Catalog
BuilderIO/factory-human-digest

BuilderIO

factory-human-digest

Experimental workflow for summarizing work that still needs human judgment across configured pull requests, issues, feedback, errors, and delivery signals. Use for a human decision queue or bounded review.

v1.0LATEST
NewUpdated Sep 24, 2026

Factory Human Digest

Start with the Factory guide for workflow setup and configuration.

Read .agent-factory/config.yaml and apply the optional skill_prompts.factory-human-digest entry as additional project guidance. Inspect only the repositories and sources it authorizes.

Choose the scope

For a manual run with no narrower request or workflow settings, include all configured source categories, use the last 7 days, and report at balanced granularity. A user can narrow or expand the request in ordinary language, for example, “PRs only, last 30 days, detailed” or “everything from this week, brief.” Use configured repository and source boundaries even when the requested time window or category changes. For scheduled runs, use workflows.human-digest from the config.

Categories can include pull requests, issues, feedback, errors, telemetry, and stalled or failed delivery work. A category filter selects records to inspect; it does not expand access to another project or integration.

Find items that need a person

Read configured sources and repositories completely for the selected window. Follow pagination and record the actual dates, filters, counts, and any source that was unavailable or truncated. Include items held outside the normal agent-handled flows, such as:

  • pull requests waiting for human review, approval, a merge decision, or product judgment;
  • issues, feedback, or errors held for missing context, unclear intent, risk, conflicting evidence, or a decision outside the configured automation rules;
  • new answers to information requests that have not yet been re-triaged;
  • recurring incidents, UX concerns, or delivery work that stopped without a verified resolution or safe authorized next step.

Exclude work that has a verified terminal outcome unless it reopened, recurred, or received new information during the window. A label or agent summary alone does not prove an item is resolved. If the source cannot distinguish pending from resolved, report that uncertainty instead of guessing.

Group patterns and preserve evidence

Group related items by the underlying user impact or failure pattern, not by similar words alone. For each group, preserve the date range, count of distinct records, source links, representative evidence, and the human decision needed. Separate event volume from affected people or sessions unless the source has a reliable identity definition. Keep unrelated reports separate even when one summary would be shorter.

Use the configured granularity, or balanced by default:

  • Brief: top groups, why each needs a person, and links to the source items.
  • Balanced: grouped summaries, representative evidence, and a linked list of each item needing a decision.
  • Detailed: one entry per item with relevant context, prior handling, evidence, and the exact decision or next step.

Report; do not take the actions

Start with coverage: window, categories, repositories, sources, filters, and pagination status. Then report recurring themes and the decision queue. For each entry include links, why the normal flow did not handle it, prior replies or dispositions, the decision required, and an owner or due date only when the source provides one.

This workflow is read-only. Do not reply, approve, merge, assign, close, change status, or notify people from the digest. Route any requested action through its owning Factory workflow and its separate configured policy. Missing or partial source data must remain visible in the report; it is never evidence of an empty queue.

Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

88

Quality

82

Clarity

84

Completeness

72

Summary

This skill guides an AI agent to read configured repository sources (PRs, issues, feedback, errors, telemetry) and produce a human decision queue summarizing items that require human judgment. It operates as a read-only digest aggregator, applying time-window and category filters, grouping patterns by user impact, and reporting findings without taking actions on the sources.

Detected Capabilities

file read (.agent-factory/config.yaml)external API read (GitHub/GitLab/issue tracker sources via configured repositories)pagination and record traversaldata aggregation and groupingstructured report generation (text output)

Trigger Keywords

Phrases that agents use to match this skill to user intent.

human review queuepull request digestissue triage summarydecision backlogworkflow digestcode review pendingincident roundup

Use Cases

  • Monitoring pull requests awaiting human review or merge decisions
  • Aggregating issues and feedback that automation cannot resolve
  • Tracking recurring incidents and errors requiring triage
  • Creating bounded decision queues for code review and product judgment
  • Periodic summaries of stalled delivery work and failed automation

Quality Notes

  • Excellent scope definition: the skill explicitly forbids write operations ('read-only' enforced multiple times) and clarifies that it does not reply, approve, merge, assign, or close items
  • Clear authorization boundary: explicitly restricts inspection to 'repositories and sources it authorizes' via config.yaml, preventing unauthorized access
  • Well-handled edge cases: distinguishes pending from resolved items, reports missing data rather than guessing, separates event volume from affected people/sessions, acknowledges pagination and unavailable sources
  • Good precedent handling: instructs agent to preserve evidence, keep unrelated reports separate, and note prior dispositions—reduces duplicate reporting
  • Three granularity options (brief/balanced/detailed) provide flexibility while keeping instructions concrete
  • Clear instructions on what to exclude (terminal outcomes) and include (held items outside normal flows) reduces ambiguity
  • References configuration entry (skill_prompts.factory-human-digest) for project-specific guidance, enabling customization without changing core logic
Model: claude-haiku-4-5-20251001Analyzed: Sep 24, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use BuilderIO/factory-human-digest in your dev environment

Command Palette

Search for a command to run...