ask-navigator

Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it produces decisions, never deliverables.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ask-navigator/SKILL.md

Quality

Content

70%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 tightly written process skill with genuinely strong workflow sequencing — signature checkpoints, feedback loops, stop conditions, and completion definitions are all explicit. Its weaknesses are moderate redundancy across sections and a fully monolithic body with no reference files despite containing several reference-sized blocks.

Dimension	Reasoning	Score
Conciseness	The prose is dense and rule-per-line with no padding about concepts Claude already knows, but there is real redundancy: 'produces decisions, never deliverables' and the one-ticket-per-session cadence are each restated three times, and out-of-scope rules repeat across Chart (step 3), Work (step 5), and the fog-or-ticket section. Mostly efficient but could be tightened — anchor 3, not 4, because the repetition is more than minor trimming.	3 / 5
Actionability	Concrete and specific throughout: exact commands ('node scripts/shipyard-audit.mjs'), exact paths ('.omc/wayfinder/<map-slug>/map.md', 'docs/adr/NNNN-<slug>.md', 'docs/research/<ticket-slug>.md'), exact label ('navigator:map'), a ticket-type table with resolution mechanisms, and a complete map-body template. Not 5 because many steps (frontier rounds, sediment routing) rest on judgment calls rather than copy-paste-ready guidance, and the audit script belongs to another skill's bundle.	4 / 5
Workflow Clarity	Both workflows are numbered with explicit validation checkpoints — W1/W2 captain signatures, 'iterate until signed', the fog test as an entry gate, the no-fog early exit ('stop and recommend /launch'), claim-before-work ordering, and a completion definition per session type. Feedback loops for error recovery (invalidated tickets updated or deleted, beyond-destination tickets closed into Out of scope) are explicit — matches anchor 5.	5 / 5
Progressive Disclosure	Headers organize the ~135-line body well, but there are no bundle files at all — everything is inline, including reference-worthy blocks (the map-body template, the ticket-type table, sediment routing rules) that could live in one-level-deep reference files. Anchor 3: some structure, but content that could be separate is inline; not 4 because no external file navigation exists and the single file is long.	3 / 5
	Total	15 / 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.

The description communicates a distinct and fairly specific capability, but the heavy shipyard metaphor crowds out natural trigger language and the 'when to use' condition survives only as a parenthetical gloss. It reads more like in-ecosystem doctrine than a user-facing trigger description.

Suggestions

Add an explicit trigger clause in plain language, e.g. 'Use when the goal is still fuzzy — the destination can't be stated in one sentence or the first decisions can't be named — or when launch's fog gate hands over residual questions.'

Reduce metaphor density: keep 'navigator' once as a label, but state the core actions in plain terms ('break an unclear effort into decision tickets on the issue tracker') so users' own words can match.

Include natural synonyms users would say — 'fuzzy idea', 'unclear requirements', 'don't know where to start', 'break down this project' — alongside the domain terms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'chart a foggy effort... into a map of decision tickets on the repo's issue tracker', 'work the frontier one ticket per session', 'hand the collapsed decisions to /launch as a mission brief' — but the shipyard metaphor ('Shipyard's navigator', 'wayfinding') veils them and coverage has minor gaps. Not 5 because the actions aren't comprehensively stated in plain operational terms; not 3 because it goes well beyond 1-2 actions.	4 / 5
Completeness	The 'what' is clear (charts decision-ticket maps, works them one per session, hands off a mission brief), but the 'when' exists only as the parenthetical '(destination unclear, questions not yet stateable)' — no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 3. Not 2 because both what and a weak when are present.	3 / 5
Trigger Term Quality	Some relevant keywords ('destination unclear', 'questions not yet stateable', 'decision tickets', 'issue tracker') but the natural phrases a user would actually type ('fuzzy idea', 'unclear requirements', 'break this project down', 'figure out what to build') are missing. Jargon like 'frontier' and 'wayfinding' isn't user-spoken language.	3 / 5
Distinctiveness Conflict Risk	'Produces decisions, never deliverables' plus the explicit '/launch' handoff carve a clear niche and bound it against its sibling skill. Not 5 because the abstract framing ('foggy effort', 'destination unclear') could plausibly match generic planning or task-breakdown skills; not 3 because the delivery boundary is stated explicitly.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/ask-navigator/SKILL.md
Commit: dc7ba1d

Reviewed: 3 days 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.