Pattern miner: Add repo-qa-assistant curated pattern: slash-command Q&A agent

[github-actions]

Mined pattern

Repositories/files mined:

• githubnext-agentics/files/workflows/repo-ask.md
• githubnext-agentics/files/workflows/q.md
• githubnext-agentics/files/workflows/archie.md
• Confirmed as a recommended, documented pattern (not just recurring code) in github-gh-aw/files/.github/aw/workflow-patterns.md ("Prefer slash_command when the action is conversational... the user may pass arguments in the comment body") and github-gh-aw/files/.github/aw/patterns.md (ChatOps: "slash-command driven, human-in-the-loop automation in issues or pull requests").

Recurring shape (3 upstream workflows):
All three (repo-ask, q, archie) are conversational, on-demand assistants that:

• trigger on slash_command (optionally paired with a reaction for immediate acknowledgement)
• run with read-only/minimal permissions (permissions: read-all or explicit contents/issues/pull-requests: read)
• use tools.github.min-integrity: none so they can read any issue/PR regardless of author trust, since they only answer questions and never act on untrusted content
• investigate via bash/web-fetch/github tools rather than making repository changes
• respond with a single add-comment (capped at max: 1), never create-pull-request or other write outputs

This satisfies the "at least two upstream workflows demonstrating the same shape" bar, and is additionally corroborated by explicit upstream documentation recommending the slash_command-driven ChatOps pattern for conversational actions.

Why the existing library did not cover this:

• pr-iteration-loop is PR-focused, long-running iteration on a draft PR — not read-only Q&A.
• repo-maintainer is a broad, proactive scheduled maintenance role with write outputs (issues + PRs) — not a read-only, on-demand answer-and-comment assistant.
• No existing archetype captures the "slash-command triggered, read-only investigation, single comment answer" shape, and no trigger-combo/tip in current-library.json documents the min-integrity: none + read-only + single add-comment combination for this use case.

What changed in patterns/:

• Added patterns/archetypes/repo-qa-assistant.json — new curated archetype (success_rate: null, count: 0, top_repos: []) with slash_command trigger, add-comment safe output/tool, role-steps prompt style, and tips capturing the reaction-ack, read-only-permissions, min-integrity: none, add-comment max: 1, and scoped-answer patterns observed upstream.
• Appended repo-qa-assistant to archetypes in patterns/manifest.json.
• Added the repo-qa-assistant runtime rendering definition (icon, capabilities, permissions, github_toolsets, prompt body) to patterns/workflow-generation.json.

No other files were touched; no scan/generation scripts were run.

Validation:

• npm test — 320 tests passed (18 test files), including test/patterns.test.js and test/generate-patterns.test.js. One unrelated ENOENT warning from vitest's GitHub Actions summary reporter trying to write to a runner temp path that doesn't exist in this sandbox; it does not affect test results.
• npm run build — succeeded, producing dist/patterns/archetypes/repo-qa-assistant.json and the updated dist/patterns/manifest.json / dist/patterns/workflow-generation.json.

Candidates deliberately left out:

• plan.md (Agentic Planner) — only one upstream example with no corroborating "planning discussion" pattern doc; would need a second example.
• dictation-prompt.md — a narrow, single-purpose voice-dictation prompt generator with no second upstream example or documented pattern.
• sub-issue-closer.md / issue-arborist.md — both overlap with the existing issue-hierarchy-manager archetype (parent/sub-issue linking and closing), so no new archetype was warranted; left the existing archetype's link-sub-issue/update-issue tips untouched since upstream evidence did not add anything new.
• duplicate-code-detector.md / large-file-simplifier.md / code-simplifier.md — already covered by the existing code-health-auditor and performance-nut archetypes.

Generated by Pattern Miner · copilot · auto · 93.6 AIC · ⌖ 12.2 AIC · ⊞ 8.5K · ◷

[github-actions]

Reviewer kind: matt-pocock (data-only JSON pattern addition, TS/generation-logic focused).

Found two correctness gaps between the new repo-qa-assistant archetype data and how src/js/workflow.js actually renders workflows:

1. capabilities.web_fetch in workflow-generation.json isn't a recognized key in inferCapabilities() — it silently has no effect, so the generated tools block won't include web-fetch despite the prompt instructing the agent to use it.
2. The archetype's tips describe setting min-integrity: none, but the corresponding min_integrity field is missing from the workflow-generation.json entry, so the generated frontmatter won't include it.

Both are inline comments above. No blocking issues beyond that — the rest of the archetype/manifest wiring looks consistent with existing patterns.

Generated by Specialist PR Review for #270 · copilot · auto · 37.5 AIC · ⌖ 5.74 AIC · ⊞ 8.1K

[github-actions]

matt-pocock: capabilities.web_fetch isn't read anywhere in src/js/workflow.js — inferCapabilities() only maps pre_steps, bash, github_toolsets, browser, network (see lines 48-57). This key is silently dropped, so generated workflows will never emit a web-fetch tool despite step 2 of the prompt body explicitly instructing the agent to "Investigate the repository... using bash and web-fetch as needed". Either rename to browser/an existing recognized capability, or add web_fetch handling to inferCapabilities/generateWorkflowFile so the tool actually gets included.

[github-actions]

matt-pocock: This tip says "Set tools.github.min-integrity: none", but there's no corresponding "min_integrity": "none" field added to the repo-qa-assistant entry in patterns/workflow-generation.json (compare status-report, which does set min_integrity). Without it, generateWorkflowFile won't emit min-integrity: none in the frontmatter, so the generated workflow won't actually match this tip's stated behavior.