CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ground

Use when a framework, analogy, earlier design or sibling structure is to be carried to a case, or an abstraction tested against its own cases, and what it licenses there is still open — judged from the request, before either side is read and compared; not where what the mapping licenses is already settled, or the user only wants an explanation. The user can then say what carries each conclusion, what would break it, and whether it holds, is blocked, or is open.

Quality

57%

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 ./analogia/skills/ground/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%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 presents an elaborate, internally consistent protocol whose sequence and invariants are genuinely specified, but at extreme token cost: the same rules are restated across five sections, the core guidance is abstract with no worked example, and the huge formal block is inlined rather than pushed to a reference. An executing model gets the philosophy but little concrete help producing an actual assessment.

Suggestions

Move the Lean formal block to a reference file (e.g., references/contract.md) and keep in SKILL.md only the step sequence, the rules, and pointers, cutting the body by roughly two-thirds.

Add one worked example — a short source/target mapping with the correspondences, one check with its defeater, and the resulting verdicts — so the abstract directives become executable.

Eliminate the repeated restatements by choosing one home per rule (the Rules section) and referencing it from FLOW, CONVERGENCE, and the Lean doc comments, and either link references/best-practices.md from the body or fold it into the activation heuristics.

DimensionReasoningScore

Conciseness

The 631-line body restates the same rules many times over — the Lean formal block, the FLOW comment, the CONVERGENCE block, the Protocol section, and the Rules section each re-express 'warrant tracks evidence, never assent', the question-standing rule, and the collection rule. Not 1: the content is a novel protocol rather than explanations of concepts Claude already knows, but the redundancy across five restatements is heavy padding.

2 / 5

Actionability

The guidance stays at the level of abstract directives ('collect to the limit of your reach over what the mapping rests on', 'construct the correspondences') with no worked example of an actual audit, no sample assessment output, and no concrete case showing verdicts in practice. Not 1: the morphism does give a named step sequence (question → collect → construct → check → warrant → judge → surface) and the Intensity table specifies output formats, which is more than pure description — but the executing model is left to infer nearly everything concrete.

2 / 5

Workflow Clarity

A real sequence exists (question read/draft → collect → construct → check → warrant → judge → surface) with the protocol's own check concept serving as an internal validation mechanism and explicit re-read rules on each new utterance. Not 4: the sequence is buried inside a Lean formalization and dense prose, checkpoints are implicit in the contract's semantics rather than stated as operational steps, and there is no error-recovery guidance for the practical workflow.

3 / 5

Progressive Disclosure

Three real reference files exist and the ones referenced are one level deep and clearly signaled ('references/judgments.md' is section-linked from four axioms, 'references/round-composition.md' is gated on a stated occasion). Not 4: references/best-practices.md is never referenced from the body, and the ~560-line Lean formal block — content that clearly belongs in a separate reference file — is inlined wholesale into SKILL.md.

3 / 5

Total

10

/

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 has an explicit and unusually detailed 'Use when…' trigger with clear exclusions, and it conveys outcomes (holds/blocked/open per conclusion). But it is written in dense contract jargon, never states the skill's action directly, and is longer and less scannable than effective descriptions, costing it trigger-term naturalness and specificity.

Suggestions

State what the skill does as a direct third-person action first (e.g., 'Audits whether a framework, analogy, or earlier design actually carries over to a case, reporting for each conclusion whether it holds, is blocked, or is undetermined'), then give the 'Use when…' trigger.

Replace contract jargon ('what it licenses there is still open', 'carried to a case') with phrases users naturally say ('does this pattern apply here', 'is this analogy sound', 'will this design carry over').

Trim the description to roughly two sentences; the current density works against trigger recognition.

DimensionReasoningScore

Specificity

Names the domain (carrying a framework/analogy/abstraction to a case) and a few concrete outcomes ('what carries each conclusion, what would break it, and whether it holds, is blocked, or is open'), but the actions are stated indirectly through what 'the user can then say' rather than as what the skill does, and 'what it licenses there is still open' is abstract. Not 4: it does not list several specific concrete actions the skill performs.

3 / 5

Completeness

Has an explicit 'Use when…' clause with both inclusion and exclusion conditions ('not where what the mapping licenses is already settled, or the user only wants an explanation'), and the second sentence conveys the 'what' via the outcomes the user gets. Not 5: what the skill actually does is never stated as its own action — only inferred from what the user can then say — so the 'what' is indirect rather than concrete.

4 / 5

Trigger Term Quality

Contains some natural keywords users would say ('framework', 'analogy', 'earlier design', 'abstraction'), but leans on jargon like 'licenses', 'carried to a case', and 'tested against its own cases', and misses common phrasings such as 'does this apply here' or 'is this pattern relevant'. Not 4: coverage of natural synonyms and variations is thin relative to the dense contract language.

3 / 5

Distinctiveness Conflict Risk

A clear niche (auditing what an analogical mapping licenses) with distinct trigger conditions and explicit negative triggers ('not where… already settled, or the user only wants an explanation'). Not 5: overlap risk remains with general reasoning/analysis and explanation-type skills, and the abstract phrasing ('what it licenses') does not sharply separate it from adjacent critique skills.

4 / 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 (632 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

jongwony/epistemic-protocols

Path

analogia/skills/ground/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.