CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

inquire

Use before gathering context — opening a link or issue, reading records, threads, documents, files or state to establish what is the case, a status check or a claim the user makes in passing included — even where the agent could gather it itself; not for a command whose targets are named or already in context and that claims nothing beyond them. The user can then recognize what was settled and from where, what rests on weak or unreached ground, and what only they decide.

Quality

64%

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 ./aitesis/skills/inquire/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

48%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 contract's sequence and checkpoints are genuinely specified — the MORPHISM pipeline, the Reaches reopening rule, and the per-completion convergence evidence give the workflow real structure — but nearly everything is written as formal Lean with redundant prose restatements, at roughly ten times the token cost the instruction content justifies. The absence of any worked example of a user-facing relay round leaves the protocol's realization dependent on the reader interpreting the formalism.

Suggestions

Replace or drastically compress the Lean block: the operative rules (collect to the limit of your own reach, cite settled facts, keep held values open for the person, show reach for what is unreached) fit in ~30 lines of prose; the current doc comments also duplicate content already in references/judgments.md.

Add one concrete worked example — a short sample relay round showing an open uncertainty with its reach, a settled fact with its citation, and a detection — so the "user-facing realization" is executable without interpreting the formal spec.

Move the formal contract to a reference file and keep a concise overview in SKILL.md with explicit load conditions, and surface the buried `references/judgments.md` §Collection pointer in a visible section instead of a mid-block Lean comment.

DimensionReasoningScore

Conciseness

The body is dominated by a ~340-line Lean 4 block whose prose doc comments restate the same contract three times over (axiom docs in SKILL.md, then again in references/judgments.md and references/round-composition.md), and the FLOW/MORPHISM/CONVERGENCE comments restate what the definitions already encode — several padded, redundant sections for a behavioral protocol whose rules fit in a fraction of the space.

2 / 5

Actionability

Some guidance is concrete (the grounding table specifies what each op presents, and rules like "name a detection as one, on its own line" are specific), but there is no worked example of an actual relay round, and the user-facing realization defers to interpreting the formal spec ("Present what `surface` names and proceed"), leaving key execution details missing.

3 / 5

Workflow Clarity

The sequence is explicitly written (MORPHISM: "scan → collect → read → relay → fuse"), with checkpoints present: the Reaches branch in `inquire` governs reopening, and CONVERGENCE names the evidence required at each completion ("for every uncertainty raised, how it stands — settled, with its citation… open, with its reach"). Minor gaps come from the practical steps being scattered across formal code and comments rather than stated as an executable sequence.

4 / 5

Progressive Disclosure

Both references (references/judgments.md, references/round-composition.md) are real, one level deep, and conditionally loaded ("Read `references/round-composition.md` before composing when…"), but the body is a monolithic inline 340-line formal block of the size that belongs behind disclosure, and the judgments.md pointer is buried mid-block inside a Lean doc comment ("Direction: `references/judgments.md` §Collection") rather than clearly signaled.

3 / 5

Total

12

/

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.

The description answers "when" unusually well, with concrete trigger situations and an explicit exclusion boundary, but answers "what" only abstractly — the skill's actual action (collect reachable context itself, then hand back open questions) must be inferred from outcomes like "recognize what was settled and from where". Trigger terms are relevant artifact nouns but miss the natural user phrasings that would invoke it.

Suggestions

State the core action concretely, e.g. "Collects every piece of context the agent can reach on its own, then hands back what remains open as the user's own unknown with its sources" — replacing abstract phrases like "establish what is the case".

Add the natural user phrasings that should trigger it ("check this", "verify this", "what do we know about…", "is this still the case") alongside the artifact nouns.

DimensionReasoningScore

Specificity

Trigger situations are concrete ("opening a link or issue, reading records, threads, documents, files or state", "a status check or a claim the user makes in passing"), but the capability itself is stated abstractly ("establish what is the case", "recognize what was settled and from where, what rests on weak or unreached ground"), so it names the domain with only 1-2 concrete actions rather than several specific ones.

3 / 5

Completeness

Both halves are explicit: "Use before gathering context" with concrete trigger situations and even a negative boundary ("not for a command whose targets are named or already in context") answers "when" strongly, while "to establish what is the case" plus the outcome sentence answers "what" — but the "what" is fuzzy rather than a concrete action list, so it falls short of the 5 anchor.

4 / 5

Trigger Term Quality

Artifact nouns like "link", "issue", "records", "threads", "documents", "files", "state", and "status check" are relevant, but the natural phrases a user would actually say when needing this skill ("check this", "verify", "is this still true", "what do we know about X") are missing, leaving keyword coverage partial.

3 / 5

Distinctiveness Conflict Risk

The pre-gathering timing and the explicit exclusion clause carve a distinct niche with low wrong-skill trigger risk, though the broad scope of "reading records, threads, documents, files or state to establish what is the case" leaves minor overlap with general research/verification skills.

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

aitesis/skills/inquire/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.