CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

factory

Deliver changes through the software factory: take over, continue or hand off a task or backlog, work in the factory, coordinate specialist writers and independent verifiers through ready plans and delivery, launch one explicit assignment, or inspect a task's delivery and exception state.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

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.

The body is an exceptionally actionable, well-sequenced orchestration procedure with explicit validation and recovery at every stage, and its bundle references are real, clearly signaled, and one level deep. Its weaknesses are mild: a few overloaded mega-paragraphs that could live in reference files, keeping the entrypoint from being a true overview.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence throughout — no basic concepts are explained, and nearly every token carries operational contract ('exit 75, which means retry later, not failure'; 'Corrections consume the task's allowance, failed ones included'). Not 5: the mega-sentences in steps 6, 8 and 9 cram edge cases and escalation rules into single paragraphs that could be tightened or offloaded to the references, a mild form of over-explanation.

4 / 5

Actionability

Fully executable guidance: exact command templates with every flag ('factory.py admit --task TASK --line LINE --goal GOAL --repo /absolute/repo --acceptance REFERENCE'), precise failure semantics (exit 75, 'at zero, launch refuses further corrections'), bounded escalation rules ('three per task'), and concrete fallbacks ('reset a writer's checkout, then launch the replacement under a new ID').

5 / 5

Workflow Clarity

Steps are explicitly sequenced (numbered 1–9 under a router that says 'pick the step that matches the user's intent and execute only that step') with validation checkpoints and feedback loops everywhere: verify the writer's commit, route findings to correction jobs, re-verify with --from-writer, release judgment, and a final acceptance judgment. Error recovery is explicit for every failure mode (dirty worktree reset, brief-known-wrong cancel, non-convergent task escalation to architect then judge).

5 / 5

Progressive Disclosure

All four referenced files exist and are one level deep with clear purpose statements and markdown links — [the command reference](references/commands.md), [the role catalog](references/roles.json), [the ready-plan reference](references/ready-plan.md), [the delivery reference](references/delivery.md) — and command I/O contracts, role definitions, plan format and delivery process are appropriately split into them. Not 5: the body itself is not an overview; it inlines dense procedural manuals (the correction/allowance/judge escalation machinery in step 8, rebase-conflict resolution in step 9) whose level of detail matches what the references already carry, rather than summarizing and linking.

4 / 5

Total

18

/

20

Passed

Description

71%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.

The description is a dense, third-person enumeration of the skill's concrete capabilities with strong specificity, but it omits any explicit 'use when' trigger guidance, which both caps completeness and weakens its value for skill selection. Adding a trigger clause with natural user phrases would lift the two lowest dimensions without touching the strong 'what' content.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to deliver, take over, continue or hand off a change or backlog through the software factory, or to check a task's delivery or exception state.'

Include a few more natural user synonyms alongside the internal terms — e.g. 'open/review/merge the PR', 'run a verification', 'check task status' — so the description matches how users actually phrase requests.

Trim internal jargon ('work in the factory', 'ready plans', 'exception state' as a bare noun phrase) in favor of user-visible language, since trigger matching happens on user wording.

DimensionReasoningScore

Specificity

Lists seven-plus concrete actions — 'Deliver changes', 'take over, continue or hand off a task or backlog', 'coordinate specialist writers and independent verifiers', 'launch one explicit assignment', 'inspect a task's delivery and exception state' — giving comprehensive coverage of the skill's modes. Not 4: there are no minor gaps; every capability mode of the router is enumerated with a specific verb.

5 / 5

Completeness

The 'what' is clear and detailed, but there is no 'Use when…' clause or equivalent explicit trigger guidance — the rubric caps completeness at 3 in that case. The scenario naming ('take over, continue or hand off') only weakly implies 'when', so this is not 4.

3 / 5

Trigger Term Quality

Good natural coverage: 'deliver changes', 'take over', 'hand off', 'task', 'backlog' are phrases a user would plausibly say. Not 5: internal jargon like 'ready plans', 'exception state' and 'work in the factory' dilutes the natural terms, and common synonyms (e.g. PR, code review, orchestration) are absent.

4 / 5

Distinctiveness Conflict Risk

The 'software factory' orchestration niche with specialist writers and independent verifiers is clearly distinct from typical single-purpose skills. Not 5: broad verbs like 'deliver changes' and 'take over a task' carry some overlap risk with generic delivery, release or handoff skills.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

jbaruch/software-factory

Path

skills/factory/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.