CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

induce

Use when the user senses that cases at hand share something no one has named yet, or that a name in use no longer says what its cases show, and wants it named; applying a fixed meaning to a disputed case is not this. The user can then name it, say which cases it takes in and leaves out, and recognize it as serving their goal.

Quality

60%

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 ./periagoge/skills/induce/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 specifies an unusually rigorous and internally consistent dialogical protocol with a genuinely well-signaled reference file, but it is severely overweight: a ~550-line Lean formal block inlined in SKILL.md, duplicated between its doc comments and the Protocol prose, with no worked example of the sheet it mandates and no consolidated step-by-step procedure. The structure is recoverable only with substantial inference effort.

Suggestions

Move the Lean formal block to a reference file (e.g. references/contract.md) and keep in SKILL.md a short summary of the judgments it fixes, cutting the duplication between the block's doc comments and the Protocol prose.

Add one compact worked example — a mini sheet with goal, working candidate, one cross-view row, and the move — so the mandated deliverable's format is unambiguous without inferring it from axiom annotations.

Consolidate the activation → sheet → response → recognition sequence into a short numbered procedure in the Protocol section, surfacing `notActivated`, `Overturned`, and the closing judgment as explicit checkpoints.

DimensionReasoningScore

Conciseness

The ~600-line body carries a ~550-line Lean 4 block whose doc comments are restated nearly verbatim in the Protocol prose (e.g. "A reading you would no longer hold stays in the cross view until the user sets it aside" appears in the `readings` axiom and again in the sheet section), and the prose's long nested em-dash clauses force re-reading. This is noticeably verbose with duplicated sections rather than severely padded explanation of known concepts, matching anchor 2 rather than 1 or 3.

2 / 5

Actionability

The sheet deliverable is concretely structured ("Each sheet opens with any case you found... Then the goal... Then the cross view, one row per live reading... Then a cases section"), giving real guidance for an instruction-only skill, but there is no worked example or template of a sheet, and operational rules are buried as formal `axiom` annotations the practitioner must infer from. Some concrete but incomplete guidance matches anchor 3 rather than 4 (a key executable detail — what a sheet looks like — is missing).

3 / 5

Workflow Clarity

A sequence exists (the FLOW comment's start → notActivated → sheet → per-utterance branches) and checkpoints exist as formal readings (`notActivated`, `Overturned`, `ClosingSupported`), but the operational sequence is scattered across the Lean comment block, Mode Activation, and Protocol sections with no consolidated step list, leaving checkpoints implicit for the practitioner. Anchor 3 fits: steps are present but the reader must reconstruct the ordered procedure and its verification points.

3 / 5

Progressive Disclosure

One well-signaled, one-level-deep reference exists with explicit load conditions ("Read `references/round-composition.md` before composing when terminology must remain stable..."), which is good practice, but the ~550-line formal contract is inlined wholesale in SKILL.md where an overview plus a reference file would serve. Some structure with clear signaling but bulk content inline matches anchor 3 rather than 4 (the monolithic inline block is a major organization gap) or 2 (the reference is present, clearly signaled, and shallow).

3 / 5

Total

11

/

20

Passed

Description

61%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 an explicit and well-bounded 'Use when' clause occupying a genuinely distinctive niche, but the 'what' is phrased as the user's outcome rather than the skill's concrete actions, and natural trigger phrasing users would actually say is only partially covered. It is functional and unambiguous for activation but abstract and stilted in register.

Suggestions

State the concrete actions the skill performs (e.g. "Draws a sheet that crosses a working name and rule with the user's goal and every live reading of the cases, marking each value as set by the user, taken, or still a proposal") instead of describing only the user's outcome.

Add natural trigger synonyms users would actually say, such as "what do these cases have in common", "help me name this concept/pattern", or "this term no longer fits what we're doing".

Keep the negative boundary (it is effective) but pair it with a plain-language restatement of the positive trigger so the boundary is legible without the philosophical register.

DimensionReasoningScore

Specificity

The 'what' is stated only as the user's outcome ("The user can then name it, say which cases it takes in and leaves out, and recognize it as serving their goal") with no concrete actions the skill itself performs. It names a distinctive domain but the actions are minimal and generic, matching anchor 2 rather than 1 (a specific activity is discernible) or 3 (no concrete skill-side action is named).

2 / 5

Completeness

The 'when' is explicit ("Use when the user senses that cases at hand share something no one has named yet..." plus the negative boundary "applying a fixed meaning to a disputed case is not this"), and a 'what' is present but abstract — an outcome statement rather than a concrete description of what the skill does. Both are explicitly present with an improvable 'what', matching anchor 4 rather than 5 (the 'what' lacks concrete actions) or 3 (neither is missing).

4 / 5

Trigger Term Quality

Phrases like "cases at hand share something no one has named yet", "a name in use no longer says what its cases show", and "wants it named" map to plausible user utterances, but common variations and synonyms are missing (e.g. "what do these examples have in common", "help me name this concept", "this term no longer fits"). Some relevant keywords without full natural coverage fits anchor 3, below 4 for thin and stilted coverage, above 2 because several phrases do connect to real user language.

3 / 5

Distinctiveness Conflict Risk

The description carves a clear niche — naming an abstraction shared by concrete cases whose name is unsettled — with distinct triggers and an explicit negative boundary ("applying a fixed meaning to a disputed case is not this") separating it from definition-application skills. Minimal overlap with any other skill's triggers, matching anchor 5.

5 / 5

Total

14

/

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 (600 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

jongwony/epistemic-protocols

Path

periagoge/skills/induce/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.