CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

factory-run

Run one factory triage run on the factory VM: settle the fixed batch of items in the watcher's message, triage, fold reports into fix branches already working on the same problem, start one Builder branch per new fix group without waiting for it, record each returned branch result, reply, and finish. Use whenever a message starts "Handle the new factory events", "Continue the current factory run", or "Review <PR url> for the agent-native factory".

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly executable operational runbook: every step carries exact commands, thresholds, and recovery paths, and the batch workflow has real validation checkpoints. Its weaknesses are at the margins — length with some deliberate redundancy, inlined sections that could live in reference files, one orphaned bundle file (babysit-round.md), and one ambiguously prefixed reference path (replies.md).

DimensionReasoningScore

Conciseness

There is no explanation of concepts Claude already knows — every line is an operational rule, command, or boundary — so it is well above the 'unnecessary explanation' anchor at 3. But at 686 lines it is not 'every token earns its place': critical rules are deliberately repeated ("Never wait for a fix branch, or end your turn to wait for one" appears in the Never list, step 4, and step 6) and a few multi-clause sentences (the `.ownership` rule in "Duplicate and competing PRs") could be tightened, matching anchor 4.

4 / 5

Actionability

Fully executable throughout: a tools table with exact commands and flags (`factory-state report upsert "<key>" --json '<fields>'`), copy-paste-ready bash with realistic JSON payloads, prompt templates for fix and refactor branches, numeric gates ("a join under 70 doesn't attach"), exit-code handling ("exit 3 at the cap"), and a 10-minute timeout rule for branch starts. Common cases for every item kind are covered with specific handling.

5 / 5

Workflow Clarity

Clear numbered sequence (steps 1–6: read the message, skip handled, triage and fold, start branches, record and close the loop, finish) with explicit validation and recovery: the finish checklist ("every claimed report has a digest card and every 👀 you added in live mode has its reply"), error branches for failed workers, launch-timeout recovery ("run `factory-branch list` and use the branch with this name"), and pre-action checks for the batch/destructive operations (duplicate check via `factory-state active` before any branch; "close nothing without both" before closing a PR). The batch-operation cap does not apply because validation checkpoints are present.

5 / 5

Progressive Disclosure

References are one level deep and mostly well-signaled at point of use ("Read [confidence.md](references/confidence.md) before the first triage", fix-branch.md linked at each use, pr-review.md for review workers). But measured against the actual bundle: references/babysit-round.md is never reachable from the body, `references/replies.md` is cited without its `community-prs/` prefix and so dangles in this bundle, and long sections (Pull requests, Refactor findings) are inlined in SKILL.md rather than split — good structure, but more than minor gaps keeps it below the anchor-5 'overview with appropriately split content'.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: it names the executor, the environment, every action in the run lifecycle in order, and gives an explicit 'Use whenever' clause with the three exact trigger phrases. It is dense without padding and in third-person imperative voice, so no guideline penalties apply.

DimensionReasoningScore

Specificity

The description enumerates the complete action lifecycle — "settle the fixed batch of items in the watcher's message, triage, fold reports into fix branches already working on the same problem, start one Builder branch per new fix group without waiting for it, record each returned branch result, reply, and finish" — seven concrete actions with comprehensive coverage, matching the top anchor rather than the 'minor gaps in coverage' anchor below.

5 / 5

Completeness

Both halves are explicit: the "what" is the full run lifecycle ("Run one factory triage run on the factory VM: settle … reply, and finish") and the "when" is a concrete trigger clause ("Use whenever a message starts …") with three quoted phrases. This clearly matches the 'both what AND when with concrete trigger phrases' anchor, not the 'when could be more explicit' anchor at 4.

5 / 5

Trigger Term Quality

It quotes the exact invocation phrases — "Handle the new factory events", "Continue the current factory run", "Review <PR url> for the agent-native factory" — which are the literal message openings a caller says, enumerating all three modes exhaustively. Since the trigger vocabulary is fixed by the watcher, this is complete coverage, above the 'a few natural terms missing' anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is pinned to "factory triage run", "the factory VM", "Builder branch", and "the agent-native factory", with triggers that are literal message prefixes no other skill would match. Conflict risk with sibling feedback skills (review-latest-feedback, review-prs, community-prs) is minimal because those are invoked by different message formats.

5 / 5

Total

20

/

20

Passed

Validation

68%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (687 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

11

/

16

Passed

Repository

BuilderIO/agent-native

Path

.agents/skills/factory-run/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.