CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

elicit

Use when the request itself does not say what result the user wants — it names an area or a wish, such as 'fix this up' or 'make it better', but not what should change; judged from the request, before files or context are looked at to guess it, even where they would suggest a plausible reading. Not where the user's words already settle it. The user can then say 'this is my intent, aligned enough', each value in their own words, what they left open carried.

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./euporia/skills/elicit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%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 elaborate Lean 4 formal contract whose doc comments carry the real instructions, wrapped by a thin layer of directly actionable sections (Mode Activation, Protocol, Intensity, Rules). The actionable guidance that exists is specific, but it is buried in heavily redundant formal prose with no worked example, and the monolithic inline block defeats progressive disclosure despite the one well-signaled reference file.

Suggestions

Move the bulk of the Lean contract into a reference file (e.g. references/contract.md) and keep in SKILL.md a one-screen operational core — the surface/read/resolve loop, the Intensity table, and the Rules — loading the formal block only when the occasion calls for it.

Deduplicate the four restatements of the flow (FLOW comment, MORPHISM, elicit definition, TOOL GROUNDING) into a single canonical sequence, and compress the long single-paragraph doc comments on StandingSupported, Reaches, and coordinates to their carve-out lists.

Add one worked example — a short seed utterance, the first surface composed per the surface entry, and one answer changing the record — so the axiom-level rules are grounded in an executable demonstration.

DimensionReasoningScore

Conciseness

Roughly 340 of the ~385 body lines are a single Lean 4 block whose doc comments restate the same distinctions several times over — the surface flow is described independently in the FLOW comment, the MORPHISM comment, the elicit/start definitions, the TOOL GROUNDING surface entry, and again in Rules ("Round composition", "Focus and record"). Long single-paragraph doc comments (e.g. StandingSupported, Reaches) repeat the same carve-outs multiple ways. This is noticeably verbose with several padded sections (anchor 2); it avoids anchor 1 only because the protocol is novel rather than re-explaining concepts Claude already knows.

2 / 5

Actionability

There is real concrete guidance: the TOOL GROUNDING surface entry specifies exactly what each surface presents ("a one-sentence read-back of the intent as understood... each open coordinate the round shows, with its question, where it comes from... your contrary grounds before the questions"), the Intensity table maps levels to formats, and Mode Activation lists explicit skip conditions. But the actionable core is buried in a formal contract where every operative judgment (aporia, coordinates, StandingSupported, operative, Reaches) is an axiom black box, and no worked example of a surface or exchange is given — some concrete guidance, incomplete in specifics, matching anchor 3.

3 / 5

Workflow Clarity

The sequence exists — detect → surface → readAnswer → converge → seam — and is even implemented structurally in the elicit recursion with explicit branches ([the utterance does not bear on this run] / [aligned enough] / [otherwise]), and the LOOP and CONVERGENCE sections state feedback behavior ("every surface is dialogue", "Demonstrated, not asserted"). However the operational sequence must be reconstructed from four scattered restatements rather than read as one coherent flow, and checkpoints like convergence evidence are implicit rather than step-anchored — sequence present with implicit checkpoints, matching anchor 3 rather than the mostly-checkpointed anchor 4.

3 / 5

Progressive Disclosure

The one bundle reference (references/round-composition.md) is well done: it exists, is one level deep with no nested references, and is conditionally loaded under clearly stated occasions ("when a term must remain stable across the session, wording must travel unchanged, or material belongs to another round or trace") — that part sits at anchor 4-5 quality. But the SKILL.md itself inlines a ~340-line formal block whose reading-guidance preamble targets a specialist reader, while the actionable sections (Protocol, Intensity, Rules) total ~40 lines — content that arguably belongs in a separate contract file is inlined monolithically, matching anchor 3's 'content that should be separate is inline'.

3 / 5

Total

11

/

20

Passed

Description

62%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 well-targeted, boundary-aware trigger description that clearly says when to invoke the skill and when not to, with quoted natural trigger phrases. Its main weakness is that the capability side is conveyed only as an outcome — the elicitation action itself is never named — and synonym coverage of vague-request phrasings is thin.

Suggestions

State the skill's action explicitly in one clause, e.g. 'Surfaces the decisions an intent turns on, one at a time, until the user recognizes the intent as theirs', so the 'what' does not have to be inferred from the closing condition.

Broaden natural trigger phrasings beyond the two quoted examples — e.g. 'improve this', 'clean this up', 'not sure what I want' — to improve keyword coverage for vague-request detection.

Trim the trailing mechanics ("each value in their own words, what they left open carried") into the what-clause so the description reads as capability + trigger rather than trigger + end-state.

DimensionReasoningScore

Specificity

The description quotes concrete trigger phrases ("'fix this up' or 'make it better'") and concretely characterizes the activating condition ("names an area or a wish... but not what should change"), but it never names what the skill actually does — the action must be inferred from the outcome clause ("The user can then say 'this is my intent, aligned enough', each value in their own words, what they left open carried"). It names the domain with 1-2 concrete behaviors, matching anchor 3, not the several specific actions anchor 4 requires.

3 / 5

Completeness

The 'when' is explicit and highly specific ("Use when the request itself does not say what result the user wants... Not where the user's words already settle it") — stronger than anchor 4's example — and the 'what' is present through the outcome the skill produces (values elicited in the user's own words, residual carried). It stays below anchor 5 because the skill's action (surfacing the decisions an intent turns on) is never stated as an action, only implied by the end state.

4 / 5

Trigger Term Quality

It includes two genuinely natural phrases users say with vague requests ("fix this up", "make it better") plus descriptive paraphrases of the trigger state ("does not say what result the user wants", "names an area or a wish"), but misses common variations such as "improve this", "clean this up", or "not sure what I want". Relevant keywords are present with notable synonym gaps, matching anchor 3 rather than the broader coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The trigger carves a clear niche — requests that express a wish without a result — and the negative boundary clause ("Not where the user's words already settle it") plus the judgment rule ("judged from the request, before files or context are looked at") reduce misfiring on concrete requests. Minor overlap risk remains with generic clarify-requirements skills triggered by phrases like "make it better", matching anchor 4 rather than the minimal-conflict profile of anchor 5.

4 / 5

Total

14

/

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

jongwony/epistemic-protocols

Path

euporia/skills/elicit/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.