AGENT SKILL

surface-extraction

Runs the extractors, normalizes the raw surfaces and fingerprints the result, so the site-map run has an evidence-backed inventory of what the app exposes. Use when readiness passed and modeling has not started.

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
surface-extraction
metadata
{ "cacheable": "false", "model_tier": "fast", "paqad-meta": "skill.meta.yaml", "output_format": "json" }
description
Runs the extractors, normalizes the raw surfaces and fingerprints the result, so the site-map run has an evidence-backed inventory of what the app exposes. Use when readiness passed and modeling has not started.

02 资源文件 3

03 SKILL.md 正文

What It Does

Produces the raw surface inventory the rest of the workflow builds on: every page, screen, endpoint, or command the extractor can prove from the code, each with resolving file:line evidence, deduped, and folded into a stable fingerprint. Mostly deterministic, the engine does the scanning; this skill orchestrates it and confirms the output is clean.

Use This When

After readiness passes and before modeling. It is the bridge from "the app is mappable" to "here is what the app exposes, with proof".

Inputs

  • The readiness verdict and detected extractor from site-map-readiness.
  • The project source the extractor scans (route files, command programs, endpoint handlers).
  • Read references/extraction-evidence.md before accepting or excluding a surface.

Procedure

Extraction is deterministic: the engine owns it. Do not re-scan the code by hand.

  1. Run paqad-ai sitemap run; it runs the extractors, dedupes, unions evidence, and computes the extraction fingerprint.
  2. Read the extraction.json in the run bundle: each extracted surface carries its kind, a file:line, and a derivation (static | convention).
  3. Confirm every surface's evidence resolves and no surface is a duplicate under a different label; flag any the engine could not ground rather than passing it through.

Output Contract

  • A JSON object { surfaces: [{ id, kind, evidence, derivation }], fingerprint, blocked_checks: [...] }.
  • Every surfaces[] entry carries at least one resolving file:line evidence pointer.
  • fingerprint is present and stable across identical inputs.

Escalate / Stop Conditions

  • Stop and record a blocked_checks entry when the extractor cannot read the app shape; never invent a surface to fill the gap.
  • Warn when the extraction is empty on a non-trivial app: that is a coverage gap, not a clean map.
  • Do not promote a convention-derived surface to static confidence without resolving evidence.

Resources

  • references/extraction-evidence.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