CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conduct

Use before work that needs several lines of thinking whose order, independence, combination, stopping point or destination is not obvious; scale or budget alone is no reason. The user can then say how the lines order, combine, stop and where results go, what they entrusted and kept, and own the method.

Quality

51%

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 ./hyphegesis/skills/conduct/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 contains an unusually rigorous, internally consistent behavioral contract with a real, well-signaled reference file, but it buries its actionable core in a ~500-line Lean formalization that restates the same protocol in four registers. A model reading it gets precise map and gate semantics yet no worked example, and the token cost is enormous relative to the behavioral payload.

Suggestions

Move the Lean formal block to a reference file (e.g. references/formal-contract.md) and keep SKILL.md to a concise prose protocol; the same rules currently appear in the Definition prose, FLOW, MORPHISM, and TOOL GROUNDING comments, and one passage repeats verbatim.

Add one worked example — a short sample map with its gate, a person's correction, and the closing relay/handoff turn — so the contract's execution is concrete rather than inferred from axioms.

Restate the operational sequence as a short numbered checklist with explicit checkpoints (observe pointer and inventory → draft whole-method map → present → gate on correction → relay and hand off in the closing turn → stop), keeping the formal detail behind the reference.

DimensionReasoningScore

Conciseness

The body is ~540 lines dominated by a Lean 4 formal block in which the same content is restated four times over — prose Definition, the FLOW comment, the MORPHISM comment, the TOOL GROUNDING strings, plus a verbatim repetition of "Once it has run, the person can say: this work proceeds this way..." in both the Definition and the ConductedMethod doc comment. The actionable core (draft a whole-method map, show it, gate on the person's correction, relay and hand off) could be carried in a fraction of the tokens. This fits anchor 2 (noticeably verbose, several padded sections); it avoids anchor 1 only because the material is an original formalism rather than explanations of concepts Claude already knows.

2 / 5

Actionability

There is genuinely specific guidance — the `.map` grounding string enumerates exactly what the map must show, `ConductedMethod` lists the handoff fields, and the gate semantics are pinned ("what the map got wrong... or take the method; silence holds and takes nothing") — but there are no worked examples (no sample map, no example taking or handoff turn), and the semantics of every key predicate are deliberately delegated to unstated "your judgment" axioms. This matches anchor 3 (some concrete guidance but incomplete, missing key details); not 4 because a model could not execute this without substantial inference the skill never grounds, and not 2 because the map contents and gating rules are far more concrete than high-level hints.

3 / 5

Workflow Clarity

The sequence is present and coherent — start, observe (pointer + inventory), first map, per-utterance gating, relay/handoff on a taking, then stop — laid out in both the FLOW comment and the `conduct`/`start` definitions, with failure handling specified ("a pointer that does not resolve... is a finding the map shows, with what was tried; it closes nothing"). However, the checkpoints are formal and implicit rather than operational: no explicit verify-then-proceed step, and the flow must be reconstructed from dense Lean recursion and cross-referenced comments. Fits anchor 3 (sequence present but checkpoints missing or implicit); not 4 because the density leaves practical checkpoints and error-recovery loops implicit. This is a dialogue protocol, not a destructive or batch operation, so the workflow-clarity cap does not apply.

3 / 5

Progressive Disclosure

The bundle structure is real and well-used: `references/round-composition.md` exists, is one level deep, and is clearly signaled with occasion-bound load conditions ("Read references/round-composition.md when terminology or wording must persist, content belongs to another turn, or placement relative to the gate is in question"). But the SKILL.md body itself inlines a ~500-line formal block that is precisely the material progressive disclosure would move to a reference, leaving the main file a monolith. Fits anchor 3 (some structure, references present and signaled, but content that should be separate is inline); not 2 because section headers and a properly signaled reference do exist, and not 4 because the dominant content of the file is the inlined block.

3 / 5

Total

11

/

20

Passed

Description

37%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 has a strong, explicit "use when" clause with an unusual but identifiable niche, but it never states what the skill actually does, and its trigger vocabulary is the author's formal idiom rather than natural user phrasing. A reader scanning skill descriptions could not tell what operation they were invoking.

Suggestions

Lead with one sentence of concrete skill actions in third person, e.g. "Drafts the whole method for multi-line work as one map — lines of work, their order and independence, how results combine, stopping points, and destinations — presents it for correction, and hands it off for execution."

Add natural trigger phrases users would actually say, such as "plan how to approach", "sequence this work", "coordinate these workstreams", or "where should these results go".

Cut the abstract tail ("what they entrusted and kept, and own the method") in favor of the concrete capability it restates.

DimensionReasoningScore

Specificity

The description names its domain ("work that needs several lines of thinking whose order, independence, combination, stopping point or destination is not obvious") but never states a concrete action the skill performs — no "drafts", "presents", or "hands off"; the outcome clause ("The user can then say how the lines order, combine, stop...") describes the user's state, not the skill's operations. This matches anchor 2 (domain named, actions minimal or generic); it is above anchor 1 because the triggering conditions are fairly concrete, and below anchor 3 because no concrete skill actions are listed.

2 / 5

Completeness

The "when" is explicit and well-scoped ("Use before work that needs several lines of thinking... scale or budget alone is no reason"), but the "what" is only implied through the user-outcome clause — the skill's actual operation (drafting a method map, presenting it for correction, handing it off) is never stated in the description. Since the rubric requires both and one is strong while the other is weak-to-absent, this sits between anchors 3 and 4; it stays at 3 because scoring only what is explicitly stated, the skill's action is not stated at all.

3 / 5

Trigger Term Quality

Phrases like "several lines of thinking", "order, independence, combination, stopping point or destination", and "own the method" are the author's vocabulary, not words a user would naturally say when needing this skill; common natural phrasings ("plan how to approach", "sequence this work", "coordinate these tasks") are absent. This fits anchor 2 (one or two generic keywords, missing the natural phrases users say); not 3 because even the common variations and synonyms for the planning/coordination domain are missing.

2 / 5

Distinctiveness Conflict Risk

The trigger conditions are unusual and fairly niche ("order, independence, combination, stopping point or destination is not obvious"), giving it some distinctiveness, but the domain — planning and coordinating multi-step work — overlaps heavily with planning, task-decomposition, and orchestration skills, so it could fire in situations where those are more appropriate. Fits anchor 3 (somewhat specific but could still overlap with similar skills); not 4 because the broad planning domain is contested territory with no tie-breaking concrete trigger phrases.

3 / 5

Total

10

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (565 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

jongwony/epistemic-protocols

Path

hyphegesis/skills/conduct/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.