production-scheduling

Codified expertise for production scheduling, job sequencing, line balancing, changeover optimization, and bottleneck resolution in discrete and batch manufacturing. Informed by production schedulers with 15+ years experience. Includes TOC/drum-buffer-rope, SMED, OEE analysis, disruption response frameworks, and ERP/MES interaction patterns. Use when scheduling production, resolving bottlenecks, optimizing changeovers, responding to disruptions, or balancing manufacturing lines.

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/production-scheduling/SKILL.md

Quality

Content

31%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 content is a well-written domain reference but reads as an inlined knowledge dump rather than an executable skill: it is verbose, provides almost no runnable code or tooling commands, and keeps everything in one monolithic file with no progressive disclosure. Workflow sequencing is decent but lacks concrete validation feedback loops.

Suggestions

Move the bulk of the Core Knowledge, Edge Cases, and escalation/communication templates into separate reference files (e.g. references/changeover.md, references/disruption-response.md, references/communication-templates.md) and keep SKILL.md a lean overview with one-level-deep links.

Add executable artifacts: runnable scripts or commands for the setup-matrix / nearest-neighbor / 2-opt optimization, a validation step for generated schedules (e.g. a feasibility check against capacity and labor matrices), and a clear validate→fix→re-run loop in the workflow.

Trim definitional background Claude already knows (OEE formulas, MRP assumptions, SMED phase explanations, shift-pattern definitions) to the decision-relevant essentials so the body respects token budget.

Dimension	Reasoning	Score
Conciseness	The ~240-line body explains concepts and background a competent model either knows or does not need restated at length (e.g. defining OEE formulas, what MRP assumes, Shingo's SMED phases, shift-pattern definitions) with padded prose throughout; it is noticeably verbose with many sections that could be trimmed to decision rules, matching the score-2 anchor.	2 / 5
Actionability	Despite the operational subject matter, almost no executable guidance is provided: there is no actual code, no commands, no tooling calls, and the algorithms (nearest-neighbor heuristic, 2-opt, setup-matrix optimization) are named but not given as runnable steps a model could execute, leaving only high-level hints — matching the score-2 anchor.	2 / 5
Workflow Clarity	The 'How It Works' and decision-framework sections give a reasonable numbered sequence, and disruption response includes freeze/lock and 30-minute communication checkpoints, but the broader batch/disruption workflows lack explicit validate-then-fix feedback loops and most steps lack concrete verification, so it sits at 'steps listed but validation gaps' rather than the capped-below-3 or the 4/5 levels.	3 / 5
Progressive Disclosure	It is a single monolithic file with no bundle references at all — all of the core knowledge, edge-case playbooks, escalation tables, and templates are inlined in SKILL.md rather than split into one-level-deep reference files, matching the score-2 anchor ('content that clearly belongs in separate files is inlined').	2 / 5
	Total	9 / 20 Passed

Description

80%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 strong: it answers both what and when with concrete trigger phrases and stakes out a distinctive, well-scoped niche. Its only weakness is trigger-term naturalness, where the phrasing leans technical and misses some everyday synonyms a user might actually say.

Suggestions

Add more natural, user-spoken trigger phrases and synonyms (e.g. "shop floor scheduling", "work order sequencing", "machine downtime", "schedule conflicts") so it surfaces when schedulers describe problems in their own words.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas — "production scheduling, job sequencing, line balancing, changeover optimization, and bottleneck resolution" plus named frameworks (TOC/drum-buffer-rope, SMED, OEE) — with only minor gaps in coverage versus the score-5 anchor, so it sits just below comprehensive.	4 / 5
Completeness	It clearly states what it does ("Codified expertise for production scheduling...") and explicitly gives a 'when' clause with concrete triggers ("Use when scheduling production, resolving bottlenecks, optimizing changeovers, responding to disruptions, or balancing manufacturing lines"), matching the score-5 anchor.	5 / 5
Trigger Term Quality	It includes relevant natural terms like "scheduling production", "resolving bottlenecks", and "optimizing changeovers", but the trigger phrasing is fairly formal/technical and omits common user-level synonyms or variations (e.g. "shop floor", "work orders", file types), so it matches 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche — discrete/batch manufacturing production scheduling with named methodologies (DBR, SMED, OEE, ERP/MES) — and its triggers are domain-specific enough to avoid firing for unrelated skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: skills/production-scheduling/SKILL.md
Commit: d8409a4

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.