enrich-work-item
Enriches an existing Epic, Feature, User Story, or Task into the host team's structured format using type-specific enricher prompts (emoji sections, scope blocks, complexity drivers, ASCII diagrams). Use when the user runs /enrich-work-item, asks to "enrich a ticket", "enrich this issue", "format this user story", "polish this feature", "structure this epic", or provides a path, URL, or pasted text plus work-item type. For raw title + requirement bullets from scratch, use generate-work-item instead. For plain-language narrative inside enricher sections, this skill delegates a sub-pass to generate-plain-language-documentation after enricher assembly.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- enrich-work-item
- license
- MIT
- description
- Enriches an existing Epic, Feature, User Story, or Task into the host team's structured format using type-specific enricher prompts (emoji sections, scope blocks, complexity drivers, ASCII diagrams). Use when the user runs /enrich-work-item, asks to "enrich a ticket", "enrich this issue", "format this user story", "polish this feature", "structure this epic", or provides a path, URL, or pasted text plus work-item type. For raw title + requirement bullets from scratch, use generate-work-item instead. For plain-language narrative inside enricher sections, this skill delegates a sub-pass to generate-plain-language-documentation after enricher assembly.
02 资源文件 4
- 参考文档manifest.json1.4 KB
- 参考文档references/examples/example-epic.md1.4 KB
- 参考文档references/examples/example-feature.md1.1 KB
- 参考文档references/examples/example-user-story.md1.2 KB
03 SKILL.md 正文
Enrich Work Item
Conductor for applying the enricher pattern to an existing work-item description. Load references as each phase needs them.
References (start at ../../common/workflows/enrich-work-item.md):
../../common/workflows/enrich-work-item.md— type map, enricher routing, artifacts paths.../../common/templates/output-formats.md— per-type output contracts.../../common/templates/— read-only shape contracts. Validate enriched output against the matching template before presenting.../../common/workflows/enrichers/— authoritative prose rules:epic-enricher.prompt.md,feature-enricher.prompt.md,work-item-enricher.prompt.md
../../common/specs/enrich-work-item/— spec forms for optional analysis artifacts../references/examples/— illustrative dummy outputs (content reference only; shape contract is./references/canonical/).../../references/decomposition-rules.md— hierarchy, story-point heuristic.../../references/ticket-structure.md— draft file constraints.../../common/providers.md— neutral artifact contract and provider translations.../generate-plain-language-documentation/references/integration-notes.md— prose polish sub-pass (PHASE 4).
Not in scope: generating a raw work item from a title alone — use generate-work-item first.
PHASE 0 — COLLECT INPUTS
Gather inputs one at a time via the host UI. Each step: brief purpose, required vs optional.
| Input | Required | Purpose |
|---|---|---|
source |
yes | url | local path | pasted text — the material to enrich |
work_item_type |
yes | epic | feature | user-story | task |
parent |
when type ≠ epic | Parent id or tracker link for hierarchy context |
attachment |
no | Extra doc URL or path |
Accept /enrich-work-item flags or conversational inference (see Examples).
Normalize type → enricher + the tracker kind (tracker_describe kinds) per pipeline.md.
Every tracker read and write goes through the harness gateway (tracker_* tools); never call a
tracker's own tools. Ask harness document path for every document's and draft's path
(../../references/document-layout.md).
PHASE 1 — INGEST
- Load
source:- Tracker id or link — read the id with the tracker's
idspatterns (tracker_describe), thentracker_get_work_item; read its artifacts withtracker_list_artifacts, parse the description for linked docs/URLs/paths, and fetch that content intosupplementary_context. Set Descrição Original from the item'sdescriptionverbatim. - path — read local markdown; capture body verbatim.
- url (not a tracker link) — fetch external doc; capture description verbatim.
- text — treat pasted content as the description to enrich.
- Tracker id or link — read the id with the tracker's
- If
parentprovided:tracker_get_work_item— capture parent chain for context and filename prefix. Whensourceis a tracker item andparentomitted, use itsparent_id. - If
attachmentprovided: read or fetch; fold into enricher context (dedupe against tracker artifacts already ingested). - Preserve Descrição Original text exactly for the enricher output section.
PHASE 2 — ROUTE ENRICHER
Read the common output contract and matching enricher:
work_item_type |
Enricher |
|---|---|
epic |
enrichers/epic-enricher.prompt.md |
feature |
enrichers/feature-enricher.prompt.md |
user-story |
enrichers/work-item-enricher.prompt.md |
task |
enrichers/task-enricher.prompt.md |
Load enricher prompts from ../../common/workflows/enrichers/.
Follow enricher Contexto Obrigatório when host monorepo docs exist; skip gracefully when absent.
For user-story sources, classify Bug vs User Story per enricher §1 keywords when applicable.
PHASE 3 — WRITE SPEC (optional artifacts path)
When the item will be persisted, fill the matching common spec-*.md into the path
harness document path --type spec --item <key> prints (--new before the item exists). Skip when
the destination is chat-only.
PHASE 4 — ENRICH
Apply the enricher rules to produce the exact output format defined in enricher §4 (Epic/Feature) or §6 (work item). The enriched body IS the deliverable — emoji sections, scope blocks, complexity drivers, ASCII diagrams as the enricher specifies.
Plain-language sub-pass: Read
../generate-plain-language-documentation/references/integration-notes.md § enrich-work-item; polish
narrative paragraphs inside sections (not emoji headings; not Descrição Original). Glossary-verify
when locale is pt-BR.
Run the enricher Checklist de Auto-Revisão before presenting.
Compare shape against ../../common/templates/canonical-<type>.md (read-only contract; do not
edit). Use ./references/examples/example-<type>.md only for illustrative content patterns.
Present the enriched markdown in chat. Suggest a title outside the markdown block when the enricher requires it (work-item enricher).
PHASE 5 — GATE & DESTINATION
── GATE — Write the enriched body as a draft ticket (harness document path --type ticket,
in Tickets/Ready/), show it with harness workflow show --artifact <draft>, then ask
harness decision present --gate publish-items with the draft as --artifact. Silence is not
approval.
The destination is the selected tracker. Write nothing anywhere else unless the user asks for chat-only output.
PHASE 6 — PERSIST
Write through the gateway per ../../common/providers.md: an existing item with
tracker_update_work_item (description — the approved draft's body, word for word — and title
when it changed), a new item with tracker_create_work_item. With the local tracker, creating the
item turns its draft into the tracked ticket. Artifacts use only provider, string provider_id,
and string parent_id.
PHASE 7 — VERIFY
Read the item back with tracker_get_work_item and verify its parent and description. Update the draft's neutral
provider identity fields when creating new items.
On failure: STOP and report.
Append checkpoint to open Agent_Sessions/ record when the host keeps a session artifacts path.
Operating rules
- Enricher is authoritative — output matches enricher § output format, not generate-work-item's uniform three-part layout.
- Verbatim original — always include Descrição Original from ingest (work-item description only; attachment text feeds enrichment context, not Descrição Original).
- WHAT not HOW — per enricher quality rules.
- One gate before persistence writes.
- Locale — Português BR for host-team enrichers unless the source is clearly another language.
Examples
Slash command:
/enrich-work-item --type feature --source Tickets/Ready/6800-oauth-login.md --parent 6800
Conversational trigger:
Enrich this user story — [pasted description]
→ Infer work_item_type: user-story, source: text, run enricher pipeline.
Tracker source:
Format issue 6871 in the team template
→ source: url (tracker item), read it with tracker_get_work_item (work item + artifacts +
description refs), enrich, present for approval.
04 同仓库更多 Skills
validate-artifact
Validate a single agile artifact (Epic, Feature, User Story, or Task) against the toolkit rule set. Use when the user asks to "validate this story/feature/epic", "check this ticket", "is this artifact ready?", or provides a local draft path or provider item and wants a quality report. Accepts a local draft or a tracker work item. Runs all checks non-blocking and emits a terminal report + persisted report. One artifact per invocation.
split-story
Lateral story-sizing skill. Takes a single User Story and determines if it should be split, how many sub-stories to create, and what split pattern to use — then drafts sub-stories and hands them off. Use when the user asks "split this story", "is this story too big?", "analyze this story for sizing", or provides an artifacts path / tracker id / file path / raw text and wants a split recommendation. One story per invocation.
research-decision
Research a product, market, domain, competitor, user, or technical question in service of a named decision, producing a cited decision brief. Use when planning depends on current evidence rather than more ideation.
product-spec
Distill an idea, brief, PRD, UX contract, architecture spine, issue, or mixed notes into a compact canonical product contract with stable capabilities and companions. Use before backlog decomposition when intent is defined; update or validate an existing product spec through the same skill.
product-requirements
Create, update, or validate a right-sized Product Requirements Document with stable requirements, explicit scope, user journeys where useful, and measurable outcomes. Use for multi-person or multi-epic alignment; skip it when a concise product spec is enough.
product-brief
Create, update, or validate a concise product brief that captures a clear concept, its users, value, scope, and success criteria. Use when the user wants a one- or two-page product narrative before a PRD or product spec.