- License
- MIT
- Instructions
- 61 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# PRD → issues (tracer-bullet tickets) > Adapted from `mattpocock/skills` (MIT, `to-tickets`) — reimplemented in this repo's style. ## When to use this A settled plan/spec exists and you need **buildable tickets** in dependency order. Each ticket is a **tracer bullet**: a thin, complete path through every layer that's independently demoable — not a horizontal "do all the schema" slice. **Not this skill if:** the spec isn't written → `write-a-prd`. There are open *decisions* to resolve first → `wayfinder`. You're executing the tickets in parallel → `orchestrate-agents`. ## Procedure 1. **Gather context.** Work from the conversation; if given a reference (spec path, issue #/URL), fetch and read its full body + comments. 2. **Explore the codebase (optional).** Use domain-glossary vocabulary; respect ADRs; look for **prefactoring** — *"make the change easy, then make the easy change."* 3. **Draft vertical slices.** Tracer-bullet rules: - each slice cuts a **narrow but COMPLETE** path through every layer (schema · API · UI · tests) — **vertical, not horizontal**; - independently **demoable / verifiable**; - sized to a **single fresh context window**; - prefactoring first. - Each ticket **declares its blocking edges** (tickets that must finish first); no-blocker tickets can start immediately. - **Wide-refactor exception:** one mechanical change with large blast radius → sequence as **expand → migrate (in batches, each blocked by expand) → contract** (delete the old form, blocked by every migrate). If batches can't each stay green, share an integration branch that all block a final integrate-and-verify ticket. 4. **Quiz the human.** Present the breakdown as a numbered list; per ticket show **Title · Blocked by · What it delivers.** Ask: granularity right? blocking edges correct? merge or split any? Iterate until approved. 5. **Publish to the tracker** 〈GitHub/GitLab via native blocking / sub-issue links · **Beads**: `bd create "<title>" -p <prio>` per ticket + `bd dep add <child> <blocker>` per edge · or local files under `.scratch/<feature-slug>/issues/NN-slug.md`, numbered in dependency order〉. Apply **`ready-for-agent`** unless told otherwise (on Beads the label is unnecessary — membership in `bd ready` IS the signal). Work the **frontier** (any ticket whose blockers are all done; Beads computes it). **Do NOT close or modify any parent issue.** **Stacked PRs (GitHub, public preview since 2026-07):** a *dependent* ticket chain can ship as a **PR stack** — one PR per slice, each targeting the slice below, reviewed as focused per-layer diffs and merged bottom-up (remaining layers auto-rebase server-side). The blocking edges you declared here ARE the stack order; **expand → migrate → contract maps 1:1 onto a stack.** Independent (no-blocker) tickets stay separate PRs. See `gh stack --help` / the official guide — preview feature, don't hardcode syntax. ## Ticket template `# <NN> — <Title>` · **What to build** (end-to-end behavior, user's POV — not a layer list) · **Blocked by** (numbers/titles, or "None — can start immediately") · **Status: ready-for-agent** · checkbox acceptance criteria. Avoid file paths / code (same decision-snippet exception as `write-a-prd`). ## Definition of done - [ ] Slices are **vertical tracer bullets** — each complete + demoable, context-window-sized - [ ] **Blocking edges** declared; wide refactors sequenced expand→migrate→contract - [ ] Human approved the breakdown (granularity + edges) - [ ] Published in dependency order, **ready-for-agent**; no parent issue touched
From KSriki/agent-harness-template, MIT.
More from KSriki/agent-harness-template
- 0.565score
evolve-harness
KSriki
Use to turn a repeated correction, a recurring failure, or a researched new practice/trend into a durable change to the AGENT LAYER — a new or edited skill…
SkillAFreshness: AClaude Code +9 - 0.524score
grill-me
KSriki
Use to grill the user relentlessly about a plan, decision, or idea — a frontier-batched interview down the design tree (rounds of ready questions, each with a…
SkillBFreshness: BClaude Code +9 - 0.524score
eval-harness
KSriki
Use when building, running, or debugging evaluations for LLM or agent components: golden sets, regression evals, LLM-as-judge, rubric scoring…
SkillBFreshness: BClaude Code +9 - 0.524score
codebase-design
KSriki
Use to design or improve a single MODULE's interface — deciding where a seam goes, making code more testable / AI-navigable, or judging whether a module is…
SkillBFreshness: BClaude Code +9 - 0.524score
observability
KSriki
Use when instrumenting a service (structured logs, metrics, traces), defining SLOs or alerts, building a dashboard, or triaging a live production incident /…
SkillBFreshness: BClaude Code +9 - 0.524score
orchestrate-agents
KSriki
Use to ship a multi-part change by running several agents IN PARALLEL — fan-out across subagents, each isolated in its own git worktree, then verify-and-merge.
SkillBFreshness: BClaude Code +9 - 0.524score
ci-cd
KSriki
Use when setting up or debugging a CI pipeline, adding a workflow or gate, promoting a build through environments, deploying, cutting a versioned release, or…
SkillBFreshness: BClaude Code +9 - 0.524score
review-pr
KSriki
Use when preparing your own change for review (self-review, commit hygiene, writing the PR description) or when reviewing someone else's pull request for…
SkillBFreshness: BClaude Code +9 - 0.520score
graphify
KSriki
Use for STRUCTURE and relationship questions about a codebase/corpus — how X reaches Y, what depends on what, blast radius, architectural hubs — and to build…
SkillBFreshness: BClaude Code +9 - 0.499score
harness-help
KSriki
Use when the user asks how to customize the harness or where something goes: "how do I add a rule / gotcha / skill", "where do I change the gate", "what file…
SkillBFreshness: BClaude Code +9 - 0.474score
handoff
KSriki
Use to compact the current session into a standalone handoff document so a FRESH agent (or you, later) can resume the work without the transcript.
SkillCFreshness: CClaude Code +9 - 0.474score
architecture-patterns
KSriki
Use when making an architectural or design decision: choosing between patterns, deciding sync vs async, picking a caching or data strategy, deciding whether…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 17, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/KSriki/agent-harness-template
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from KSriki
- 0.565score
evolve-harness
KSriki
Use to turn a repeated correction, a recurring failure, or a researched new practice/trend into a durable change to the AGENT LAYER — a new or edited skill…
SkillAFreshness: AClaude Code +9 - 0.524score
grill-me
KSriki
Use to grill the user relentlessly about a plan, decision, or idea — a frontier-batched interview down the design tree (rounds of ready questions, each with a…
SkillBFreshness: BClaude Code +9 - 0.524score
orchestrate-agents
KSriki
Use to ship a multi-part change by running several agents IN PARALLEL — fan-out across subagents, each isolated in its own git worktree, then verify-and-merge.
SkillBFreshness: BClaude Code +9 - 0.524score
eval-harness
KSriki
Use when building, running, or debugging evaluations for LLM or agent components: golden sets, regression evals, LLM-as-judge, rubric scoring…
SkillBFreshness: BClaude Code +9 - 0.524score
observability
KSriki
Use when instrumenting a service (structured logs, metrics, traces), defining SLOs or alerts, building a dashboard, or triaging a live production incident /…
SkillBFreshness: BClaude Code +9 - 0.524score
review-pr
KSriki
Use when preparing your own change for review (self-review, commit hygiene, writing the PR description) or when reviewing someone else's pull request for…
SkillBFreshness: BClaude Code +9
Cite this page
prd-to-issues skill. Agent Mart. https://agentmart.dev/skills/ksriki-prd-to-issues (last updated 2026-10-24)