plugins/codex-sdlc/skills/artifact-lookup/SKILL.md
Search and navigate SDLC artifacts by topic, type, phase, or tag using the aiwg index CLI
npx skillsauth add jmagly/aiwg artifact-lookupInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Search and navigate SDLC artifacts using the artifact index.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
This skill wraps the aiwg index CLI commands to provide natural language artifact discovery. Agents and users can query, navigate dependencies, and check project health without knowing the exact CLI syntax.
When the user asks to find artifacts by topic, type, or phase:
# By keyword
aiwg index query "authentication" --json
# By type
aiwg index query --type use-case --json
# By phase
aiwg index query --phase testing --json
# By tag
aiwg index query --tags security,auth --json
# Combined filters
aiwg index query "login" --type use-case --phase requirements --json
Parse the JSON output and present results in a readable summary:
When the user asks what depends on or references an artifact:
# Both directions
aiwg index deps .aiwg/requirements/UC-001.md --json
# Upstream only (what this depends on)
aiwg index deps .aiwg/requirements/UC-001.md --direction upstream --json
# Downstream only (what depends on this)
aiwg index deps .aiwg/requirements/UC-001.md --direction downstream --json
Present the dependency tree in a readable format:
When the user asks about project health or artifact stats:
aiwg index stats --json
Summarize:
When the user creates new artifacts or asks to refresh:
aiwg index build
Report what changed (new, updated, unchanged counts).
--archive-answer flagPass --archive-answer to persist the query result as a structured artifact instead of (or in addition to) displaying it in chat:
artifact-lookup "authentication flow" --archive-answer
artifact-lookup --type use-case --archive-answer --tags auth,security
When this flag is present, after presenting results the skill invokes archive-answer with:
title derived from the query stringcontent set to the formatted result summarysource-query set to the original query expressiontags forwarded if providedWithout the flag, the skill still offers archival automatically when it detects a substantive result (3+ matching artifacts with meaningful relevance scores, or a dependency tree with 5+ nodes). In that case it asks: "This looks like a useful finding. Archive it? (y/n)"
Archived answers land in .aiwg/working/answers/ and are picked up by the next aiwg index build run.
Always present results as structured summaries, not raw JSON dumps. Example:
Found 3 artifacts about "authentication":
1. UC-001: User Authentication (requirements, score: 0.95)
Path: .aiwg/requirements/UC-001.md
Tags: auth, security
2. ADR-001: JWT Token Strategy (architecture, score: 0.82)
Path: .aiwg/architecture/adr-001.md
Tags: auth, architecture
3. TP-001: Auth Test Plan (testing, score: 0.75)
Path: .aiwg/testing/tp-001.md
Tags: auth, testing
aiwg index build must have been run)data-ai
Report which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first. Runs via `aiwg corpus radar-status`.
data-ai
Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue table, and per-radar rationale snippets. Runs via `aiwg corpus radar-report`.
testing
Scaffold radar/freshness sidecars for research-corpus REFs. Pulls title/authors from the citation sidecar and GRADE from the analysis doc, defaults the refresh cadence from GRADE and the cluster from a corpus-local map, and stamps documentation/radar/REF-XXX-radar.md. Runs via `aiwg corpus radar-init`.
data-ai
Compute an entity's publication trajectory — per-year paper counts, topic drift, hot-streak detection (≥3 consecutive A-grade years), and career phase. Runs via `aiwg corpus profile-temporal`.