AGENT SKILL

site-map-assembly

Drives the compile verb that folds the surface, transition and guard layers into app-map.yaml, and resolves merge conflicts against the committed content without overwriting curated entries. Use when modeling and flow tracing are done and verification has not run.

License 许可
MIT
所属仓库
Eliyce/paqad-ai
最近更新
2026-11-13
Stars
★ 8
Forks
0

01 前言 Front Matter

name
site-map-assembly
metadata
{ "cacheable": "false", "model_tier": "fast", "paqad-meta": "skill.meta.yaml", "output_format": "json" }
description
Drives the compile verb that folds the surface, transition and guard layers into app-map.yaml, and resolves merge conflicts against the committed content without overwriting curated entries. Use when modeling and flow tracing are done and verification has not run.

02 资源文件 3

03 SKILL.md 正文

What It Does

Compiles the modeled layers (surfaces, transitions, guards, areas) into the single app-map.yaml of record, and reconciles them against what is already committed. The compile is the engine's; this skill drives it and resolves conflicts by preserving locked human-curated content rather than clobbering it.

Use This When

After modeling and flow tracing, once the layers are ready to become one map. It precedes verification and publication.

Inputs

  • The run bundle's modeled layers (surfaces, transitions, guards).
  • The stored docs/site-map/app-map.yaml, if one exists.
  • Read references/merge-policy.md before resolving any conflict.

Procedure

The compile and its schema validation are the engine's; do not hand-assemble the YAML.

  1. Run paqad-ai sitemap run; it compiles the layers into app-map.yaml and validates the result against the app-map schema.
  2. Read the reconciliation: entries added, entries the committed map already covers, and any conflict between a fresh layer and a curated entry.
  3. Resolve each conflict per the merge policy: locked, human-curated content wins over a re-derived layer; a genuine change is surfaced, not silently overwritten.

Output Contract

  • A JSON object { compiled: true, app_map_path, added: [...], preserved: [...], conflicts: [...] }.
  • compiled is true only when the engine's schema validation passed.
  • Every conflict names the curated entry it preserved and why.

Escalate / Stop Conditions

  • Stop when schema validation fails; a map that does not validate is not written.
  • Do not overwrite a locked, human-curated entry to resolve a conflict: surface the change for a human decision.
  • Do not hand-edit app-map.yaml outside the compile; the engine owns its shape.

Resources

  • references/merge-policy.md
  • agents/openai.yaml

04 同仓库更多 Skills

Eliyce
Eliyce/paqad-ai

sample-skill

Sample bundled skill fixture

★ 8
Eliyce
Eliyce/paqad-ai

processing-invoices

Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.

★ 8
Eliyce
Eliyce/paqad-ai

processing-invoices

Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.

★ 8
Eliyce
Eliyce/paqad-ai

understand-idea

Chat and Claude Code: Step 1 of the discover journey: clarifies the goal, who benefits, success and constraints into the idea block. Use when the journey directs it to step 1, not directly.

★ 8
Eliyce
Eliyce/paqad-ai

size-work

Chat and Claude Code: Suggest a size for a ticket from comparable finished work, as a labelled suggestion the team still owns. Use it when someone asks "how big is this?", "roughly how much work is ABC-12?", or wants a backlog item sized. It finds the team's sizing scale at first use, picks two to five of the closest finished tickets with links, and gives a size or range with the drivers behind it and a confidence of low, medium or high, lowered and explained when the area's documents are template text. Every result is labelled a suggested size, never a date or a commitment. It writes nothing into the size field unless the user says "set it", and it refuses to overwrite an existing size unless the user asks to replace it. Produces the sizing block of the record.

★ 8
Eliyce
Eliyce/paqad-ai

refine-ticket

Chat and Claude Code: Improve one or more existing tracker tickets without losing the author's intent. Use it when someone wants a ticket read, diagnosed and tidied up ("this ticket is vague", "fix up ABC-12", "split this, it's too big"). It reads each ticket in full and snapshots it with its last-updated time, says what is wrong with evidence, and proposes a field-by-field before and after change set limited to summary, description, labels, parent, links and new child tickets on a split. It writes nothing until an explicit "apply it" bound to that exact change set, re-checks the ticket for conflicting edits just before writing, never replaces rich descriptions with plain text, never deletes or closes a ticket, and reads each ticket back after applying. Produces the existing and changes blocks of the record.

★ 8