Tessl • The management layer for AI agent skills

SkillPublic

drydock

Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards), seeded as two faces on day one (CLAUDE.md + GLOSSARY.md) with every other surface appearing on first use, so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.

Quality

67%

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/drydock/SKILL.md

Quality

Content

63%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 well-sequenced, highly actionable skill body whose verbatim templates and guardrails make it executable in practice, held back by monolithic inline seed exemplars (three full language companions plus a machine contract) that belong in reference files and by prose that could be tightened considerably without losing information.

Suggestions

Move the seed companions (A/B en, zh-Hans, zh-Hant) and the document-language contract JSON into references/ files (e.g. references/seeds.md, references/language-contract.md), keeping SKILL.md as an overview with one-level-deep, clearly signaled links.

Provide the shipyard-audit.mjs seed content (or a starter implementation in scripts/) since the skill instructs running it without ever defining what to seed into it.

Tighten the longest compound sentences (the legacy CONTEXT.md migration rules and CLAUDE.md-rewrite paragraphs) into short checkable rules, and state the first-use trigger once per surface instead of repeating it in both the scaffold table and the governance-loop section.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with no explanations of concepts Claude already knows, but at ~365 lines it contains long compound sentences (e.g. the legacy CONTEXT.md migration paragraph), repeated first-use-trigger statements across sections 3 and 4, and three full inline language companions of which any single invocation renders at most one.	3 / 5
Actionability	Guidance is mostly executable: verbatim seed templates with exact filenames, an ordered language-resolution procedure, and 'node scripts/shipyard-audit.mjs [repoRoot]' with documented exit codes. Minor gaps: the audit script's content is never provided (it must be authored at first use), and the guardrail hook command is a '<confirm-before-destructive-git>' placeholder.	4 / 5
Workflow Clarity	A clear five-step sequence (Detect → Resolve language → Scaffold → Wire governance loop → Report) with checkpoints such as 'Report the map first, then act', 'stop before writing localized artifacts', and --check's exit-code contract; migration renames carry guardrails (git mv, byte-for-byte preservation, never-clobber). Not 5 because there is no explicit post-scaffold verification step.	4 / 5
Progressive Disclosure	Section structure and navigation are good (When to Use, When Not to Use, numbered workflow, --check mode), but there are no bundle files at all: the document-language contract JSON and the three seed companions clearly belong in references/ files, leaving ~365 lines monolithic where a well-signaled one-level reference split is warranted.	3 / 5
	Total	14 / 20 Passed

Description

58%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.

A specific, distinctive description with concrete artifacts and flags, weakened by the absence of an explicit 'Use when...' trigger clause and by metaphor-heavy phrasing that crowds out the natural keywords users would actually say when they need this skill.

Suggestions

Add an explicit trigger clause, e.g. 'Use when starting a repo that humans and agents will both build on, or when onboarding new contributors by reading rather than asking.'

Include natural trigger keywords users would say — 'set up', 'initialize', 'onboarding', 'bootstrap' — alongside the existing file names and flags.

Trim the shipyard metaphor in the description so concrete actions (seed CLAUDE.md and GLOSSARY.md, defer other surfaces to first use, audit drift with --check) dominate.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions with named artifacts — 'seeded as two faces on day one (CLAUDE.md + GLOSSARY.md)', 're-run with --check to audit drift' — but the actions are wrapped in heavy shipyard metaphor ('Lay the keel'), leaving minor gaps in coverage.	4 / 5
Completeness	The 'what' is clear (a 4-pillar shared environment seeded as two files), but there is no explicit 'Use when...' trigger clause; 'when' is only weakly implied by 'Run once per repo; re-run with --check to audit drift', which caps completeness at 3 per the judging guideline.	3 / 5
Trigger Term Quality	Relevant keywords are present ('any repo', 'CLAUDE.md', 'GLOSSARY.md', '--check', 'audit drift') but common natural phrasings a user would say — 'set up', 'initialize', 'onboard', 'bootstrap a repo' — are absent, and the maritime metaphor does not match user language.	3 / 5
Distinctiveness Conflict Risk	The niche is distinct — repo harness initialization with glossary authority and a --check drift-audit mode — with only minor overlap risk against generic repo-init/onboarding skills; it would not naturally trigger for the wrong skill.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/drydock/SKILL.md
Revision: f2dffcc

Reviewed: 16 days ago

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.

drydock

Table of Contents

Is this your skill?