CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lexicographer

Looks words up in FEED, the first-party enough english dictionary, and writes the user's own dictionary entries with them — a coinage, a family word, a term from their field, a private name for a thing, or their own version of a word FEED already has — one column at a time, in FEED's house style. Use for "is X a word", "what does X mean", "look up X", "add X to my dictionary", "put this word in the dictionary", "I made up a word", "my family says X", "fix the entry for X", "my version of X", "define X for me and keep it". Not for translating text (that is the translator skill) and not for spelling or grammar checks of a document (that is analyzer's proofread).

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

Excellent single-file instructional content: dense, non-obvious house style with no filler, exact tool and column contracts, and a conversational workflow with an explicit confirmation gate before any write. The only structural blemishes are the stray trailing metadata line and the inline column reference that could live in a separate file if the bundle grew.

Suggestions

Move or delete the trailing "enough-tooltip-text" line so the body ends on the update/remove guidance instead of stray metadata.

If the bundle grows, split the per-column specification (domain list, frequency bands, forms labels) into a references file and keep SKILL.md as the conversational workflow plus a pointer.

DimensionReasoningScore

Conciseness

Every section carries house style Claude could not know ("/ər/ for the unstressed r-vowel", the 45-domain enumeration, the 0–8 frequency bands, forms labels) with zero padding or explanation of known concepts. Lean throughout; not 4 because there is no over-explanation left to trim.

5 / 5

Actionability

Exact tool names (`dict_lookup`, `dict_add_entry`, `dict_update_entry`), per-column formats with inline examples (`glimmerwicks /ˈɡlɪmərˌwɪks/ pl.`), a required-fields rule, and a complete worked example entry make the guidance fully executable for an instruction-only skill. Not 4 because the worked example plus per-column specs cover the common cases end to end.

5 / 5

Workflow Clarity

"The conversation" lays out a clear 6-step sequence (look up first → say if FEED has it → draft → ask → confirm → add) with an explicit validation checkpoint: "Confirm in plain words before writing... Wait for a yes." Writes are non-destructive (user's own dictionary only), so the destructive-cap does not apply, and the confirm-before-write gate plus mandatory pre-lookup satisfy the top anchor.

5 / 5

Progressive Disclosure

Sections are well organized (conversation, columns, a whole worked entry) with no nested references, but the skill exceeds 50 lines with the full column specification inline, and the trailing "enough-tooltip-text: ..." line sits outside any section as stray clutter. Between the 4 and 5 anchors: structure is good but not impeccable.

4 / 5

Total

19

/

20

Passed

Description

95%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 strong description: it states concrete capabilities in third person, enumerates the entry types it handles, gives an explicit and comprehensive "Use for" trigger list, and actively disambiguates adjacent skills with a "Not for" clause. The only shortfall is that the update-an-entry capability is conveyed through a trigger phrase rather than stated as an action.

Suggestions

State the update capability explicitly alongside lookup and write (e.g. "and updates entries the user already has") so all three tool-backed actions appear as actions, not just as triggers.

DimensionReasoningScore

Specificity

Concrete actions are named — "Looks words up in FEED", "writes the user's own dictionary entries", "one column at a time, in FEED's house style" — with five entry types enumerated. Minor gap: updating an existing entry is only implied via the trigger "fix the entry for X", keeping it below the comprehensive 5 anchor.

4 / 5

Completeness

Explicitly answers what ("Looks words up in FEED... and writes the user's own dictionary entries") and when ("Use for 'is X a word'..." with concrete trigger phrases), matching the top anchor. It even adds explicit anti-triggers ("Not for translating text...").

5 / 5

Trigger Term Quality

"is X a word", "what does X mean", "look up X", "add X to my dictionary", "I made up a word", "my family says X", "fix the entry for X", "my version of X" are exactly the natural phrases a user would say, covering synonyms and variations comprehensively. Not 4 because no common natural phrasing for this task is missing.

5 / 5

Distinctiveness Conflict Risk

Clear dictionary-lookup/entry-authoring niche with distinct triggers, plus explicit disambiguation from neighboring skills: "Not for translating text (that is the translator skill) and not for spelling or grammar checks of a document (that is analyzer's proofread)". Minimal conflict risk.

5 / 5

Total

19

/

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

0gsd/enough

Path

defaults/skills/lexicographer/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.